Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark
Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels. State-of-the-art object detectors do not provide satisfactory results on tiny objects due to the lack of supervision from discriminative features. Our key observation is that the Intersection...
Saved in:
| Published in | ISPRS journal of photogrammetry and remote sensing Vol. 190; pp. 79 - 93 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.08.2022
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0924-2716 1872-8235 |
| DOI | 10.1016/j.isprsjprs.2022.06.002 |
Cover
Loading…
| Abstract | Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels. State-of-the-art object detectors do not provide satisfactory results on tiny objects due to the lack of supervision from discriminative features. Our key observation is that the Intersection over Union (IoU) metric and its extensions are very sensitive to the location deviation of the tiny objects, which drastically deteriorates the quality of label assignment when used in anchor-based detectors. To tackle this problem, we propose a new evaluation metric dubbed Normalized Wasserstein Distance (NWD) and a new RanKing-based Assigning (RKA) strategy for tiny object detection. The proposed NWD-RKA strategy can be easily embedded into all kinds of anchor-based detectors to replace the standard IoU threshold-based one, significantly improving label assignment and providing sufficient supervision information for network training. Tested on four datasets, NWD-RKA can consistently improve tiny object detection performance by a large margin. Besides, observing prominent noisy labels in the Tiny Object Detection in Aerial Images (AI-TOD) dataset, we are motivated to meticulously relabel it and release AI-TOD-v2 and its corresponding benchmark. In AI-TOD-v2, the missing annotation and location error problems are considerably mitigated, facilitating more reliable training and validation processes. Embedding NWD-RKA into DetectoRS, the detection performance achieves 4.3 AP points improvement over state-of-the-art competitors on AI-TOD-v2. Datasets, codes, and more visualizations are available at: https://chasel-tsui.github.io/AI-TOD-v2/. |
|---|---|
| AbstractList | Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels. State-of-the-art object detectors do not provide satisfactory results on tiny objects due to the lack of supervision from discriminative features. Our key observation is that the Intersection over Union (IoU) metric and its extensions are very sensitive to the location deviation of the tiny objects, which drastically deteriorates the quality of label assignment when used in anchor-based detectors. To tackle this problem, we propose a new evaluation metric dubbed Normalized Wasserstein Distance (NWD) and a new RanKing-based Assigning (RKA) strategy for tiny object detection. The proposed NWD-RKA strategy can be easily embedded into all kinds of anchor-based detectors to replace the standard IoU threshold-based one, significantly improving label assignment and providing sufficient supervision information for network training. Tested on four datasets, NWD-RKA can consistently improve tiny object detection performance by a large margin. Besides, observing prominent noisy labels in the Tiny Object Detection in Aerial Images (AI-TOD) dataset, we are motivated to meticulously relabel it and release AI-TOD-v2 and its corresponding benchmark. In AI-TOD-v2, the missing annotation and location error problems are considerably mitigated, facilitating more reliable training and validation processes. Embedding NWD-RKA into DetectoRS, the detection performance achieves 4.3 AP points improvement over state-of-the-art competitors on AI-TOD-v2. Datasets, codes, and more visualizations are available at: https://chasel-tsui.github.io/AI-TOD-v2/. |
| Author | Xu, Chang Yu, Huai Yang, Wen Wang, Jinwang Xia, Gui-Song Yu, Lei |
| Author_xml | – sequence: 1 givenname: Chang surname: Xu fullname: Xu, Chang email: xuchangeis@whu.edu.cn organization: School of Electronic Information, Wuhan University, Wuhan 430072, China – sequence: 2 givenname: Jinwang surname: Wang fullname: Wang, Jinwang email: jwwangchn@whu.edu.cn organization: School of Electronic Information, Wuhan University, Wuhan 430072, China – sequence: 3 givenname: Wen surname: Yang fullname: Yang, Wen email: yangwen@whu.edu.cn organization: School of Electronic Information, Wuhan University, Wuhan 430072, China – sequence: 4 givenname: Huai surname: Yu fullname: Yu, Huai email: yuhuai@whu.edu.cn organization: School of Electronic Information, Wuhan University, Wuhan 430072, China – sequence: 5 givenname: Lei surname: Yu fullname: Yu, Lei email: ly.wd@whu.edu.cn organization: School of Electronic Information, Wuhan University, Wuhan 430072, China – sequence: 6 givenname: Gui-Song surname: Xia fullname: Xia, Gui-Song email: guisong.xia@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan 430072, China |
| BookMark | eNqNkM1LxDAQxYMouH78DebopTXNbttU8LD4DYIXxZthmkw1tZuumajoX29kxYMXPcwMA-89eL8ttu5Hj4ztFSIvRFEd9LmjZaA-TS6FlLmociHkGpsUqpaZktNynU1EI2eZrItqk20R9UKIoqzUhN2fYEQTnX_gab3zse3TS9x5DhgcDNwt4AHpkM-5H8MCBveBlt8BEQaKmHTWUQRvkIO3HLjHN96iN48LCE87bKODgXD3-26z27PTm-OL7Or6_PJ4fpWZ6UzFrDHQ1EpKWUow2FjbolAKsLAzK6Atp2UHQtam7WZ1J6vOgDG2VE1XV03ZKjXdZvur3GUYn1-Qol44MjgM4HF8IZ2aK6kqJcskrVdSE0aigJ1ehtQxvOtC6C-iutc_RPUXUS0qnYgm59Evp3ERoht9DOCGf_jnKz8mEq8OgybjEim0LiTo2o7uz4xPYJqcwQ |
| CitedBy_id | crossref_primary_10_1109_TGRS_2024_3486751 crossref_primary_10_3788_LOP241506 crossref_primary_10_1109_TPAMI_2023_3290594 crossref_primary_10_1109_TGRS_2023_3299636 crossref_primary_10_1109_TMM_2023_3305120 crossref_primary_10_1109_TGRS_2024_3510948 crossref_primary_10_3390_app13169438 crossref_primary_10_1109_TGRS_2024_3452175 crossref_primary_10_1016_j_dsp_2024_104957 crossref_primary_10_1109_ACCESS_2024_3401397 crossref_primary_10_1117_1_JRS_18_034521 crossref_primary_10_1016_j_isprsjprs_2024_01_005 crossref_primary_10_11834_jig_221202 crossref_primary_10_1109_TGRS_2024_3382099 crossref_primary_10_1109_TGRS_2025_3525720 crossref_primary_10_1111_phor_12446 crossref_primary_10_3390_electronics13245014 crossref_primary_10_1109_TGRS_2024_3386735 crossref_primary_10_1016_j_imavis_2024_105262 crossref_primary_10_1007_s00530_025_01738_0 crossref_primary_10_1109_TIM_2023_3334348 crossref_primary_10_1109_TCSVT_2024_3485548 crossref_primary_10_1016_j_isprsjprs_2024_09_027 crossref_primary_10_1109_ACCESS_2024_3498057 crossref_primary_10_3390_smartcities7040086 crossref_primary_10_1038_s41598_024_79132_5 crossref_primary_10_1109_ACCESS_2024_3444900 crossref_primary_10_3934_mbe_2023842 crossref_primary_10_1016_j_isprsjprs_2023_04_009 crossref_primary_10_1016_j_isprsjprs_2023_02_006 crossref_primary_10_1016_j_dsp_2024_104615 crossref_primary_10_1016_j_energy_2024_131357 crossref_primary_10_1109_JSTARS_2023_3241969 crossref_primary_10_1109_LGRS_2025_3527712 crossref_primary_10_3390_s23187806 crossref_primary_10_3390_rs15164017 crossref_primary_10_1007_s00371_024_03284_8 crossref_primary_10_1109_TGRS_2025_3526799 crossref_primary_10_1109_ACCESS_2024_3403716 crossref_primary_10_1109_TII_2024_3378841 crossref_primary_10_1109_TIM_2024_3370962 crossref_primary_10_1016_j_cja_2023_04_022 crossref_primary_10_3390_electronics13224470 crossref_primary_10_1007_s11042_024_18866_w crossref_primary_10_1016_j_jag_2024_104019 crossref_primary_10_1016_j_patcog_2025_111425 crossref_primary_10_1109_TGRS_2024_3430071 crossref_primary_10_3390_drones9010057 crossref_primary_10_1109_TIM_2023_3251414 crossref_primary_10_1016_j_patcog_2024_110976 crossref_primary_10_3390_electronics12234886 crossref_primary_10_3390_rs16010025 crossref_primary_10_1109_TGRS_2022_3215543 crossref_primary_10_1109_TGRS_2024_3482358 crossref_primary_10_1109_LGRS_2025_3531970 crossref_primary_10_1016_j_asoc_2025_112775 crossref_primary_10_1109_LGRS_2024_3374418 crossref_primary_10_1109_TGRS_2024_3381774 crossref_primary_10_1109_LGRS_2024_3406345 crossref_primary_10_1109_TIM_2025_3545522 crossref_primary_10_1016_j_ipm_2024_103858 crossref_primary_10_1016_j_neucom_2023_126285 crossref_primary_10_1016_j_compag_2024_108639 crossref_primary_10_1109_TITS_2024_3386928 crossref_primary_10_1109_TGRS_2024_3452010 crossref_primary_10_3390_rs16224175 crossref_primary_10_1109_TGRS_2024_3396489 crossref_primary_10_1109_TGRS_2024_3373621 crossref_primary_10_1109_TGRS_2024_3477575 crossref_primary_10_1007_s40747_024_01652_4 crossref_primary_10_1109_LGRS_2024_3507209 crossref_primary_10_3390_s25020306 crossref_primary_10_1109_JSEN_2024_3425156 crossref_primary_10_1007_s13721_023_00438_x crossref_primary_10_1109_TITS_2023_3334873 crossref_primary_10_1109_TGRS_2024_3395483 crossref_primary_10_12677_orf_2024_144371 crossref_primary_10_1002_eng2_13117 crossref_primary_10_1016_j_isprsjprs_2025_01_037 crossref_primary_10_3390_rs16091641 crossref_primary_10_3390_rs15061659 crossref_primary_10_3390_w17030430 crossref_primary_10_1007_s10462_025_11150_9 crossref_primary_10_1109_TGRS_2024_3470900 crossref_primary_10_3389_fnbot_2023_1273251 crossref_primary_10_32604_cmc_2024_056824 crossref_primary_10_1016_j_engappai_2024_109609 crossref_primary_10_1038_s41598_025_85630_x crossref_primary_10_3390_rs15112928 crossref_primary_10_1007_s10278_025_01460_3 crossref_primary_10_1016_j_jvcir_2024_104349 crossref_primary_10_1109_TGRS_2023_3298852 crossref_primary_10_3390_rs15123027 crossref_primary_10_1016_j_isprsjprs_2023_08_016 crossref_primary_10_1109_TGRS_2023_3278075 crossref_primary_10_1142_S0218001423540241 crossref_primary_10_1109_TGRS_2024_3363614 crossref_primary_10_1109_JSTARS_2024_3518753 crossref_primary_10_1109_TIM_2025_3545998 crossref_primary_10_1016_j_knosys_2024_112353 crossref_primary_10_1109_MGRS_2023_3312347 crossref_primary_10_3390_app15052749 crossref_primary_10_3390_bioengineering11100993 |
| Cites_doi | 10.1109/ICCV.2015.169 10.1109/ICCV.2019.00982 10.3390/rs10010132 10.1007/978-3-319-46448-0_2 10.1109/CVPR.2016.89 10.3390/rs12091432 10.1109/TPAMI.2020.2981890 10.1109/CVPRW53098.2021.00130 10.1109/ICCV.2017.324 10.1016/j.imavis.2020.103910 10.1109/CVPR.2016.90 10.1109/CVPR.2017.211 10.1016/j.isprsjprs.2014.10.002 10.1109/CVPRW.2019.00184 10.1109/CVPR.2016.314 10.5121/csit.2019.91713 10.1609/aaai.v34i07.6999 10.1007/s11263-014-0733-5 10.1109/TIP.2020.3002345 10.1109/CVPR.2018.00442 10.1109/CVPR46437.2021.00037 10.1109/CVPR.2017.106 10.1109/LGRS.2016.2565705 10.1109/CVPR.2019.00754 10.1007/978-3-030-01261-8_13 10.1016/j.jvcir.2015.11.002 10.1109/CVPR.2018.00377 10.1561/2200000073 10.3390/rs12193152 10.1109/CVPR.2018.00378 10.1109/CVPR.2019.00356 10.1007/978-3-319-10602-1_48 10.1109/TGRS.2019.2899955 10.1007/s10489-020-01949-0 10.1109/TPAMI.2021.3117983 10.1109/CVPR.2019.00519 10.1109/WACV45572.2020.9093394 10.1109/ICCV.2015.135 10.3390/app8050813 10.1109/CVPR.2019.00584 10.1109/ICPR48806.2021.9413340 10.1109/CVPR.2018.00418 10.1109/ICCV.2019.00972 10.3390/rs12152501 10.1109/ICCV.2019.00615 10.1109/ICCV.2017.30 10.3390/rs9020173 10.1109/TGRS.2020.3010051 10.1016/j.isprsjprs.2020.04.019 10.1007/978-3-030-58595-2_22 10.1109/CVPR.2019.00537 10.1609/aaai.v33i01.33019259 10.1016/j.isprsjprs.2019.11.023 10.1109/CVPR42600.2020.00978 10.1016/j.isprsjprs.2021.12.004 10.3390/rs13091854 10.1016/j.isprsjprs.2018.04.003 10.1109/CVPR.2018.00644 10.1109/CVPR.2019.00075 10.1109/CVPR46437.2021.01008 10.1109/CVPR42600.2020.01060 10.1109/ICCV.2019.00975 10.1007/978-3-030-01228-1_20 |
| ContentType | Journal Article |
| Copyright | 2022 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) |
| Copyright_xml | – notice: 2022 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) |
| DBID | AAYXX CITATION 7S9 L.6 |
| DOI | 10.1016/j.isprsjprs.2022.06.002 |
| DatabaseName | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geography Engineering |
| EISSN | 1872-8235 |
| EndPage | 93 |
| ExternalDocumentID | 10_1016_j_isprsjprs_2022_06_002 S0924271622001599 |
| GroupedDBID | --K --M .~1 0R~ 1B1 1RT 1~. 1~5 29J 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABJNI ABMAC ABQEM ABQYD ABXDB ABYKQ ACDAQ ACGFS ACLVX ACNNM ACRLP ACSBN ACZNC ADBBV ADEZE ADJOM ADMUD AEBSH AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG ATOGT AVWKF AXJTR AZFZN BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HMA HVGLF HZ~ H~9 IHE IMUCA J1W KOM LY3 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SDF SDG SEP SES SEW SPC SPCBC SSE SSV SSZ T5K T9H WUQ ZMT ~02 ~G- AAHBH AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH 7S9 EFKBS L.6 |
| ID | FETCH-LOGICAL-c348t-9ca97822252ace9ddbe088ae1d4d0ab535fa027cbf47f26fcaccd589f7695b883 |
| IEDL.DBID | .~1 |
| ISSN | 0924-2716 |
| IngestDate | Thu Sep 04 18:53:47 EDT 2025 Tue Jul 01 03:46:48 EDT 2025 Thu Apr 24 23:13:14 EDT 2025 Fri Feb 23 02:40:46 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Tiny object detection Benchmark dataset Aerial images |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c348t-9ca97822252ace9ddbe088ae1d4d0ab535fa027cbf47f26fcaccd589f7695b883 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PQID | 2718286825 |
| PQPubID | 24069 |
| PageCount | 15 |
| ParticipantIDs | proquest_miscellaneous_2718286825 crossref_primary_10_1016_j_isprsjprs_2022_06_002 crossref_citationtrail_10_1016_j_isprsjprs_2022_06_002 elsevier_sciencedirect_doi_10_1016_j_isprsjprs_2022_06_002 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | August 2022 2022-08-00 20220801 |
| PublicationDateYYYYMMDD | 2022-08-01 |
| PublicationDate_xml | – month: 08 year: 2022 text: August 2022 |
| PublicationDecade | 2020 |
| PublicationTitle | ISPRS journal of photogrammetry and remote sensing |
| PublicationYear | 2022 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Sun, K., Xiao, B., Liu, D., Wang, J., 2019. Deep high-resolution representation learning for human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5693–5703. Sun, X., Wang, P., Yan, Z., Xu, F., Wang, R., Diao, W., Chen, J., Li, J., Feng, Y., Xu, T. et al., 2021b. Fair1m: A benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery. arXiv preprint arXiv:2103.05569. Ge, Z., Liu, S., Li, Z., Yoshie, O., Sun, J., 2021. Ota: Optimal transport assignment for object detection. IEEE Conference on Computer Vision and Pattern Recognition. Pang, Li, Shi, Xu, Feng (b0190) 2019; 57 Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L., 2014. Microsoft coco: Common objects in context. In: European Conference on Computer Vision, Springer, pp. 740–755. Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S., 2019. Reppoints: Point set representation for object detection. In: IEEE International Conference on Computer Vision, pp. 9657–9666. Girshick, R., 2015. Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440–1448. Cai, Z., Vas., N., 2018. Cascade r-cnn: Delving into high quality object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154–6162. Lam, D., Kuzma, R., McGee, K., Dooley, S., Laielli, M., Klaric, M., Bulatov, Y., McCord, B., 2018. xview: Objects in context in overhead imagery. arXiv preprint arXiv:1802.07856. Oksuz, Cam, Kalkan, Akbas (b0185) 2021; 43 Noh, J., Bae, W., Lee, W., Seo, J., Kim, G., 2019. Better to follow, follow to be better: Towards precise supervision of feature super-resolution for small object detection. In: IEEE International Conference on Computer Vision, pp. 9725–9734. Tong, Wu, Zhou (b0290) 2020; 97 Zheng, Zhong, Ma, Han, Zhao, Liu, Zhang (b0365) 2020; 166 Ding, J., Xue, N., Xia, G.-S., Bai, X., Yang, W., Yang, M.Y., Belongie, S., Luo, J., Datcu, M., Pelillo, M. et al., 2021. Object detection in aerial images: A large-scale benchmark and challenges. IEEE Trans. Pattern Anal. Machine Intell. p. in press. Yang, X., Yan, J., Ming, Q., Wang, W., Zhang, X., Tian, Q., 2021. Rethinking rotated object detection with gaussian wasserstein distance loss. In: International Conference on Machine Learning, vol. 139, pp. 11830–11841. Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., Li, S.Z., 2017. S3fd: Single shot scale-invariant face detector. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 192–201. Ming, X., Wei, F., Zhang, T., Chen, D., Wen, F., 2019. Group sampling for scale invariant face detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3446–3456. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C., 2016a. SSD: Single shot multibox detector. In: European Conference on Computer Vision, Springer, pp. 21–37. Lu, X., Li, B., Yue, Y., Li, Q., Yan, J., 2019. Grid r-cnn. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7363–7372. Cheng, Han, Zhou, Guo (b0035) 2014; 98 Du, D., Zhu, P., Wen, L., et al., 2019. Visdrone-det2019: The vision meets drone object detection in image challenge results. In: IEEE International Conference on Computer Vision Workshops, pp. 213–226. Yu, Li, Zhang, Huang, Du, Tian, Sebe (b0330) 2019 Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollar, P., 2017b. Focal loss for dense object detection. In: IEEE International Conference on Computer Vision, pp. 2980–2988. Redmon, J., Farhadi, A., 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767. Paszke, A., Gross, S., Massa, F., Lerer, A. et al., 2019. Pytorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024–8035. Airbus, 2018. Airbus ship detection challenge. Pham, Courtrai, Friguet, Lefèvre, Baussard (b0210) 2020; 12 . Kim, K., Lee, H.S., 2020. Probabilistic anchor assignment with iou prediction for object detection. In: European Conference on Computer Vision, Springer, pp. 355–371. Kim, Y., Kang, B.-N., Kim, D., 2018. San: Learning relationship between convolutional features for multi-scale object detection. In: European Conference on Computer Vision, Springer, pp. 316–331. Bai, Y., Zhang, Y., Ding, M., Ghanem, B., 2018. Sod-mtgan: Small object detection via multi-task generative adversarial network. In: European Conference on Computer Vision, Springer, pp. 206–221. Goldman, E., Herzig, R., Eisenschtat, A., Goldberger, J., Hassner, T., 2019. Precise detection in densely packed scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5227–5236. Razakarivony, Jurie (b0225) 2016; 34 Xia, G.-S., Bai, X., Ding, J., Zhu, Z., Belongie, S., Luo, J., Datcu, M., Pelillo, M., Zhang, L., 2018. DOTA: A large-scale dataset for object detection in aerial images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3974–3983. Bell, S., Zitnick, C.L., Bala, K., Girshick, R.B., 2016. Inside-Outside Net: Detecting objects in context with skip pooling and recurrent neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2874–2883. Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y., 2018. Relation networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588–3597. Qiao, S., Chen, L.-C., Yuille, A., 2021. Detectors: Detecting objects with recursive feature pyramid and switchable atrous convolution. In: IEEE Conference on Computer Vision and Pattern Recognition. Peyré, Cuturi (b0205) 2019; 11 Ren, S., He, K., Girshick, R., Sun, J., 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99. Wang, J., Yang, W., Guo, H., Zhang, R., Xia, G.-S., 2021a. Tiny object detection in aerial images. In: International Conference on Pattern Recognition, pp. 3791–3798. Shermeyer, J., Van Etten, A., 2019. The effects of super-resolution on object detection performance in satellite imagery. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 0–0. Everingham, Eslami, Van Gool, Williams, Winn, Zisserman (b0060) 2015; 111 Ren, Zhu, Xiao (b0240) 2018; 8 Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S., 2017. Perceptual generative adversarial networks for small object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1222–1230. Kisantal, M., Wojna, Z., Murawski, J., Naruniec, J., Cho, K., 2019. Augmentation for small object detection. arXiv preprint arXiv:1902.07296. Yu, X., Gong, Y., Jiang, N., Ye, Q., Han, Z., 2020. Scale match for tiny person detection. In: IEEE Workshops on Applications of Computer Vision, pp. 1257–1265. Sun, Ai, Wang, Zhang (b0270) 2021; 51 Zhou, X., Wang, D., Krähenbühl, P., 2019. Objects as points. arXiv preprint arXiv:1904.07850. Bashir, Wang (b0015) 2021; 13 Singh, B., Najibi, M., Davis, L.S., 2018. Sniper: Efficient multi-scale training. In: Advances in Neural Information Processing Systems, pp. 9310–9320. Yang, Sun, Fu, Yang, Sun, Yan, Guo (b0315) 2018; 10 Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S., 2017a. Feature pyramid networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125. Zhao, Q., Sheng, T., Wang, Y., Tang, Z., Chen, Y., Cai, L., Ling, H., 2019. M2det: A single-shot object detector based on multi-level feature pyramid network. In: AAAI Conference on Artificial Intelligence, pp. 9259–9266. Li, Y., Chen, Y., Wang, N., Zhang, Z., 2019b. Scale-aware trident networks for object detection. In: IEEE International Conference on Computer Vision, pp. 6054–6063. Singh, B., Davis, L.S., 2018. An analysis of scale invariance in object detection snip. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3578–3587. Wang, Yang, Li, Zhang, Xia (b0300) 2021; 59 Courtrai, Pham, Lefèvre (b0040) 2020; 12 Shrivastava, A., Gupta, A., Girshick, R., 2016. Training region-based object detectors with online hard example mining. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 761–769. Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z., 2018. Single-shot refinement neural network for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4203–4212. Deng, Sun, Zhou, Zhao, Lei, Zou (b0045) 2018; 145 He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. Li, H., Wu, Z., Zhu, C., Xiong, C., Socher, R., Davis, L.S., 2020a. Learning from noisy anchors for one-stage object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10588–10597. Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.S., 2019a. Learning to learn from noisy labeled data. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5051–5059. Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z., 2020. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9759–9768. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S., 2019. Generalized intersection over union: A metric and a loss for bounding box regression. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 658–666. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D., 2020a. Distance-iou loss: Faster and better learning for bounding box regression. In: AAAI Conference on Artificial Intelligence, Vol. 34number 07, pp. 12993–13000. Li, Wan, Cheng, Meng, Han (b0135) 2020; 159 Liu, Wang, Weng, Yang (b0165) 2016; 13 Xu, C., Wang, J., Yang, W., Yu, L., 2021. Dot distance for tiny object detection in aerial images. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1192–1201. Zhu, P., Wen, L., Du, D., Bian, X., Ling, H., Hu, Q., Nie, Q., Cheng, H., Liu, C., Liu, X. et al., 2018. Visdrone-det2 Peyré (10.1016/j.isprsjprs.2022.06.002_b0205) 2019; 11 10.1016/j.isprsjprs.2022.06.002_b0080 Yu (10.1016/j.isprsjprs.2022.06.002_b0330) 2019 10.1016/j.isprsjprs.2022.06.002_b0280 10.1016/j.isprsjprs.2022.06.002_b0120 10.1016/j.isprsjprs.2022.06.002_b0285 10.1016/j.isprsjprs.2022.06.002_b0320 10.1016/j.isprsjprs.2022.06.002_b0160 Zheng (10.1016/j.isprsjprs.2022.06.002_b0365) 2020; 166 Cheng (10.1016/j.isprsjprs.2022.06.002_b0035) 2014; 98 10.1016/j.isprsjprs.2022.06.002_b0085 Kong (10.1016/j.isprsjprs.2022.06.002_b0110) 2020; 29 10.1016/j.isprsjprs.2022.06.002_b0360 10.1016/j.isprsjprs.2022.06.002_b0355 10.1016/j.isprsjprs.2022.06.002_b0235 10.1016/j.isprsjprs.2022.06.002_b0115 Wang (10.1016/j.isprsjprs.2022.06.002_b0300) 2021; 59 Pang (10.1016/j.isprsjprs.2022.06.002_b0190) 2019; 57 10.1016/j.isprsjprs.2022.06.002_b0090 Pelletier (10.1016/j.isprsjprs.2022.06.002_b0200) 2017; 9 10.1016/j.isprsjprs.2022.06.002_b0170 10.1016/j.isprsjprs.2022.06.002_b0010 10.1016/j.isprsjprs.2022.06.002_b0175 10.1016/j.isprsjprs.2022.06.002_b0055 Ren (10.1016/j.isprsjprs.2022.06.002_b0240) 2018; 8 10.1016/j.isprsjprs.2022.06.002_b0375 10.1016/j.isprsjprs.2022.06.002_b0255 10.1016/j.isprsjprs.2022.06.002_b0050 10.1016/j.isprsjprs.2022.06.002_b0095 10.1016/j.isprsjprs.2022.06.002_b0370 10.1016/j.isprsjprs.2022.06.002_b0250 10.1016/j.isprsjprs.2022.06.002_b0130 10.1016/j.isprsjprs.2022.06.002_b0295 Li (10.1016/j.isprsjprs.2022.06.002_b0135) 2020; 159 Pham (10.1016/j.isprsjprs.2022.06.002_b0210) 2020; 12 10.1016/j.isprsjprs.2022.06.002_b0245 10.1016/j.isprsjprs.2022.06.002_b0125 10.1016/j.isprsjprs.2022.06.002_b0005 Liu (10.1016/j.isprsjprs.2022.06.002_b0165) 2016; 13 10.1016/j.isprsjprs.2022.06.002_b0325 Sun (10.1016/j.isprsjprs.2022.06.002_b0270) 2021; 51 Oksuz (10.1016/j.isprsjprs.2022.06.002_b0185) 2021; 43 Bashir (10.1016/j.isprsjprs.2022.06.002_b0015) 2021; 13 10.1016/j.isprsjprs.2022.06.002_b0180 Rabbi (10.1016/j.isprsjprs.2022.06.002_b0220) 2020; 12 10.1016/j.isprsjprs.2022.06.002_b0065 10.1016/j.isprsjprs.2022.06.002_b0340 10.1016/j.isprsjprs.2022.06.002_b0100 10.1016/j.isprsjprs.2022.06.002_b0265 Tong (10.1016/j.isprsjprs.2022.06.002_b0290) 2020; 97 10.1016/j.isprsjprs.2022.06.002_b0145 Yang (10.1016/j.isprsjprs.2022.06.002_b0315) 2018; 10 10.1016/j.isprsjprs.2022.06.002_b0260 Deng (10.1016/j.isprsjprs.2022.06.002_b0045) 2018; 145 10.1016/j.isprsjprs.2022.06.002_b0140 10.1016/j.isprsjprs.2022.06.002_b0020 Courtrai (10.1016/j.isprsjprs.2022.06.002_b0040) 2020; 12 10.1016/j.isprsjprs.2022.06.002_b0335 10.1016/j.isprsjprs.2022.06.002_b0215 Everingham (10.1016/j.isprsjprs.2022.06.002_b0060) 2015; 111 10.1016/j.isprsjprs.2022.06.002_b0070 Razakarivony (10.1016/j.isprsjprs.2022.06.002_b0225) 2016; 34 10.1016/j.isprsjprs.2022.06.002_b0230 10.1016/j.isprsjprs.2022.06.002_b0275 10.1016/j.isprsjprs.2022.06.002_b0155 10.1016/j.isprsjprs.2022.06.002_b0310 10.1016/j.isprsjprs.2022.06.002_b0150 10.1016/j.isprsjprs.2022.06.002_b0030 10.1016/j.isprsjprs.2022.06.002_b0195 10.1016/j.isprsjprs.2022.06.002_b0075 10.1016/j.isprsjprs.2022.06.002_b0350 10.1016/j.isprsjprs.2022.06.002_b0305 10.1016/j.isprsjprs.2022.06.002_b0025 10.1016/j.isprsjprs.2022.06.002_b0345 10.1016/j.isprsjprs.2022.06.002_b0105 |
| References_xml | – reference: Zhao, Q., Sheng, T., Wang, Y., Tang, Z., Chen, Y., Cai, L., Ling, H., 2019. M2det: A single-shot object detector based on multi-level feature pyramid network. In: AAAI Conference on Artificial Intelligence, pp. 9259–9266. – reference: Gidaris, S., Komodakis, N., 2015. Object detection via a multi-region and semantic segmentation-aware cnn model. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1134–1142. – reference: Noh, J., Bae, W., Lee, W., Seo, J., Kim, G., 2019. Better to follow, follow to be better: Towards precise supervision of feature super-resolution for small object detection. In: IEEE International Conference on Computer Vision, pp. 9725–9734. – reference: Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S., 2019. Generalized intersection over union: A metric and a loss for bounding box regression. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 658–666. – reference: Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z., 2018. Single-shot refinement neural network for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4203–4212. – reference: Cao, G., Xie, X., Yang, W., Liao, Q., Shi, G., Wu, J., 2018. Feature-fused ssd: Fast detection for small objects. In: Ninth International Conference on Graphic and Image Processing (ICGIP 2017), Vol. 10615, International Society for Optics and Photonics, p. 106151E. – volume: 13 start-page: 1074 year: 2016 end-page: 1078 ident: b0165 article-title: Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds publication-title: IEEE Geosci. Remote Sens. Lett. – reference: Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z., 2020. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9759–9768. – reference: Singh, B., Davis, L.S., 2018. An analysis of scale invariance in object detection snip. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3578–3587. – reference: Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S., 2019. Reppoints: Point set representation for object detection. In: IEEE International Conference on Computer Vision, pp. 9657–9666. – reference: Girshick, R., 2015. Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440–1448. – reference: He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. – reference: Tian, Z., Shen, C., Chen, H., He, T., 2019. FCOS: Fully convolutional one-stage object detection. In: IEEE International Conference on Computer Vision, pp. 9627–9636. – volume: 9 start-page: 173 year: 2017 ident: b0200 article-title: Effect of training class label noise on classification performances for land cover mapping with satellite image time series publication-title: Remote Sensing – volume: 159 start-page: 296 year: 2020 end-page: 307 ident: b0135 article-title: Object detection in optical remote sensing images: A survey and a new benchmark publication-title: ISPRS J. Photogramm. Remote Sensing – volume: 29 start-page: 7389 year: 2020 end-page: 7398 ident: b0110 article-title: Foveabox: Beyound anchor-based object detection publication-title: IEEE Trans. Image Process. – reference: Kisantal, M., Wojna, Z., Murawski, J., Naruniec, J., Cho, K., 2019. Augmentation for small object detection. arXiv preprint arXiv:1902.07296. – reference: Sun, K., Xiao, B., Liu, D., Wang, J., 2019. Deep high-resolution representation learning for human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5693–5703. – volume: 51 start-page: 3311 year: 2021 end-page: 3322 ident: b0270 article-title: Mask-guided ssd for small-object detection publication-title: Appl. Intell. – reference: Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L., 2014. Microsoft coco: Common objects in context. In: European Conference on Computer Vision, Springer, pp. 740–755. – reference: Cai, Z., Vas., N., 2018. Cascade r-cnn: Delving into high quality object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154–6162. – volume: 11 start-page: 355 year: 2019 end-page: 607 ident: b0205 article-title: Computational optimal transport: With applications to data science publication-title: Found. Trends Machine Learn. – reference: Ding, J., Xue, N., Xia, G.-S., Bai, X., Yang, W., Yang, M.Y., Belongie, S., Luo, J., Datcu, M., Pelillo, M. et al., 2021. Object detection in aerial images: A large-scale benchmark and challenges. IEEE Trans. Pattern Anal. Machine Intell. p. in press. – reference: Du, D., Zhu, P., Wen, L., et al., 2019. Visdrone-det2019: The vision meets drone object detection in image challenge results. In: IEEE International Conference on Computer Vision Workshops, pp. 213–226. – reference: Lu, X., Li, B., Yue, Y., Li, Q., Yan, J., 2019. Grid r-cnn. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7363–7372. – reference: Li, Y., Chen, Y., Wang, N., Zhang, Z., 2019b. Scale-aware trident networks for object detection. In: IEEE International Conference on Computer Vision, pp. 6054–6063. – reference: Paszke, A., Gross, S., Massa, F., Lerer, A. et al., 2019. Pytorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024–8035. – reference: Xu, C., Wang, J., Yang, W., Yu, L., 2021. Dot distance for tiny object detection in aerial images. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1192–1201. – reference: Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.S., 2019a. Learning to learn from noisy labeled data. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5051–5059. – reference: Lam, D., Kuzma, R., McGee, K., Dooley, S., Laielli, M., Klaric, M., Bulatov, Y., McCord, B., 2018. xview: Objects in context in overhead imagery. arXiv preprint arXiv:1802.07856. – reference: Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S., 2017. Perceptual generative adversarial networks for small object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1222–1230. – reference: Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C., 2016a. SSD: Single shot multibox detector. In: European Conference on Computer Vision, Springer, pp. 21–37. – volume: 12 start-page: 1432 year: 2020 ident: b0220 article-title: Small-object detection in remote sensing images with end-to-end edge-enhanced gan and object detector network publication-title: Remote Sensing – reference: Xia, G.-S., Bai, X., Ding, J., Zhu, Z., Belongie, S., Luo, J., Datcu, M., Pelillo, M., Zhang, L., 2018. DOTA: A large-scale dataset for object detection in aerial images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3974–3983. – reference: Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., Li, S.Z., 2017. S3fd: Single shot scale-invariant face detector. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 192–201. – reference: Shrivastava, A., Gupta, A., Girshick, R., 2016. Training region-based object detectors with online hard example mining. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 761–769. – volume: 145 start-page: 3 year: 2018 end-page: 22 ident: b0045 article-title: Multi-scale object detection in remote sensing imagery with convolutional neural networks publication-title: ISPRS J. Photogramm. Remote Sensing – volume: 34 start-page: 187 year: 2016 end-page: 203 ident: b0225 article-title: Vehicle detection in aerial imagery: A small target detection benchmark publication-title: J. Vis. Commun. Image Represent. – reference: Ge, Z., Liu, S., Li, Z., Yoshie, O., Sun, J., 2021. Ota: Optimal transport assignment for object detection. IEEE Conference on Computer Vision and Pattern Recognition. – reference: Yu, X., Gong, Y., Jiang, N., Ye, Q., Han, Z., 2020. Scale match for tiny person detection. In: IEEE Workshops on Applications of Computer Vision, pp. 1257–1265. – volume: 57 start-page: 5512 year: 2019 end-page: 5524 ident: b0190 article-title: -CNN: Fast tiny object detection in large-scale remote sensing images publication-title: IEEE Trans. Geosci. Remote Sens. – reference: Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y., 2018. Relation networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588–3597. – volume: 12 start-page: 2501 year: 2020 ident: b0210 article-title: Yolo-fine: One-stage detector of small objects under various backgrounds in remote sensing images publication-title: Remote Sensing – reference: Airbus, 2018. Airbus ship detection challenge. – reference: Zhou, X., Wang, D., Krähenbühl, P., 2019. Objects as points. arXiv preprint arXiv:1904.07850. – reference: Qiao, S., Chen, L.-C., Yuille, A., 2021. Detectors: Detecting objects with recursive feature pyramid and switchable atrous convolution. In: IEEE Conference on Computer Vision and Pattern Recognition. – volume: 166 start-page: 1 year: 2020 end-page: 14 ident: b0365 article-title: Hynet: Hyper-scale object detection network framework for multiple spatial resolution remote sensing imagery publication-title: ISPRS J. Photogramm. Remote Sensing – reference: Zhu, P., Wen, L., Du, D., Bian, X., Ling, H., Hu, Q., Nie, Q., Cheng, H., Liu, C., Liu, X. et al., 2018. Visdrone-det2018: The vision meets drone object detection in image challenge results. In: European Conference on Computer Vision Workshops, Springer, pp. 437–468. – reference: Bai, Y., Zhang, Y., Ding, M., Ghanem, B., 2018. Sod-mtgan: Small object detection via multi-task generative adversarial network. In: European Conference on Computer Vision, Springer, pp. 206–221. – reference: Goldman, E., Herzig, R., Eisenschtat, A., Goldberger, J., Hassner, T., 2019. Precise detection in densely packed scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5227–5236. – reference: Kim, Y., Kang, B.-N., Kim, D., 2018. San: Learning relationship between convolutional features for multi-scale object detection. In: European Conference on Computer Vision, Springer, pp. 316–331. – volume: 8 start-page: 813 year: 2018 ident: b0240 article-title: Small object detection in optical remote sensing images via modified faster r-cnn publication-title: Appl. Sci. – reference: Sun, X., Wang, P., Yan, Z., Xu, F., Wang, R., Diao, W., Chen, J., Li, J., Feng, Y., Xu, T. et al., 2021b. Fair1m: A benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery. arXiv preprint arXiv:2103.05569. – reference: Redmon, J., Farhadi, A., 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767. – reference: Li, H., Wu, Z., Zhu, C., Xiong, C., Socher, R., Davis, L.S., 2020a. Learning from noisy anchors for one-stage object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10588–10597. – volume: 98 start-page: 119 year: 2014 end-page: 132 ident: b0035 article-title: Multi-class geospatial object detection and geographic image classification based on collection of part detectors publication-title: ISPRS J. Photogramm. Remote Sensing – reference: Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollar, P., 2017b. Focal loss for dense object detection. In: IEEE International Conference on Computer Vision, pp. 2980–2988. – reference: Bell, S., Zitnick, C.L., Bala, K., Girshick, R.B., 2016. Inside-Outside Net: Detecting objects in context with skip pooling and recurrent neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2874–2883. – reference: Wang, J., Yang, W., Guo, H., Zhang, R., Xia, G.-S., 2021a. Tiny object detection in aerial images. In: International Conference on Pattern Recognition, pp. 3791–3798. – volume: 43 start-page: 3388 year: 2021 end-page: 3415 ident: b0185 article-title: Imbalance problems in object detection: A review publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: . – start-page: 1 year: 2019 end-page: 19 ident: b0330 article-title: The unmanned aerial vehicle benchmark: Object detection, tracking and baseline publication-title: Int. J. Comput. Vision – volume: 111 start-page: 98 year: 2015 end-page: 136 ident: b0060 article-title: The pascal visual object classes challenge: A retrospective publication-title: Int. J. Comput. Vision – volume: 12 start-page: 3152 year: 2020 ident: b0040 article-title: Small object detection in remote sensing images based on super-resolution with auxiliary generative adversarial networks publication-title: Remote Sensing – reference: Kim, K., Lee, H.S., 2020. Probabilistic anchor assignment with iou prediction for object detection. In: European Conference on Computer Vision, Springer, pp. 355–371. – reference: Ren, S., He, K., Girshick, R., Sun, J., 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99. – reference: Shermeyer, J., Van Etten, A., 2019. The effects of super-resolution on object detection performance in satellite imagery. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 0–0. – volume: 10 start-page: 132 year: 2018 ident: b0315 article-title: Automatic ship detection in remote sensing images from google earth of complex scenes based on multiscale rotation dense feature pyramid networks publication-title: Remote Sensing – volume: 13 start-page: 1854 year: 2021 ident: b0015 article-title: Small object detection in remote sensing images with residual feature aggregation-based super-resolution and object detector network publication-title: Remote Sensing – reference: Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S., 2017a. Feature pyramid networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125. – reference: Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D., 2020a. Distance-iou loss: Faster and better learning for bounding box regression. In: AAAI Conference on Artificial Intelligence, Vol. 34number 07, pp. 12993–13000. – reference: Singh, B., Najibi, M., Davis, L.S., 2018. Sniper: Efficient multi-scale training. In: Advances in Neural Information Processing Systems, pp. 9310–9320. – volume: 59 start-page: 4307 year: 2021 end-page: 4323 ident: b0300 article-title: Learning center probability map for detecting objects in aerial images publication-title: IEEE Trans. Geosci. Remote Sens. – reference: Ming, X., Wei, F., Zhang, T., Chen, D., Wen, F., 2019. Group sampling for scale invariant face detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3446–3456. – reference: Yang, X., Yan, J., Ming, Q., Wang, W., Zhang, X., Tian, Q., 2021. Rethinking rotated object detection with gaussian wasserstein distance loss. In: International Conference on Machine Learning, vol. 139, pp. 11830–11841. – volume: 97 start-page: 103910 year: 2020 ident: b0290 article-title: Recent advances in small object detection based on deep learning: A review publication-title: Image Vis. Comput. – ident: 10.1016/j.isprsjprs.2022.06.002_b0375 – ident: 10.1016/j.isprsjprs.2022.06.002_b0115 – ident: 10.1016/j.isprsjprs.2022.06.002_b0075 doi: 10.1109/ICCV.2015.169 – ident: 10.1016/j.isprsjprs.2022.06.002_b0180 doi: 10.1109/ICCV.2019.00982 – volume: 10 start-page: 132 issue: 1 year: 2018 ident: 10.1016/j.isprsjprs.2022.06.002_b0315 article-title: Automatic ship detection in remote sensing images from google earth of complex scenes based on multiscale rotation dense feature pyramid networks publication-title: Remote Sensing doi: 10.3390/rs10010132 – ident: 10.1016/j.isprsjprs.2022.06.002_b0160 doi: 10.1007/978-3-319-46448-0_2 – ident: 10.1016/j.isprsjprs.2022.06.002_b0255 doi: 10.1109/CVPR.2016.89 – volume: 12 start-page: 1432 issue: 9 year: 2020 ident: 10.1016/j.isprsjprs.2022.06.002_b0220 article-title: Small-object detection in remote sensing images with end-to-end edge-enhanced gan and object detector network publication-title: Remote Sensing doi: 10.3390/rs12091432 – ident: 10.1016/j.isprsjprs.2022.06.002_b0195 – volume: 43 start-page: 3388 issue: 10 year: 2021 ident: 10.1016/j.isprsjprs.2022.06.002_b0185 article-title: Imbalance problems in object detection: A review publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2020.2981890 – ident: 10.1016/j.isprsjprs.2022.06.002_b0310 doi: 10.1109/CVPRW53098.2021.00130 – ident: 10.1016/j.isprsjprs.2022.06.002_b0150 doi: 10.1109/ICCV.2017.324 – volume: 97 start-page: 103910 year: 2020 ident: 10.1016/j.isprsjprs.2022.06.002_b0290 article-title: Recent advances in small object detection based on deep learning: A review publication-title: Image Vis. Comput. doi: 10.1016/j.imavis.2020.103910 – ident: 10.1016/j.isprsjprs.2022.06.002_b0085 doi: 10.1109/CVPR.2016.90 – ident: 10.1016/j.isprsjprs.2022.06.002_b0125 doi: 10.1109/CVPR.2017.211 – ident: 10.1016/j.isprsjprs.2022.06.002_b0055 – volume: 98 start-page: 119 year: 2014 ident: 10.1016/j.isprsjprs.2022.06.002_b0035 article-title: Multi-class geospatial object detection and geographic image classification based on collection of part detectors publication-title: ISPRS J. Photogramm. Remote Sensing doi: 10.1016/j.isprsjprs.2014.10.002 – ident: 10.1016/j.isprsjprs.2022.06.002_b0250 doi: 10.1109/CVPRW.2019.00184 – ident: 10.1016/j.isprsjprs.2022.06.002_b0020 doi: 10.1109/CVPR.2016.314 – ident: 10.1016/j.isprsjprs.2022.06.002_b0105 doi: 10.5121/csit.2019.91713 – ident: 10.1016/j.isprsjprs.2022.06.002_b0360 doi: 10.1609/aaai.v34i07.6999 – ident: 10.1016/j.isprsjprs.2022.06.002_b0030 – volume: 111 start-page: 98 issue: 1 year: 2015 ident: 10.1016/j.isprsjprs.2022.06.002_b0060 article-title: The pascal visual object classes challenge: A retrospective publication-title: Int. J. Comput. Vision doi: 10.1007/s11263-014-0733-5 – volume: 29 start-page: 7389 year: 2020 ident: 10.1016/j.isprsjprs.2022.06.002_b0110 article-title: Foveabox: Beyound anchor-based object detection publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2020.3002345 – ident: 10.1016/j.isprsjprs.2022.06.002_b0345 doi: 10.1109/CVPR.2018.00442 – ident: 10.1016/j.isprsjprs.2022.06.002_b0065 doi: 10.1109/CVPR46437.2021.00037 – ident: 10.1016/j.isprsjprs.2022.06.002_b0145 doi: 10.1109/CVPR.2017.106 – volume: 13 start-page: 1074 issue: 8 year: 2016 ident: 10.1016/j.isprsjprs.2022.06.002_b0165 article-title: Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2016.2565705 – ident: 10.1016/j.isprsjprs.2022.06.002_b0170 doi: 10.1109/CVPR.2019.00754 – ident: 10.1016/j.isprsjprs.2022.06.002_b0010 doi: 10.1007/978-3-030-01261-8_13 – volume: 34 start-page: 187 year: 2016 ident: 10.1016/j.isprsjprs.2022.06.002_b0225 article-title: Vehicle detection in aerial imagery: A small target detection benchmark publication-title: J. Vis. Commun. Image Represent. doi: 10.1016/j.jvcir.2015.11.002 – ident: 10.1016/j.isprsjprs.2022.06.002_b0260 doi: 10.1109/CVPR.2018.00377 – ident: 10.1016/j.isprsjprs.2022.06.002_b0320 – volume: 11 start-page: 355 issue: 5–6 year: 2019 ident: 10.1016/j.isprsjprs.2022.06.002_b0205 article-title: Computational optimal transport: With applications to data science publication-title: Found. Trends Machine Learn. doi: 10.1561/2200000073 – volume: 12 start-page: 3152 issue: 19 year: 2020 ident: 10.1016/j.isprsjprs.2022.06.002_b0040 article-title: Small object detection in remote sensing images based on super-resolution with auxiliary generative adversarial networks publication-title: Remote Sensing doi: 10.3390/rs12193152 – ident: 10.1016/j.isprsjprs.2022.06.002_b0090 doi: 10.1109/CVPR.2018.00378 – ident: 10.1016/j.isprsjprs.2022.06.002_b0175 doi: 10.1109/CVPR.2019.00356 – ident: 10.1016/j.isprsjprs.2022.06.002_b0155 doi: 10.1007/978-3-319-10602-1_48 – start-page: 1 year: 2019 ident: 10.1016/j.isprsjprs.2022.06.002_b0330 article-title: The unmanned aerial vehicle benchmark: Object detection, tracking and baseline publication-title: Int. J. Comput. Vision – volume: 57 start-page: 5512 issue: 8 year: 2019 ident: 10.1016/j.isprsjprs.2022.06.002_b0190 article-title: R2-CNN: Fast tiny object detection in large-scale remote sensing images publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2019.2899955 – volume: 51 start-page: 3311 issue: 6 year: 2021 ident: 10.1016/j.isprsjprs.2022.06.002_b0270 article-title: Mask-guided ssd for small-object detection publication-title: Appl. Intell. doi: 10.1007/s10489-020-01949-0 – ident: 10.1016/j.isprsjprs.2022.06.002_b0050 doi: 10.1109/TPAMI.2021.3117983 – ident: 10.1016/j.isprsjprs.2022.06.002_b0130 doi: 10.1109/CVPR.2019.00519 – ident: 10.1016/j.isprsjprs.2022.06.002_b0335 doi: 10.1109/WACV45572.2020.9093394 – ident: 10.1016/j.isprsjprs.2022.06.002_b0070 doi: 10.1109/ICCV.2015.135 – volume: 8 start-page: 813 issue: 5 year: 2018 ident: 10.1016/j.isprsjprs.2022.06.002_b0240 article-title: Small object detection in optical remote sensing images via modified faster r-cnn publication-title: Appl. Sci. doi: 10.3390/app8050813 – ident: 10.1016/j.isprsjprs.2022.06.002_b0275 doi: 10.1109/CVPR.2019.00584 – ident: 10.1016/j.isprsjprs.2022.06.002_b0295 doi: 10.1109/ICPR48806.2021.9413340 – ident: 10.1016/j.isprsjprs.2022.06.002_b0305 doi: 10.1109/CVPR.2018.00418 – ident: 10.1016/j.isprsjprs.2022.06.002_b0235 – ident: 10.1016/j.isprsjprs.2022.06.002_b0285 doi: 10.1109/ICCV.2019.00972 – volume: 12 start-page: 2501 issue: 15 year: 2020 ident: 10.1016/j.isprsjprs.2022.06.002_b0210 article-title: Yolo-fine: One-stage detector of small objects under various backgrounds in remote sensing images publication-title: Remote Sensing doi: 10.3390/rs12152501 – ident: 10.1016/j.isprsjprs.2022.06.002_b0140 doi: 10.1109/ICCV.2019.00615 – ident: 10.1016/j.isprsjprs.2022.06.002_b0350 doi: 10.1109/ICCV.2017.30 – volume: 9 start-page: 173 issue: 2 year: 2017 ident: 10.1016/j.isprsjprs.2022.06.002_b0200 article-title: Effect of training class label noise on classification performances for land cover mapping with satellite image time series publication-title: Remote Sensing doi: 10.3390/rs9020173 – ident: 10.1016/j.isprsjprs.2022.06.002_b0265 – volume: 59 start-page: 4307 issue: 5 year: 2021 ident: 10.1016/j.isprsjprs.2022.06.002_b0300 article-title: Learning center probability map for detecting objects in aerial images publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2020.3010051 – volume: 166 start-page: 1 year: 2020 ident: 10.1016/j.isprsjprs.2022.06.002_b0365 article-title: Hynet: Hyper-scale object detection network framework for multiple spatial resolution remote sensing imagery publication-title: ISPRS J. Photogramm. Remote Sensing doi: 10.1016/j.isprsjprs.2020.04.019 – ident: 10.1016/j.isprsjprs.2022.06.002_b0005 – ident: 10.1016/j.isprsjprs.2022.06.002_b0095 doi: 10.1007/978-3-030-58595-2_22 – ident: 10.1016/j.isprsjprs.2022.06.002_b0080 doi: 10.1109/CVPR.2019.00537 – ident: 10.1016/j.isprsjprs.2022.06.002_b0355 doi: 10.1609/aaai.v33i01.33019259 – volume: 159 start-page: 296 year: 2020 ident: 10.1016/j.isprsjprs.2022.06.002_b0135 article-title: Object detection in optical remote sensing images: A survey and a new benchmark publication-title: ISPRS J. Photogramm. Remote Sensing doi: 10.1016/j.isprsjprs.2019.11.023 – ident: 10.1016/j.isprsjprs.2022.06.002_b0340 doi: 10.1109/CVPR42600.2020.00978 – ident: 10.1016/j.isprsjprs.2022.06.002_b0280 doi: 10.1016/j.isprsjprs.2021.12.004 – ident: 10.1016/j.isprsjprs.2022.06.002_b0370 – volume: 13 start-page: 1854 issue: 9 year: 2021 ident: 10.1016/j.isprsjprs.2022.06.002_b0015 article-title: Small object detection in remote sensing images with residual feature aggregation-based super-resolution and object detector network publication-title: Remote Sensing doi: 10.3390/rs13091854 – volume: 145 start-page: 3 year: 2018 ident: 10.1016/j.isprsjprs.2022.06.002_b0045 article-title: Multi-scale object detection in remote sensing imagery with convolutional neural networks publication-title: ISPRS J. Photogramm. Remote Sensing doi: 10.1016/j.isprsjprs.2018.04.003 – ident: 10.1016/j.isprsjprs.2022.06.002_b0025 doi: 10.1109/CVPR.2018.00644 – ident: 10.1016/j.isprsjprs.2022.06.002_b0245 doi: 10.1109/CVPR.2019.00075 – ident: 10.1016/j.isprsjprs.2022.06.002_b0215 doi: 10.1109/CVPR46437.2021.01008 – ident: 10.1016/j.isprsjprs.2022.06.002_b0120 doi: 10.1109/CVPR42600.2020.01060 – ident: 10.1016/j.isprsjprs.2022.06.002_b0325 doi: 10.1109/ICCV.2019.00975 – ident: 10.1016/j.isprsjprs.2022.06.002_b0100 doi: 10.1007/978-3-030-01228-1_20 – ident: 10.1016/j.isprsjprs.2022.06.002_b0230 |
| SSID | ssj0001568 |
| Score | 2.6577902 |
| Snippet | Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels. State-of-the-art object detectors do not provide... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 79 |
| SubjectTerms | Aerial images aerial photography Benchmark dataset data collection detectors information networks photogrammetry product labeling remote sensing testing Tiny object detection |
| Title | Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark |
| URI | https://dx.doi.org/10.1016/j.isprsjprs.2022.06.002 https://www.proquest.com/docview/2718286825 |
| Volume | 190 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T-QwELYQVwDF6XgJOEBGog2bh504dCse2gOJBhBURONHRHhkV7tLAQW_nRkn4XE6ieKKRElkK9HYmfnG_maGsd0YZCkgiQItsyQQkbOBoqvcZKAQUITgPMv3LB1cipNreT3DDrpYGKJVtrq_0eleW7dPeq00e6Oq6p2H6DrElACJaEEypyA-ITLKn7_3-kHziJpwOGocUOsvHK9qMhpP7vBARzGOfSLPdn3lHxbqL13tDdDxL_azRY6833zcIptx9RJb-JRPcInNtSXNb5-X2c2ho_0BfM7x9MyHmlZcJryqOfhZx6tH1CWTfd7nNQHXh-rFWX4FPv6SamByS9gSBcKhthw4AnCuUUC3jzC-X2GXx0cXB4OgLaYQmESoKQofco8GZAzG5dZqhwoGXGSFDUHLRJaALqrRpcjKOC0NGGOlyssszaVWKllls_WwdmuMhxZhW5pmeW5LkSRS0easibS0YBQ6aOss7QRYmDbTOBW8eCg6Stld8S75giRfeHJdvM7C946jJtnG9132uxEqvsybAk3C9513ujEt8K-irRKo3fAJG6HJjlWK7vPG_7zgN5unu4YwuMlmp-Mnt4UgZqq3_SzdZj_6f04HZ2-TpfO7 |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT9wwEB5ROFAOqKWtyqOtK_UabV5ObG4rKFoK3UtBcKo1fkSEQna1uxzg1zNOnFVBlTj0kChyPHI0nsx8Y49nAL6lyKscsyTSvMyiPHE2Ev5JmhIFAYoYXRvlOy5G5_mPS365Agf9WRgfVhl0f6fTW20dWgaBm4NpXQ9-xeQ6pD4Bkg8L4lK-gjWfnYqEfW14fDIaLxVy0p2I8_0jT_AkzKueT2fza7rIV0zTNpdnWGL5h5F6pq5bG3T0BjYDeGTD7vvewoprtmDjr5SCW7Aeqppf3b-D34fObxFQO6PbPZtov-gyZ3XDsBU8Vt-SOpnvsyFrPHa9qR-cZRfYHsH0ZTCZ9fCSeMKwsQwZYXCmiUdXtzj78x7Oj76fHYyiUE8hMlkuFsR_lC0g4CkaJ63VjnQMusTmNkbNM14healGV3lZpUVl0BjLhazKQnItRPYBVptJ4z4Ciy0ht6IopbRVnmVc-P1Zk2hu0Qjy0bah6BmoTEg27mte3Kg-quxaLTmvPOdVG1-XbkO8JJx2-TZeJtnvZ0g9ER1FVuFl4q_9nCr6sfxuCTZuckedyGqnoiAPeud_BvgC66Ozn6fq9Hh8sguv_ZsufnAPVhezO_eJMM1Cfw4y-wjnL_Zs |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Detecting+tiny+objects+in+aerial+images%3A+A+normalized+Wasserstein+distance+and+a+new+benchmark&rft.jtitle=ISPRS+journal+of+photogrammetry+and+remote+sensing&rft.au=Xu%2C+Chang&rft.au=Wang%2C+Jinwang&rft.au=Yang%2C+Wen&rft.au=Yu%2C+Huai&rft.date=2022-08-01&rft.issn=0924-2716&rft.volume=190+p.79-93&rft.spage=79&rft.epage=93&rft_id=info:doi/10.1016%2Fj.isprsjprs.2022.06.002&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0924-2716&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0924-2716&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0924-2716&client=summon |