Robust self-supervised learning for source-free domain adaptation
Source-free domain adaptation (SFDA) is from unsupervised domain adaptation (UDA) and do apply to the special situation in reality that the source domain data is not accessible. In this subject, self-supervised learning is widely used in previous works. However, inaccurate pseudo-labels are hardly a...
Saved in:
| Published in | Signal, image and video processing Vol. 17; no. 5; pp. 2405 - 2413 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
London
Springer London
01.07.2023
Springer Nature B.V |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Source-free domain adaptation (SFDA) is from unsupervised domain adaptation (UDA) and do apply to the special situation in reality that the source domain data is not accessible. In this subject, self-supervised learning is widely used in previous works. However, inaccurate pseudo-labels are hardly avoidable and that degenerates the adapted target model. In this work, we propose an effective method, named RS2L (robust self-supervised learning), to reduce the negative impact due to inaccurate pseudo-labels. Two strategies are adapted. The first is called structure-preserved pseudo-labeling strategy which generates much better pseudo-labels by stored predictions of
k
-closest neighbors. Another is self-supervised learning with mask. We use threshold masks to select samples for different operations, i.e., self-supervised learning and structure-preserved learning. For different masks, the threshold values are different. So it is not excluded that some samples participate in both two operations. Experiments on three benchmark datasets show that our method achieves the state-of-the-art results. |
|---|---|
| AbstractList | Source-free domain adaptation (SFDA) is from unsupervised domain adaptation (UDA) and do apply to the special situation in reality that the source domain data is not accessible. In this subject, self-supervised learning is widely used in previous works. However, inaccurate pseudo-labels are hardly avoidable and that degenerates the adapted target model. In this work, we propose an effective method, named RS2L (robust self-supervised learning), to reduce the negative impact due to inaccurate pseudo-labels. Two strategies are adapted. The first is called structure-preserved pseudo-labeling strategy which generates much better pseudo-labels by stored predictions of
k
-closest neighbors. Another is self-supervised learning with mask. We use threshold masks to select samples for different operations, i.e., self-supervised learning and structure-preserved learning. For different masks, the threshold values are different. So it is not excluded that some samples participate in both two operations. Experiments on three benchmark datasets show that our method achieves the state-of-the-art results. Source-free domain adaptation (SFDA) is from unsupervised domain adaptation (UDA) and do apply to the special situation in reality that the source domain data is not accessible. In this subject, self-supervised learning is widely used in previous works. However, inaccurate pseudo-labels are hardly avoidable and that degenerates the adapted target model. In this work, we propose an effective method, named RS2L (robust self-supervised learning), to reduce the negative impact due to inaccurate pseudo-labels. Two strategies are adapted. The first is called structure-preserved pseudo-labeling strategy which generates much better pseudo-labels by stored predictions of k-closest neighbors. Another is self-supervised learning with mask. We use threshold masks to select samples for different operations, i.e., self-supervised learning and structure-preserved learning. For different masks, the threshold values are different. So it is not excluded that some samples participate in both two operations. Experiments on three benchmark datasets show that our method achieves the state-of-the-art results. |
| Author | Zhou, Lihua Tian, Liang Zhang, Hao Ye, Mao Wang, Zhenbin |
| Author_xml | – sequence: 1 givenname: Liang surname: Tian fullname: Tian, Liang organization: School of Computer Science and Engineering, University of Electronic Science and Technology of China – sequence: 2 givenname: Lihua surname: Zhou fullname: Zhou, Lihua email: lihua.zhou@std.uestc.edu.cn organization: School of Computer Science and Engineering, University of Electronic Science and Technology of China – sequence: 3 givenname: Hao surname: Zhang fullname: Zhang, Hao organization: School of Computer Science and Engineering, University of Electronic Science and Technology of China – sequence: 4 givenname: Zhenbin surname: Wang fullname: Wang, Zhenbin organization: School of Computer Science and Engineering, University of Electronic Science and Technology of China – sequence: 5 givenname: Mao surname: Ye fullname: Ye, Mao organization: School of Computer Science and Engineering, University of Electronic Science and Technology of China |
| BookMark | eNp9kFtLAzEQhYNUsNb-AZ8WfI7msrn0sRRvUBCk7yG7mZQt282abAX7642uKPjQgWHm4Xwzh3OJJl3oAKFrSm4pIeouUaokwYSx3KVQ-HiGplRLjqmidPK7E36B5intSC7OlJZ6ipavoTqkoUjQepwOPcT3JoErWrCxa7pt4UMsUjjEGrCPAIULe9t0hXW2H-zQhO4KnXvbJpj_zBnaPNxvVk94_fL4vFqucc3pYsDMU11qCU7a2npeaqgXghJVCqecrIDIiipRWs2s9lCxmjgnhPRSuhKI5zN0M57tY3g7QBrMLrvq8kfDNBVc8lKIrNKjqo4hpQje1M1oc4i2aQ0l5isyM0ZmcmTmOzJzzCj7h_ax2dv4cRriI5SyuNtC_HN1gvoEzkyBWA |
| CitedBy_id | crossref_primary_10_1007_s11760_024_03200_6 crossref_primary_10_1038_s41598_024_53311_w crossref_primary_10_1109_JSTARS_2024_3408817 crossref_primary_10_1109_TPAMI_2024_3370978 crossref_primary_10_1007_s10489_024_05713_6 crossref_primary_10_1080_01431161_2024_2358547 |
| Cites_doi | 10.1109/WACV45572.2020.9093626 10.1016/j.neunet.2022.05.015 10.1109/CVPR.2018.00392 10.24963/ijcai.2021/402 10.1109/CVPR46437.2021.01636 10.1109/ICCV.2015.293 10.1016/j.neunet.2023.08.005 10.1109/CVPR.2019.00503 10.1109/ACCESS.2021.3110605 10.1109/CVPR.2016.90 10.1109/LSP.2022.3194414 10.1109/CVPR.2017.316 10.1109/ACCESS.2021.3136567 10.1109/ICCV48922.2021.00885 10.1007/978-3-642-15561-1_16 10.1109/CVPR52688.2022.00784 10.1109/ICCV.2017.244 10.1016/j.imavis.2022.104504 10.1109/TPAMI.2021.3103390 10.1109/TCSVT.2021.3111034 10.1109/TAI.2021.3110179 10.1109/CVPR.2017.572 10.1214/aoms/1177729694 10.1109/CVPR42600.2020.00966 |
| ContentType | Journal Article |
| Copyright | The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| Copyright_xml | – notice: The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| DBID | AAYXX CITATION |
| DOI | 10.1007/s11760-022-02457-z |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1863-1711 |
| EndPage | 2413 |
| ExternalDocumentID | 10_1007_s11760_022_02457_z |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 62276048 funderid: http://dx.doi.org/10.13039/501100001809 – fundername: Sichuan Province Science and Technology Support Program grantid: 2020YFG0476 funderid: http://dx.doi.org/10.13039/100012542 – fundername: Sichuan Province Science and Technology Support Program grantid: 2020YFG0476; 2020YFG0476; 2020YFG0476; 2020YFG0476 funderid: http://dx.doi.org/10.13039/100012542 – fundername: National Natural Science Foundation of China grantid: 62276048; 62276048; 62276048; 62276048 funderid: http://dx.doi.org/10.13039/501100001809 |
| GroupedDBID | -5B -5G -BR -EM -Y2 -~C .VR 06D 0R~ 123 1N0 203 29~ 2J2 2JN 2JY 2KG 2KM 2LR 2VQ 2~H 30V 4.4 406 408 409 40D 40E 5VS 67Z 6NX 875 8TC 95- 95. 95~ AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBXA ABDZT ABECU ABFTV ABHQN ABJNI ABJOX ABKCH ABMNI ABMQK ABNWP ABQBU ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACHXU ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSNA ACZOJ ADHHG ADHIR ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEGAL AEGNC AEJHL AEJRE AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFGCZ AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARMRJ AXYYD AYJHY B-. BA0 BDATZ BGNMA BSONS CAG COF CS3 CSCUP DDRTE DNIVK DPUIP EBLON EBS EIOEI EJD ESBYG FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ6 GQ7 GQ8 GXS H13 HF~ HG5 HG6 HLICF HMJXF HQYDN HRMNR HZ~ IJ- IKXTQ IWAJR IXC IXD IXE IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ KDC KOV LLZTM M4Y MA- NPVJJ NQJWS NU0 O9- O93 O9J OAM P9O PF0 PT4 QOS R89 R9I RIG ROL RPX RSV S16 S1Z S27 S3B SAP SDH SEG SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TSG TSK TSV TUC U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W48 YLTOR Z45 Z5O Z7R Z7X Z83 Z88 ZMTXR ~A9 AAPKM AAYXX ABBRH ABDBE ABFSG ACSTC ADKFA AEZWR AFDZB AFHIU AFOHR AHPBZ AHWEU AIXLP ATHPR AYFIA CITATION ABRTQ |
| ID | FETCH-LOGICAL-c319t-2f18486ed6acaf348ec9510745d7d6be06b1754a82a8feb2c0dd556f66d4e0f3 |
| IEDL.DBID | U2A |
| ISSN | 1863-1703 |
| IngestDate | Fri Jul 25 07:48:35 EDT 2025 Tue Jul 01 03:24:18 EDT 2025 Thu Apr 24 22:54:52 EDT 2025 Fri Feb 21 02:44:53 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Keywords | Local structure clustering Source-free domain adaptation Self-supervised learning |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c319t-2f18486ed6acaf348ec9510745d7d6be06b1754a82a8feb2c0dd556f66d4e0f3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| PQID | 2815363455 |
| PQPubID | 2044169 |
| PageCount | 9 |
| ParticipantIDs | proquest_journals_2815363455 crossref_citationtrail_10_1007_s11760_022_02457_z crossref_primary_10_1007_s11760_022_02457_z springer_journals_10_1007_s11760_022_02457_z |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2023-07-01 |
| PublicationDateYYYYMMDD | 2023-07-01 |
| PublicationDate_xml | – month: 07 year: 2023 text: 2023-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | London |
| PublicationPlace_xml | – name: London – name: Heidelberg |
| PublicationTitle | Signal, image and video processing |
| PublicationTitleAbbrev | SIViP |
| PublicationYear | 2023 |
| Publisher | Springer London Springer Nature B.V |
| Publisher_xml | – name: Springer London – name: Springer Nature B.V |
| References | IqbalJRawalHHafizRChiY-TAliMDistribution regularized self-supervised learning for domain adaptation of semantic segmentationImage Vis. Comput.202212410.1016/j.imavis.2022.104504 Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., Lempitsky, V.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096–2030 (2016) Ding, Y., Sheng, L., Liang, J., Zheng, A., He, R.: Proxymix: proxy-based mixup training with label refinery for source-free domain adaptation. arXiv preprint arXiv:2205.14566 (2022) Zellinger, W., Grubinger, T., Lughofer, E., Natschläger, T., Saminger-Platz, S.: Central moment discrepancy (CMD) for domain-invariant representation learning. arXiv preprint arXiv:1702.08811 (2017) Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4893–4902 (2019) YangSvan de WeijerJHerranzLJuiSExploiting the intrinsic neighborhood structure for source-free domain adaptationAdv. Neural. Inf. Process. Syst.2021342939329405 Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3723–3732 (2018) Liang, J., Hu, D., Feng, J.: Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation. In: International Conference on Machine Learning, pp. 6028–6039. PMLR (2020) Peng, X., Usman, B., Kaushik, N., Hoffman, J., Wang, D., Saenko, K.: VisDA: the visual domain adaptation challenge. arXiv preprint arXiv:1710.06924 (2017) Yang, S., Wang, Y., van de Weijer, J., Herranz, L., Jui, S.: Generalized source-free domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8978–8987 (2021) Liang, J., Hu, D., Feng, J.: Domain adaptation with auxiliary target domain-oriented classifier. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16632–16642 (2021) Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167–7176 (2017) Tang, S., Zou, Y., Song, Z., Lyu, J., Chen, L., Ye, M., Zhong, S., Zhang, J.: Semantic consistency learning on manifold for source data-free unsupervised domain adaptation. Neural Netw. (2022) Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017) Liu, M.-Y., Tuzel, O.: Coupled generative adversarial networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016) Yang, S., Wang, Y., Weijer, J.V.D., Herranz, L., Jui, S.: Unsupervised domain adaptation without source data by casting a bait. arXiv preprint arXiv:2010.12427 (2020) Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D.: Domain generalization for object recognition with multi-task autoencoders. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2551–2559 (2015) Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: European Conference on Computer Vision, pp. 213–226. Springer, Berlin (2010) Qiu, Z., Zhang, Y., Lin, H., Niu, S., Liu, Y., Du, Q., Tan, M.: Source-free domain adaptation via avatar prototype generation and adaptation. arXiv preprint arXiv:2106.15326 (2021) NgoBHParkJHParkSJChoSISemi-supervised domain adaptation using explicit class-wise matching for domain-invariant and class-discriminative feature learningIEEE Access2021912846712848010.1109/ACCESS.2021.3110605 Tian, J., Zhang, J., Li, W., Xu, D.: VDM-DA: virtual domain modeling for source data-free domain adaptation. In: IEEE Transactions on Circuits and Systems for Video Technology (2021) Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: Advances in Neural Information Processing Systems, vol. 31 (2018) Liang, J., Hu, D., Feng, J., He, R.: Dine: Domain adaptation from single and multiple black-box predictors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8003–8013 (2022) Liang, J., Hu, D., Wang, Y., He, R., Feng, J.: Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2021) KimYChoDHanKPandaPHongSDomain adaptation without source dataIEEE Trans. Artif. Intell.20212650851810.1109/TAI.2021.3110179 Li, R., Jiao, Q., Cao, W., Wong, H.-S., Wu, S.: Model adaptation: unsupervised domain adaptation without source data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9641–9650 (2020) LiuCZhouLYeMLiXSelf-alignment for black-box domain adaptation of image classificationIEEE Signal Process. Lett.2022291709171310.1109/LSP.2022.3194414 Iqbal, J., Ali, M.: MLSL: multi-level self-supervised learning for domain adaptation with spatially independent and semantically consistent labeling. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1864–1873 (2020) Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008) NgoBHKimJHChaeYJChoSIMulti-view collaborative learning for semi-supervised domain adaptationIEEE Access2021916648816650110.1109/ACCESS.2021.3136567 Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5018–5027 (2017) He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016) KullbackSLeiblerRAOn information and sufficiencyAnn. Math. Stat.195122179863996810.1214/aoms/11777296940042.38403 Sun, Y., Tzeng, E., Darrell, T., Efros, A.A.: Unsupervised domain adaptation through self-supervision. arXiv preprint arXiv:1909.11825 (2019) 2457_CR28 2457_CR29 J Iqbal (2457_CR12) 2022; 124 2457_CR22 2457_CR23 2457_CR20 2457_CR21 2457_CR26 2457_CR24 2457_CR25 BH Ngo (2457_CR15) 2021; 9 2457_CR1 S Kullback (2457_CR27) 1951; 22 2457_CR4 2457_CR19 2457_CR5 2457_CR2 2457_CR17 2457_CR3 2457_CR18 2457_CR9 2457_CR6 C Liu (2457_CR11) 2022; 29 2457_CR7 2457_CR33 2457_CR34 2457_CR31 2457_CR10 2457_CR16 2457_CR13 S Yang (2457_CR32) 2021; 34 Y Kim (2457_CR8) 2021; 2 BH Ngo (2457_CR14) 2021; 9 2457_CR30 |
| References_xml | – reference: Tang, S., Zou, Y., Song, Z., Lyu, J., Chen, L., Ye, M., Zhong, S., Zhang, J.: Semantic consistency learning on manifold for source data-free unsupervised domain adaptation. Neural Netw. (2022) – reference: Ding, Y., Sheng, L., Liang, J., Zheng, A., He, R.: Proxymix: proxy-based mixup training with label refinery for source-free domain adaptation. arXiv preprint arXiv:2205.14566 (2022) – reference: Liang, J., Hu, D., Wang, Y., He, R., Feng, J.: Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2021) – reference: NgoBHParkJHParkSJChoSISemi-supervised domain adaptation using explicit class-wise matching for domain-invariant and class-discriminative feature learningIEEE Access2021912846712848010.1109/ACCESS.2021.3110605 – reference: Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4893–4902 (2019) – reference: Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: European Conference on Computer Vision, pp. 213–226. Springer, Berlin (2010) – reference: Zellinger, W., Grubinger, T., Lughofer, E., Natschläger, T., Saminger-Platz, S.: Central moment discrepancy (CMD) for domain-invariant representation learning. arXiv preprint arXiv:1702.08811 (2017) – reference: Liang, J., Hu, D., Feng, J.: Domain adaptation with auxiliary target domain-oriented classifier. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16632–16642 (2021) – reference: Liu, M.-Y., Tuzel, O.: Coupled generative adversarial networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016) – reference: Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5018–5027 (2017) – reference: Iqbal, J., Ali, M.: MLSL: multi-level self-supervised learning for domain adaptation with spatially independent and semantically consistent labeling. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1864–1873 (2020) – reference: Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3723–3732 (2018) – reference: Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017) – reference: NgoBHKimJHChaeYJChoSIMulti-view collaborative learning for semi-supervised domain adaptationIEEE Access2021916648816650110.1109/ACCESS.2021.3136567 – reference: KullbackSLeiblerRAOn information and sufficiencyAnn. Math. Stat.195122179863996810.1214/aoms/11777296940042.38403 – reference: KimYChoDHanKPandaPHongSDomain adaptation without source dataIEEE Trans. Artif. Intell.20212650851810.1109/TAI.2021.3110179 – reference: Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D.: Domain generalization for object recognition with multi-task autoencoders. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2551–2559 (2015) – reference: Peng, X., Usman, B., Kaushik, N., Hoffman, J., Wang, D., Saenko, K.: VisDA: the visual domain adaptation challenge. arXiv preprint arXiv:1710.06924 (2017) – reference: Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: Advances in Neural Information Processing Systems, vol. 31 (2018) – reference: YangSvan de WeijerJHerranzLJuiSExploiting the intrinsic neighborhood structure for source-free domain adaptationAdv. Neural. Inf. Process. Syst.2021342939329405 – reference: Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167–7176 (2017) – reference: Qiu, Z., Zhang, Y., Lin, H., Niu, S., Liu, Y., Du, Q., Tan, M.: Source-free domain adaptation via avatar prototype generation and adaptation. arXiv preprint arXiv:2106.15326 (2021) – reference: Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., Lempitsky, V.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096–2030 (2016) – reference: Liang, J., Hu, D., Feng, J.: Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation. In: International Conference on Machine Learning, pp. 6028–6039. PMLR (2020) – reference: Yang, S., Wang, Y., Weijer, J.V.D., Herranz, L., Jui, S.: Unsupervised domain adaptation without source data by casting a bait. arXiv preprint arXiv:2010.12427 (2020) – reference: Li, R., Jiao, Q., Cao, W., Wong, H.-S., Wu, S.: Model adaptation: unsupervised domain adaptation without source data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9641–9650 (2020) – reference: Liang, J., Hu, D., Feng, J., He, R.: Dine: Domain adaptation from single and multiple black-box predictors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8003–8013 (2022) – reference: Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008) – reference: LiuCZhouLYeMLiXSelf-alignment for black-box domain adaptation of image classificationIEEE Signal Process. Lett.2022291709171310.1109/LSP.2022.3194414 – reference: Tian, J., Zhang, J., Li, W., Xu, D.: VDM-DA: virtual domain modeling for source data-free domain adaptation. In: IEEE Transactions on Circuits and Systems for Video Technology (2021) – reference: Yang, S., Wang, Y., van de Weijer, J., Herranz, L., Jui, S.: Generalized source-free domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8978–8987 (2021) – reference: IqbalJRawalHHafizRChiY-TAliMDistribution regularized self-supervised learning for domain adaptation of semantic segmentationImage Vis. Comput.202212410.1016/j.imavis.2022.104504 – reference: Sun, Y., Tzeng, E., Darrell, T., Efros, A.A.: Unsupervised domain adaptation through self-supervision. arXiv preprint arXiv:1909.11825 (2019) – reference: He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016) – ident: 2457_CR13 doi: 10.1109/WACV45572.2020.9093626 – ident: 2457_CR23 – ident: 2457_CR9 doi: 10.1016/j.neunet.2022.05.015 – ident: 2457_CR1 doi: 10.1109/CVPR.2018.00392 – ident: 2457_CR5 doi: 10.24963/ijcai.2021/402 – ident: 2457_CR28 doi: 10.1109/CVPR46437.2021.01636 – volume: 34 start-page: 29393 year: 2021 ident: 2457_CR32 publication-title: Adv. Neural. Inf. Process. Syst. – ident: 2457_CR22 doi: 10.1109/ICCV.2015.293 – ident: 2457_CR10 doi: 10.1016/j.neunet.2023.08.005 – ident: 2457_CR3 – ident: 2457_CR17 doi: 10.1109/CVPR.2019.00503 – volume: 9 start-page: 128467 year: 2021 ident: 2457_CR14 publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3110605 – ident: 2457_CR33 doi: 10.1109/CVPR.2016.90 – ident: 2457_CR16 – ident: 2457_CR18 – ident: 2457_CR31 – volume: 29 start-page: 1709 year: 2022 ident: 2457_CR11 publication-title: IEEE Signal Process. Lett. doi: 10.1109/LSP.2022.3194414 – ident: 2457_CR19 doi: 10.1109/CVPR.2017.316 – volume: 9 start-page: 166488 year: 2021 ident: 2457_CR15 publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3136567 – ident: 2457_CR25 doi: 10.1109/ICCV48922.2021.00885 – ident: 2457_CR29 doi: 10.1007/978-3-642-15561-1_16 – ident: 2457_CR26 doi: 10.1109/CVPR52688.2022.00784 – ident: 2457_CR20 – ident: 2457_CR21 doi: 10.1109/ICCV.2017.244 – volume: 124 year: 2022 ident: 2457_CR12 publication-title: Image Vis. Comput. doi: 10.1016/j.imavis.2022.104504 – ident: 2457_CR6 – ident: 2457_CR2 – ident: 2457_CR7 doi: 10.1109/TPAMI.2021.3103390 – ident: 2457_CR24 doi: 10.1109/TCSVT.2021.3111034 – volume: 2 start-page: 508 issue: 6 year: 2021 ident: 2457_CR8 publication-title: IEEE Trans. Artif. Intell. doi: 10.1109/TAI.2021.3110179 – ident: 2457_CR34 – ident: 2457_CR30 doi: 10.1109/CVPR.2017.572 – volume: 22 start-page: 79 issue: 1 year: 1951 ident: 2457_CR27 publication-title: Ann. Math. Stat. doi: 10.1214/aoms/1177729694 – ident: 2457_CR4 doi: 10.1109/CVPR42600.2020.00966 |
| SSID | ssj0000327868 |
| Score | 2.3318248 |
| Snippet | Source-free domain adaptation (SFDA) is from unsupervised domain adaptation (UDA) and do apply to the special situation in reality that the source domain data... |
| SourceID | proquest crossref springer |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 2405 |
| SubjectTerms | Adaptation Computer Imaging Computer Science Domains Image Processing and Computer Vision Labels Masks Multimedia Information Systems Original Paper Pattern Recognition and Graphics Robustness Self-supervised learning Signal,Image and Speech Processing Vision |
| Title | Robust self-supervised learning for source-free domain adaptation |
| URI | https://link.springer.com/article/10.1007/s11760-022-02457-z https://www.proquest.com/docview/2815363455 |
| Volume | 17 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED7xWGDgjSgveWADS2liO-5YEAWBYEAgwRT5cUZI0FakXfj1nJuEAgIkpgxxPHyXO3_newEcpNoSbyAnxyH5qsLqjHecCxwTRQQarUCMtcNX1-r8Tlzcy_u6KKxsst2bkOTEUk-L3dq5SnjMPo_hwpy_zcK8JN89JnLdpd2Pm5UkS3Nd1cBpFftvJlldLfPzNl9PpCnN_BYZnRw4vRVYqpki61aiXYUZ7K_BcjOFgdVKuQaLn1oKrkP3ZmDH5YiV-Bx4OR5GU1CiZ_V0iEdGJJVVN_Y8vCIyP3gxT31mvBlWUfkNuO2d3p6c83pMAnekPyOeBvLSCFevjDMhExpdpE25kD73yhLqljiCMDo1OpAj7RLvpVRBKS8wCdkmzPUHfdwCZmVuDC3piNARbZRWWYdOk1FLsO1E3oJ2g1Th6hbicZLFczFtfhzRLQjdYoJu8daCw49vhlUDjT9X7zYCKGplKotUk1lWmZCyBUeNUKavf99t-3_Ld2AhDpOvknF3YW70OsY9ohwjuw_z3d7x8XV8nj1cnu5P_rh3xvbQiw |
| linkProvider | Springer Nature |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLZ4HIADb8R45sANInVtmmbHCYEGDA5oSNyqPByEBNtEtwu_HmdtN0CAxLluDp9j53Mc2wAnsTLEGyjIsUixqjAq4S1rPcdIEoFGIxBD7fDtnew8iOvH9LEqCivq1-51SnLiqWfFbs1MRjy8Pg_pwoy_z8MikQEV9vJD3J7erERJnKmyBk7J0H8zSqpqmZ-X-XoizWjmt8zo5MC5XIfViimydqnaDZjD_ias1VMYWGWUm7DyqaXgFrTvB2ZcjFiBL54X42FwBQU6Vk2HeGJEUll5Y8_9GyJzg1f93Gfa6WGZld-G3uVF77zDqzEJ3JL9jHjsKUojXJ3UVvtEKLSBNmUidZmThlA3xBGEVrFWngJpGzmXptJL6QRGPtmBhf6gj7vATJppTSIt4VuiiamRxqJV5NQibFqRNaBZI5XbqoV4mGTxks-aHwd0c0I3n6CbvzfgdPrPsGyg8af0Qa2AvDKmIo8VuWWZiDRtwFmtlNnn31fb-5_4MSx1erfdvHt1d7MPy2GwfPkw9wAWRm9jPCT6MTJHk932Aa7I0G4 |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTxsxEB5BkCo4AKWtCKTUh95ai314vc4xKo2AtqiqQOK28mOMkNJNlN1c8usZZ3dJWrWVet5ZH2Y84288_mYA3ifKEG6gJMci5arCqJQPrfUcI0kAGo1ADNzhbzfy8k5c32f3Gyz-1Wv3riTZcBpCl6ayPp85f74mvsW5jHh4iR5KhzlfbsOOCGxg2tF3yej5liVKk1w1fDglQy_OKG2ZM39e5tfTaQ05f6uSrg6f8SHst6iRjRozv4QtLI_goJvIwFoHPYK9jfaCr2D0Y2oWVc0qnHheLWYhLFToWDsp4oERYGXN7T33c0Tmpj_1Y8m007OmQv8absefbz9d8nZkArfkSzVPPGVspGMntdU-FQptgFC5yFzupCELGMILQqtEK09JtY2cyzLppXQCI5--gV45LfEYmMlyrUlkKPxQxJgZaSxaRQEuwtiKvA9xp6nCtu3Ew1SLSbFuhBy0W5B2i5V2i2UfPjz_M2uaafxTetAZoGgdqyoSRSFapiLL-vCxM8r6899XO_k_8Xfw4vvFuPh6dfPlFHbDjPnmje4AevV8gW8JidTmbLXZngDQKdSh |
| 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=Robust+self-supervised+learning+for+source-free+domain+adaptation&rft.jtitle=Signal%2C+image+and+video+processing&rft.au=Tian%2C+Liang&rft.au=Zhou%2C+Lihua&rft.au=Zhang%2C+Hao&rft.au=Wang%2C+Zhenbin&rft.date=2023-07-01&rft.issn=1863-1703&rft.eissn=1863-1711&rft.volume=17&rft.issue=5&rft.spage=2405&rft.epage=2413&rft_id=info:doi/10.1007%2Fs11760-022-02457-z&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s11760_022_02457_z |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1863-1703&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1863-1703&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1863-1703&client=summon |