Few-Shot Object Detection With Multilevel Information Interaction for Optical Remote Sensing Images

• Published in: IEEE transactions on geoscience and remote sensing Vol. 62; pp. 1 - 14
• Main Authors: Wang, Lefan, Mei, Shaohui, Wang, Yi, Lian, Jiawei, Han, Zonghao, Chen, Xiaoning
• Format: Journal Article
• Language: English
• Published: New York IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aggregation; Bias; Detectors; Feature extraction; Few-shot learning (FSL); Metalearning; Misalignment; Modules; Object detection; Object recognition; optical remote sensing images (RSIs); Queries; Remote sensing; Semantics; Task analysis; Training
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2024.3410308

Metalearning has been widely applied to solve the few-shot object detection (FSOD) problem in natural scenes, which performs similarity measurement and information aggregation of the support set and the query set. However, regarding remote sensing images (RSIs), many difficulties caused by their disparities need to be further addressed, such as inconsistencies in imaging scale, direction, and background between support and query images. These result in feature misalignment and attention bias, interfering with model performance. In this article, a multilevel information interaction (MLII) strategy is proposed for FSOD to alleviate feature misalignment and attention bias. Information interactions are conducted within multiple scales of features and highlight similar regions of query and support features. A semantic enhancement module (SEM) is proposed to assist MLII in extracting key information and achieving more discriminative feature representation. Moreover, a feature cross-aggregation module (FCM) with separate classification losses is designed to train the detector to identify objects that coexist in query and support images. Extensive experiments demonstrate that the proposed method outperforms several state-of-the-art few-shot object detectors over commonly used benchmark datasets, i.e., DIOR and NWPU-10.