Papers › Dynamic Relevance Learning for Few-Shot Object Detection

Dynamic Relevance Learning for Few-Shot Object Detection

4 Aug 2021arXiv:2108.02235archive 2025-07-28

Weijie Liu, Chong Wang, Haohe Li, Shenghao Yu, Jiafei Wu

Expensive bounding-box annotations have limited the development of object detection task. Thus, it is necessary to focus on more challenging task of few-shot object detection. It requires the detector to recognize objects of novel classes with only a few training samples. Nowadays, many existing popular methods adopting training way similar to meta-learning have achieved promising performance, such as Meta R-CNN series. However, support data is only used as the class attention to guide the detecting of query images each time. Their relevance to each other remains unexploited. Moreover, a lot of recent works treat the support data and query images as independent branch without considering the relationship between them. To address this issue, we propose a dynamic relevance learning model, which utilizes the relationship between all support images and Region of Interest (RoI) on the query images to construct a dynamic graph convolutional network (GCN). By adjusting the prediction distribution of the base detector using the output of this GCN, the proposed model serves as a hard auxiliary classification task, which guides the detector to improve the class representation implicitly. Comprehensive experiments have been conducted on Pascal VOC and MS-COCO dataset. The proposed model achieves the best overall performance, which shows its effectiveness of learning more generalized features. Our code is available at https://github.com/liuweijie19980216/DRL-for-FSOD.

PaperPDFCode

Code

liuweijie19980216/DRL-for-FSOD officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Few-Shot Object DetectionMeta-LearningObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Class AttentionGCN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections