![](https://d3ilqtpdwi981i.cloudfront.net/jBO5x16nv2NaCTF46Sk7Y2bA30c=/425x550/smart/https://bepress-attached-resources.s3.amazonaws.com/uploads/a7/b2/3c/a7b23cc1-bca7-4320-a2a1-64a90b13e5d6/thumbnail_b4a72b2b-f1b0-4f9a-a265-867fea44e8be.jpg)
Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks. Despite its success, the said paradigm is still constrained by several factors, such as (i) low-quality region proposals for novel classes and (ii) negligence of the inter-class correlation among different classes. Such limitations hinder the generalization of base-class knowledge for the detection of novel-class objects. In this work, we design Meta-DETR, which (i) is the first image-level few-shot detector, and (ii) introduces a novel inter-class correlational meta-learning strategy to capture and leverage the correlation among different classes for robust and accurate few-shot object detection. Meta-DETR works entirely at image level without any region proposals, which circumvents the constraint of inaccurate proposals in prevalent few-shot detection frameworks. In addition, the introduced correlational meta-learning enables Meta-DETR to simultaneously attend to multiple support classes within a single feedforward, which allows to capture the inter-class correlation among different classes, thus significantly reducing the misclassification over similar classes and enhancing knowledge generalization to novel classes. Experiments over multiple few-shot object detection benchmarks show that the proposed Meta-DETR outperforms state-of-the-art methods by large margins. The implementation codes are available at https://github.com/ZhangGongjie/Meta-DETR. © 2022, CC BY-NC-ND.
- Class Correlation,
- Few-Shot Learning,
- Few-Shot Object Detection,
- Meta-Learning,
- Object Detection
Preprint: arXiv
Archived with thanks to arXiv
Preprint License: CC by NC-ND 4.0
Uploaded 23 September 2022