English

Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation

Computer Vision and Pattern Recognition 2022-08-02 v1 Artificial Intelligence Machine Learning Multimedia

Abstract

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.

Keywords

Cite

@article{arxiv.2208.00219,
  title  = {Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation},
  author = {Gongjie Zhang and Zhipeng Luo and Kaiwen Cui and Shijian Lu and Eric P. Xing},
  journal= {arXiv preprint arXiv:2208.00219},
  year   = {2022}
}

Comments

Accepted by T-PAMI (IEEE Transactions on Pattern Analysis and Machine Intelligence). Codes: https://github.com/ZhangGongjie/Meta-DETR

R2 v1 2026-06-25T01:21:01.187Z