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

TL;DR

Meta-DETR introduces a proposal-free, image-level few-shot object detection framework that leverages inter-class correlation to improve generalization and accuracy on novel classes, outperforming existing methods.

Contribution

It proposes Meta-DETR, a novel few-shot detection method that uses correlational aggregation and operates at image level without region proposals, enhancing inter-class correlation exploitation.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Effectively captures inter-class correlation to reduce misclassification.

Operates entirely at image level without region proposals.

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 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, a novel few-shot detection framework that incorporates correlational aggregation for meta-learning into DETR detection frameworks. Meta-DETR works entirely at image level without any region proposals, which circumvents the constraint of inaccurate proposals in prevalent few-shot detection frameworks. Besides, Meta-DETR can simultaneously attend to multiple support classes within a single feed-forward. This unique design allows capturing the inter-class correlation among different classes, which significantly reduces the misclassification of similar classes and enhances 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 will be released at https://github.com/ZhangGongjie/Meta-DETR.