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

22 Mar 2021  ·  Gongjie Zhang, Zhipeng Luo, Kaiwen Cui, Shijian Lu ·

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.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Object Detection MS-COCO (10-shot) Meta-DETR (Multi-Scale Feature) AP 17.8 # 4
Few-Shot Object Detection MS-COCO (10-shot) Meta-DETR (Single-Scale Feature) AP 16.7 # 5
Few-Shot Object Detection MS-COCO (30-shot) Meta-DETR (Multi-Scale Feature) AP 22.9 # 2
Few-Shot Object Detection MS-COCO (30-shot) Meta-DETR (Single-Scale Feature) AP 21.3 # 4

Methods