|国家预印本平台
首页|Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization

Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization

Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization

来源:Arxiv_logoArxiv
英文摘要

Despite advancements in Transformer-based detectors for small object detection (SOD), recent studies show that these detectors still face challenges due to inherent noise sensitivity in feature pyramid networks (FPN) and diminished query quality in existing label assignment strategies. In this paper, we propose a novel Noise-Resilient Query Optimization (NRQO) paradigm, which innovatively incorporates the Noise-Tolerance Feature Pyramid Network (NT-FPN) and the Pairwise-Similarity Region Proposal Network (PS-RPN). Specifically, NT-FPN mitigates noise during feature fusion in FPN by preserving spatial and semantic information integrity. Unlike existing label assignment strategies, PS-RPN generates a sufficient number of high-quality positive queries by enhancing anchor-ground truth matching through position and shape similarities, without the need for additional hyperparameters. Extensive experiments on multiple benchmarks consistently demonstrate the superiority of NRQO over state-of-the-art baselines.

Xiaocheng Fang、Jieyi Cai、Huanyu Liu、Wenxiu Cai、Yishu Liu、Bingzhi Chen

计算技术、计算机技术

Xiaocheng Fang,Jieyi Cai,Huanyu Liu,Wenxiu Cai,Yishu Liu,Bingzhi Chen.Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization[EB/OL].(2025-07-25)[2025-08-18].https://arxiv.org/abs/2507.19059.点此复制

评论