Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911077363613696 |
|---|---|
| author | Fang, Xiaocheng Cai, Jieyi Liu, Huanyu Cai, Wenxiu Liu, Yishu Chen, Bingzhi |
| author_facet | Fang, Xiaocheng Cai, Jieyi Liu, Huanyu Cai, Wenxiu Liu, Yishu Chen, Bingzhi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19059 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization Fang, Xiaocheng Cai, Jieyi Liu, Huanyu Cai, Wenxiu Liu, Yishu Chen, Bingzhi Computer Vision and Pattern Recognition 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. |
| title | Revisiting DETR for Small Object Detection via Noise-Resilient Query Optimization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.19059 |