2025-01-14-fu25a.md

title	booktitle	year	volume	series	month	publisher	pdf	url	openreview	abstract	layout	issn	id	tex_title	firstpage	lastpage	page	order	cycles	bibtex_editor	editor	bibtex_author	author	date	address	container-title	genre	issued	extras
Enhancing DETRs for Small Object Detection via Multi-Scale Refinement and Query-Aided Mining	Proceedings of the 16th Asian Conference on Machine Learning	2025	260	Proceedings of Machine Learning Research	0	PMLR	https://raw.githubusercontent.com/mlresearch/v260/main/assets/fu25a/fu25a.pdf	https://proceedings.mlr.press/v260/fu25a.html	RDa1Uj27U9	Small object detection (SOD) aims to precisely localize and accurately classify objects from limited spatial extent and discernible features. Despite significant advancements in object detection driven by CNN-based and Transformer-based methods, SOD remains a significant challenge. This is primarily due to their minimal spatial dimensions and distinct features which pose difficulties in both computational efficiency and effective supervision. Particularly, Transformer-based detectors suffer from the high computational cost caused by the introduction of a feature pyramid network (FPN) and the sparse supervision for the encoder output due to insufficient positive queries. Current approaches attempt to mitigate these issues through sparse attention mechanisms and auxiliary one-to-many label assignment strategies. However, these approaches often still suffer from inefficiencies in processing multi-scale information and a deficiency in generating adequate positive queries for small objects. To address this issue, we propose a novel small object detector MRQM, which integrates Multi-scale Refinement and Query-aided Mining. The scale-aware encoder strategically refines features across multiple scales from a bi-directional feature pyramid network (BiFPN) through iterative updates. This process not only reduces redundant computations but also significantly enhances the representation of features at various scales. Furthermore, the IoU-aware head integrates the dynamic anchors mining strategy and one-to-many label assignments to fully mine potential high-quality auxiliary positive queries for small instances, and mitigate issues related to sparse supervision for the encoder. Extensive experiments on the SODA-D and VisDrone datasets consistently demonstrate the superiority and effectiveness of our MRQM method.	inproceedings	2640-3498	fu25a	Enhancing DETRs for Small Object Detection via Multi-Scale Refinement and Query-Aided Mining	936	951	936-951	936	false	Nguyen, Vu and Lin, Hsuan-Tien	given family Vu Nguyen given family Hsuan-Tien Lin	Fu, Sisi and Chen, Zhiming and Fang, Xiaocheng and Cai, Jieyi and Liu, Huanyu and Wen, Huosheng and Chen, Bingzhi	given family Sisi Fu given family Zhiming Chen given family Xiaocheng Fang given family Jieyi Cai given family Huanyu Liu given family Huosheng Wen given family Bingzhi Chen	2025-01-14		Proceedings of the 16th Asian Conference on Machine Learning	inproceedings	date-parts 2025 1 14