RQFormer: Rotated Query Transformer for End-to-End Oriented Object Detection
Jiaqi Zhao, Zeyu Ding, Yong Zhou, Hancheng Zhu, Wenliang Du, Rui Yao,, Abdulmotaleb El Saddik

TL;DR
RQFormer introduces a novel rotated query transformer with aligned attention and distinct query selection, significantly improving end-to-end oriented object detection accuracy across multiple datasets.
Contribution
The paper proposes RQFormer, a new end-to-end oriented detector combining Rotated RoI Attention and Selective Distinct Queries for better alignment and optimization.
Findings
Effective on remote sensing datasets
Improves one-to-one label assignment
Extends to horizontal object detection
Abstract
Oriented object detection presents a challenging task due to the presence of object instances with multiple orientations, varying scales, and dense distributions. Recently, end-to-end detectors have made significant strides by employing attention mechanisms and refining a fixed number of queries through consecutive decoder layers. However, existing end-to-end oriented object detectors still face two primary challenges: 1) misalignment between positional queries and keys, leading to inconsistency between classification and localization; and 2) the presence of a large number of similar queries, which complicates one-to-one label assignments and optimization. To address these limitations, we propose an end-to-end oriented detector called the Rotated Query Transformer, which integrates two key technologies: Rotated RoI Attention (RRoI Attention) and Selective Distinct Queries (SDQ). First,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Remote-Sensing Image Classification · Advanced Neural Network Applications
