Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer

Hakjin Lee, MinKi Song, Jamyoung Koo, Junghoon Seo; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 1872-1882

Detection Transformers (DETR) have recently set new benchmarks in object detection. However their performance in detecting rotated objects lags behind established oriented object detectors. Our analysis identifies a key observation: the boundary discontinuity and square-like problem in bipartite matching poses an issue with assigning appropriate ground truths to predictions leading to du plicate low-confidence predictions. To address this we introduce a Hausdorff distance-based cost for bipartite matching which more accurately quantifies the discrepancy between predictions and ground truths. Additionally we find that a static denoising approach impedes the training of rotated DETR especially as the quality of the detector's predictions begins to exceed that of the noised ground truths. To overcome this we propose an adaptive query denoising method that employs bipartite matching to selectively eliminate noised queries that detract from model improvement. When compared to models adopting a ResNet-50 backbone our proposed model yields remarkable improvements achieving +4.18 AP50 +4.59 AP50 and +4.99 AP50 on DOTA-v2.0 DOTA-v1.5 and DIOR-R respectively.