CVLGMay 12, 2023

Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer

arXiv:2305.07598v520 citations
Originality Incremental advance
AI Analysis

This work addresses a specific bottleneck in rotated object detection for computer vision applications, representing an incremental advancement over existing DETR methods.

The paper tackles the problem of rotated object detection with Detection Transformers (DETR), which underperform compared to oriented detectors, by introducing a Hausdorff distance-based matching cost and adaptive query denoising, resulting in improvements of +4.18 to +4.99 AP50 on benchmark datasets.

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 duplicate 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 $\textbf{+4.18}$ AP$_{50}$, $\textbf{+4.59}$ AP$_{50}$, and $\textbf{+4.99}$ AP$_{50}$ on DOTA-v2.0, DOTA-v1.5, and DIOR-R, respectively.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes