SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.07598 · 2023

Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.07598")
get_code_for_paper("2305.07598")
have("2305.07598")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.07598.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.07598.svg)](https://syntology.ai/paper/2305.07598)

Connect an agent — have() is free.