SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.11035 · ICCV · 2023

Cascade-DETR: Delving into High-Quality Universal Object Detection

Martin Danelljan, Hkust, Siyuan Li, Yu-Wing Tai, Chi-Keung Tang, Lei Ke, Fisher Yu, Mingqiao Ye

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

Figure 1. Cascade-DETR for high-quality universal object detection. We compare Faster R-CNN [35], DN-DETR [24] and our Cascade-DN-DETR on the constructed UDB10 benchmark. Cascade-DN-DETR gives a strong performance on a variety of benchmarks, spanning traffic, medical, art, open-world, etc. Taking the previous SOTA method DN-DETR [24] as baseline, our approach achieves 5.7 UniAP performance gain on the UDB10.

For agents

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

get_harvested_code_for_paper("2307.11035")
get_code_for_paper("2307.11035")
have("2307.11035")

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

curl https://syntology.ai/api/ran/2307.11035.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.11035.svg)](https://syntology.ai/paper/2307.11035)

Connect an agent — have() is free.