SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.08353 · 2023

Box-DETR: Understanding and Boxing Conditional Spatial Queries

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

Conditional spatial queries are recently introduced into DEtection TRansformer (DETR) to accelerate convergence. In DAB-DETR, such queries are modulated by the so-called conditional linear projection at each decoder stage, aiming to search for positions of interest such as the four extremities of the box. Each decoder stage progressively updates the box by predicting the anchor box offsets, while in cross-attention only the box center is informed as the reference point. The use of only box center, however, leaves the width and height of the previous box unknown to the current stage, which hinders accurate prediction of offsets. We argue that the explicit use of the entire box information in cross-attention matters. In this work, we propose Box Agent to condense the box into head-specific agent points. By replacing the box center with the agent point as the reference point in each head, the conditional cross-attention can search for positions from a more reasonable starting point by considering the full scope of the previous box, rather than always from the previous box center. This significantly reduces the burden of the conditional linear projection. Experimental results show that the box agent leads to not only faster convergence but also improved detection performance, e.g., our single-scale model achieves $44.2$ AP with ResNet-50 based on DAB-DETR. Our Box Agent requires minor modifications to the code and has negligible computational workload. Code is available at https://github.com/tiny-smart/box-detr.

For agents

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

get_harvested_code_for_paper("2307.08353")
get_code_for_paper("2307.08353")
have("2307.08353")

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

curl https://syntology.ai/api/ran/2307.08353.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.08353.svg)](https://syntology.ai/paper/2307.08353)

Connect an agent — have() is free.