Box-DETR: Understanding and Boxing Conditional Spatial Queries

07/17/2023
by   Wenze Liu, et al.
0

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.

READ FULL TEXT

page 2

page 6

research
07/18/2022

Conditional DETR V2: Efficient Detection Transformer with Box Queries

In this paper, we are interested in Detection Transformer (DETR), an end...
research
09/12/2022

CenterFormer: Center-based Transformer for 3D Object Detection

Query-based transformer has shown great potential in constructing long-r...
research
01/04/2023

SPTS v2: Single-Point Scene Text Spotting

End-to-end scene text spotting has made significant progress due to its ...
research
11/24/2020

Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

3D object detection has attracted much attention thanks to the advances ...
research
09/15/2021

Anchor DETR: Query Design for Transformer-Based Detector

In this paper, we propose a novel query design for the transformer-based...
research
08/08/2021

From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder

In this paper, we present an Intersection-over-Union (IoU) guided two-st...
research
01/19/2021

Fast Convergence of DETR with Spatially Modulated Co-Attention

The recently proposed Detection Transformer (DETR) model successfully ap...

Please sign up or login with your details

Forgot password? Click here to reset