Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
Authors:
Top Cited Papers
- 1 October 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6610-6619
Abstract
Detection transformer (DETR) relies on one-to-one assignment, assigning one ground-truth object to one prediction, for end-to-end detection without NMS post-processing. It is known that one-to-many assignment, assigning one ground-truth object to multiple predictions, succeeds in detection methods such as Faster R-CNN and FCOS. While the naive one-to-many assignment does not work for DETR, and it remains challenging to apply one-to-many assignment for DETR training. In this paper, we introduce Group DETR, a simple yet efficient DETR training approach that introduces a group-wise way for one-to-many assignment. This approach involves using multiple groups of object queries, conducting one-to-one assignment within each group, and performing decoder self-attention separately. It resembles data augmentation with automatically-learned object query augmentation. It is also equivalent to simultaneously training parameter-sharing networks of the same architecture, introducing more supervision and thus improving DETR training. The inference process is the same as DETR trained normally and only needs one group of queries without any architecture modification. Group DETR is versatile and is applicable to various DETR variants. The experiments show that Group DETR signifi-cantly speeds up the training convergence and improves the performance of various DETR-based models. Code will be available at https://github.com/Atten4Vis/GroupDETR.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 28 references indexed in Scilit:
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers2022
- PETR: Position Embedding Transformation for Multi-view 3D Object Detection2022
- Probabilistic Anchor Assignment with IoU Prediction for Object Detection2020
- End-to-End Object Detection with Transformers2020
- Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection2020
- nuScenes: A Multimodal Dataset for Autonomous Driving2020
- CenterMask: Real-Time Anchor-Free Instance Segmentation2020
- Learning Non-maximum Suppression2017
- Deep Residual Learning for Image Recognition2016
- Microsoft COCO: Common Objects in Context2014