Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment

By Qiang Chen, Xiaokang Chen, Jian Wang, Haocheng Feng, Junyu Han, Errui Ding, Gang Zeng, Jingdong Wang. 2022

254 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Lei Zhang
2. Ziwei Liu
3. Chen Change Loy
4. Jianwei Yang
5. Ping Luo
6. Feng Li
7. Hao Zhang
8. Kai Chen

In Computer Vision and Pattern Recognition

1. Lei Zhang
2. Dacheng Tao
3. Luc Van Gool
4. Chen Change Loy
5. Xiaogang Wang
6. Ping Luo
7. Ming-Hsuan Yang
8. Jianwei Yang

In Model Architectures

1. Jianwei Yang
2. Feng Li
3. Hao Zhang
4. Lei Zhang
5. Shilong Liu
6. Guiguang Ding
7. Ping Luo
8. Hang Su

Citations in the corpus

• Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection (2023, background): “DETR was first proposed in [2] and then has been improved from many directions [4, 5, 12, 17, 33, 50, 64] in the past few years.”
• Transformer-Based Visual Segmentation: A Survey (2023, background): “Group DETR [183] proposes group-wise one-to-many assignments during training.”
• DiffusionDet: Diffusion Model for Object Detection (2022, background): “Since then, the query-based detection paradigm has attracted great attention and inspired a series of following works [12,24,43,51,58,64,66,90,91,108,111, 115].”
• YOLOv10: Real-Time End-to-End Object Detection (2024, background): “Since then, various DETR variants have been proposed to enhance its performance and efficiency [42, 67, 56, 30, 36, 28, 5, 77, 82].”
• Context Autoencoder for Self-supervised Representation Learning (2022, unknown): “The detection model is built upon ViT-Huge [26], DINO [98], and Group DETR [16] (see [17] for more details).”