---
license: apache-2.0
tags:
- image-segmentation
- vision
datasets:
- coco
---

# DETRs with Collaborative Hybrid Assignments Training

## Introduction

In this paper, we present a novel collaborative hybrid assignments training scheme, namely Co-DETR, to learn more efficient and effective DETR-based detectors from versatile label assignment manners. 
1. **Encoder optimization**: The proposed training scheme can easily enhance the encoder's learning ability in end-to-end detectors by training multiple parallel auxiliary heads supervised by one-to-many label assignments. 
2. **Decoder optimization**: We conduct extra customized positive queries by extracting the positive coordinates from these auxiliary heads to improve attention learning of the decoder. 
3. **State-of-the-art performance**: Co-DETR with ViT-Large (304M parameters) is **the first model to achieve 66.0 AP on COCO test-dev.**

## Model Zoo

| Model | Backbone | Aug | Dataset | box AP (val) | box AP (minival) |
| --- | --- | --- | --- | --- | --- |
| Co-DETR | ViT-L | LSJ	| LVIS | 68.0 | 72.0 |

## How to use

We implement Co-DETR using [MMDetection V2.25.3](https://github.com/open-mmlab/mmdetection/releases/tag/v2.25.3) and [MMCV V1.5.0](https://github.com/open-mmlab/mmcv/releases/tag/v1.5.0). Please refer to our [github repo](https://github.com/Sense-X/Co-DETR/tree/main) for more details.

### Training
Train Co-Deformable-DETR + ResNet-50 with 8 GPUs:
```shell
sh tools/dist_train.sh projects/configs/co_deformable_detr/co_deformable_detr_r50_1x_coco.py 8 path_to_exp
```
Train using slurm:
```shell
sh tools/slurm_train.sh partition job_name projects/configs/co_deformable_detr/co_deformable_detr_r50_1x_coco.py path_to_exp
```

### Testing
Test Co-Deformable-DETR + ResNet-50 with 8 GPUs, and evaluate:
```shell
sh tools/dist_test.sh  projects/configs/co_deformable_detr/co_deformable_detr_r50_1x_coco.py path_to_checkpoint 8 --eval bbox
```
Test using slurm:
```shell
sh tools/slurm_test.sh partition job_name projects/configs/co_deformable_detr/co_deformable_detr_r50_1x_coco.py path_to_checkpoint --eval bbox
```

## Cite Co-DETR

If you find this repository useful, please use the following BibTeX entry for citation.

```latex
@inproceedings{zong2023detrs,
  title={Detrs with collaborative hybrid assignments training},
  author={Zong, Zhuofan and Song, Guanglu and Liu, Yu},
  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
  pages={6748--6758},
  year={2023}
}
```