detection

COCO Object detection with TransNeXt

Getting started

This repository is the official PyTorch implementation of TransNeXt for COCO object detection.

Our code is built on MMDetection. The Mask R-CNN method is built on MMDetection version 2.28.2, while the DINO method is built on MMDetection version 3.0.0.

Since MMDetection is no longer compatible with the previous version of the configuration file format after 3.0.0, different environments need to be built for the two methods. The requirements.txt can be found in their respective folders.

Model Zoo

COCO object detection and instance segmentation results using the Mask R-CNN method:

Backbone	Pretrained Model	Lr Schd	box mAP	mask mAP	#Params	Download	Config	Log
TransNeXt-Tiny	ImageNet-1K	1x	49.9	44.6	47.9M	model	config	log
TransNeXt-Small	ImageNet-1K	1x	51.1	45.5	69.3M	model	config	log
TransNeXt-Base	ImageNet-1K	1x	51.7	45.9	109.2M	model	config	log

• When we checked the training logs, we found that the mask mAP and other detailed performance of the Mask R-CNN using the TransNeXt-Tiny backbone were even better than reported in the paper (versions V1 and V2). We have already fixed this in version V3 (it should be a data entry error).

COCO object detection results using the DINO method:

Backbone	Pretrained Model	scales	epochs	box mAP	#Params	Download	Config	Log
TransNeXt-Tiny	ImageNet-1K	4scale	12	55.1	47.8M	model	config	log
TransNeXt-Tiny	ImageNet-1K	5scale	12	55.7	48.1M	model	config	log
TransNeXt-Small	ImageNet-1K	5scale	12	56.6	69.6M	model	config	log
TransNeXt-Base	ImageNet-1K	5scale	12	57.1	110M	model	config	log

How to use

The code & tutorial for the Mask R-CNN method are >> here <<

The code & tutorial for the DINO method are >> here <<

Acknowledgement

The released script for Object Detection with TransNeXt is built based on the MMDetection and timm library.

License

This project is released under the Apache 2.0 license. Please see the LICENSE file for more information.

Citation

If you find our work helpful, please consider citing the following bibtex. We would greatly appreciate a star for this project.

@InProceedings{shi2023transnext,
  author    = {Dai Shi},
  title     = {TransNeXt: Robust Foveal Visual Perception for Vision Transformers},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  year      = {2024},
  pages     = {17773-17783}
}