`Bilateral Reference for High-Resolution Dichotomous Image Segmentation`

DIS-Sample_1	DIS-Sample_2

This repo is the official implementation of "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (arXiv 2024).

Authors: Peng Zheng, Dehong Gao, Deng-Ping Fan, Li Liu, Jorma Laaksonen, Wanli Ouyang, & Nicu Sebe.

[arXiv] [code] [stuff] [中文版]

Our BiRefNet has achieved SOTA on many similar HR tasks:

DIS:

Figure of Comparison on Papers with Codes (by the time of this work):

COD:

Figure of Comparison on Papers with Codes (by the time of this work):

HRSOD:

Figure of Comparison on Papers with Codes (by the time of this work):

Try our online demos for inference:

Inference and evaluation of your given weights:
Online Inference with GUI with adjustable resolutions:
Online Single Image Inference on Colab:

Model Zoo

For more general use of our BiRefNet, I managed to extend the original adademic one to more general ones for better application in real life.

Datasets and datasets are suggested to download from official pages. But you can also download the packaged ones: DIS, HRSOD, COD, Backbones.

Find performances (almost all metrics) of all models in the exp-TASK_SETTINGS folders in [stuff].

Models in the original paper, for comparison on benchmarks:

Task	Training Sets	Backbone	Download
DIS	DIS5K-TR	swin_v1_large	google-drive
COD	COD10K-TR, CAMO-TR	swin_v1_large	google-drive
HRSOD	DUTS-TR	swin_v1_large	google-drive
HRSOD	HRSOD-TR	swin_v1_large	google-drive
HRSOD	UHRSD-TR	swin_v1_large	google-drive
HRSOD	DUTS-TR, HRSOD-TR	swin_v1_large	google-drive
HRSOD	DUTS-TR, UHRSD-TR	swin_v1_large	google-drive
HRSOD	HRSOD-TR, UHRSD-TR	swin_v1_large	google-drive
HRSOD	DUTS-TR, HRSOD-TR, UHRSD-TR	swin_v1_large	google-drive

Models trained with customed data (massive, portrait), for general use in practical application:

Task	Training Sets	Backbone	Test Set	Metric (S, wF[, HCE])	Download
general use	DIS5K-TR,DIS-TEs, DUTS-TR_TE,HRSOD-TR_TE,UHRSD-TR_TE, HRS10K-TR_TE	swin_v1_large	DIS-VD	0.889, 0.840, 1152	google-drive
general use	DIS5K-TR,DIS-TEs, DUTS-TR_TE,HRSOD-TR_TE,UHRSD-TR_TE, HRS10K-TR_TE	swin_v1_tiny	DIS-VD	0.867, 0.809, 1182	Google-drive
general use	DIS5K-TR, DIS-TEs	swin_v1_large	DIS-VD	0.907, 0.865, 1059	google-drive
portrait segmentation	P3M-10k	swin_v1_large	P3M-500-P	0.982, 0.990	google-drive

Segmentation with box guidance:

In progress...

Model efficiency:

Screenshot from the original paper. All tests are conducted on a single A100 GPU.

Third-Party Creations

Concerning edge devices with less computing power, we provide a lightweight version with swin_v1_tiny as the backbone, which is x4+ faster and x5+ smaller. The details can be found in this issue and links there.

We found there've been some 3rd party applications based on our BiRefNet. Many thanks for their contribution to the community!
Choose the one you like to try with clicks instead of codes:

Applications:
- Thanks fal.ai/birefnet: this project on fal.ai encapsulates BiRefNet online with more useful options in UI and API to call the model.
- Thanks ZHO-ZHO-ZHO/ComfyUI-BiRefNet-ZHO: this project further improves the UI for BiRefNet in ComfyUI, especially for video data.
  
  https://github.com/ZhengPeng7/BiRefNet/assets/25921713/3a1c7ab2-9847-4dac-8935-43a2d3cd2671
- Thanks viperyl/ComfyUI-BiRefNet: this project packs BiRefNet as ComfyUI nodes, and makes this SOTA model easier use for everyone.
- Thanks Rishabh for offerring a demo for the easier single image inference on colab.
More Visual Comparisons
- Thanks twitter.com/ZHOZHO672070 for the comparison with more background-removal methods in images:
- Thanks twitter.com/toyxyz3 for the comparison with more background-removal methods in videos:
https://github.com/ZhengPeng7/BiRefNet/assets/25921713/40136198-01cc-4106-81f9-81c985f02e31

https://github.com/ZhengPeng7/BiRefNet/assets/25921713/1a32860c-0893-49dd-b557-c2e35a83c160

Usage

Environment Setup

# PyTorch==2.0.1 is used for faster training with compilation.
conda create -n dis python=3.9 -y && conda activate dis
pip install -r requirements.txt

Dataset Preparation

Download combined training / test sets I have organized well from: DIS--COD--HRSOD or the single official ones in the single_ones folder, or their official pages. You can also find the same ones on my BaiduDisk: DIS--COD--HRSOD.

Weights Preparation

Download backbone weights from my google-drive folder or their official pages.

Run

# Train & Test & Evaluation
./train_test.sh RUN_NAME GPU_NUMBERS_FOR_TRAINING GPU_NUMBERS_FOR_TEST
# See train.sh / test.sh for only training / test-evaluation.
# After the evluation, run `gen_best_ep.py` to select the best ckpt from a specific metric (you choose it from Sm, wFm, HCE (DIS only)).

Well-trained weights:

Download the BiRefNet-{TASK}-{EPOCH}.pth from [stuff]. Info of the corresponding (predicted_maps/performance/training_log) weights can be also found in folders like exp-BiRefNet-{TASK_SETTINGS} in the same directory.

You can also download the weights from the release of this repo.

The results might be a bit different from those in the original paper, you can see them in the eval_results-BiRefNet-{TASK_SETTINGS} folder in each exp-xx, we will update them in the following days. Due to the very high cost I used (A100-80G x 8) which many people cannot afford to (including myself....), I re-trained BiRefNet on a single A100-40G only and achieve the performance on the same level (even better). It means you can directly train the model on a single GPU with 36.5G+ memory. BTW, 5.5G GPU memory is needed for inference in 1024x1024. (I personally paid a lot for renting an A100-40G to re-train BiRefNet on the three tasks... T_T. Hope it can help you.)

But if you have more and more powerful GPUs, you can set GPU IDs and increase the batch size in config.py to accelerate the training. We have made all this kind of things adaptive in scripts to seamlessly switch between single-card training and multi-card training. Enjoy it :)

Some of my messages:

This project was originally built for DIS only. But after the updates one by one, I made it larger and larger with many functions embedded together. Finally, you can use it for any binary image segmentation tasks, such as DIS/COD/SOD, medical image segmentation, anomaly segmentation, etc. You can eaily open/close below things (usually in config.py):

Multi-GPU training: open/close with one variable.
Backbone choices: Swin_v1, PVT_v2, ConvNets, ...
Weighted losses: BCE, IoU, SSIM, MAE, Reg, ...
Adversarial loss for binary segmentation (proposed in my previous work MCCL).
Training tricks: multi-scale supervision, freezing backbone, multi-scale input...
Data collator: loading all in memory, smooth combination of different datasets for combined training and test.
... I really hope you enjoy this project and use it in more works to achieve new SOTAs.

Quantitative Results

Qualitative Results

Citation

@article{zheng2024birefnet,
  title={Bilateral Reference for High-Resolution Dichotomous Image Segmentation},
  author={Zheng, Peng and Gao, Dehong and Fan, Deng-Ping and Liu, Li and Laaksonen, Jorma and Ouyang, Wanli and Sebe, Nicu},
  journal={arXiv},
  year={2024}
}

Contact

Any question, discussion or even complaint, feel free to leave issues here or send me e-mails ([email protected]).