Visual Attention Network (VAN) for Segmentaion

This repo is a PyTorch implementation of applying VAN (Visual Attention Network) to semantic segmentation. The code is based on mmsegmentaion.

More detailes can be found in

Results

Notes: Pre-trained models can be found in Visual Attention Network for Classification.

VAN + UperNet

Backbone	Iters	mIoU	Config	Download
VAN-Tiny	160K	41.1	config
VAN-Small	160K	44.9	config
VAN-Base	160K	48.3	config
VAN-Large	160K	50.1	config

Notes: In this scheme, we use multi-scale validation following Swin-Transformer.

VAN + Semantic FPN

Backbone	Iters	mIoU	Config	Download
VAN-Tiny	40K	38.5	config
VAN-Small	40K	42.9	config
VAN-Base	40K	46.7	config
VAN-Large	40K	48.1	config

Preparation

Install MMSegmentation and download ADE20K according to the guidelines in MMSegmentation.

Training

We use 8 GPUs for training by default. Run:

dist_train.sh /path/to/config 8

Evaluation

To evaluate the model, run:

dist_test.sh /path/to/config /path/to/checkpoint_file 8 --out results.pkl --eval mIoU

Acknowledgment

Our implementation is mainly based on mmsegmentaion, Swin-Transformer, and PoolFormer. Thanks for their authors.

LICENSE

This repo is under the Apache-2.0 license. For commercial use, please contact the authors.