/ Machine Learning

BASNet: Boundary Aware Salient Object Detection

BASNet: Boundary Aware Salient Object Detection

BASNet

Code for paper 'BASNet: Boundary-Aware Salient Object Detection', Xuebin Qin, Zichen Zhang, Chenyang Huang, Chao Gao, Masood Dehghan and Martin Jagersand. (supplementary)

Required libraries

Python 3.6
numpy 1.15.2
scikit-image 0.14.0
PIL 5.2.0
PyTorch 0.4.0
torchvision 0.2.1
glob

The SSIM loss is adapted from pytorch-ssim.

Usage

  1. Clone this repo
git clone https://github.com/NathanUA/BASNet.git
  1. Download the pre-trained model basnet.pth and put it into the dirctory 'saved_models/basnet_bsi/'

  2. Cd to the directory 'BASNet', run the training or inference process by command: python basnet_train.py
    or python basnet_test.py respectively.

We also provide the predicted saliency maps for datasets SOD, ECSSD, DUT-OMRON, PASCAL-S, HKU-IS and DUTS-TE.

Architecture

architecture

Quantitative Comparison

quan

Qualitative Comparison

qual

Citation

@InProceedings{Qin_2019,
  author = {Qin, Xuebin and Zhang, Zichen and Huang, Chenyang and Gao, Chao and Dehghan, Masood and Jagersand, Martin},
  title = {BASNet: Boundary Aware Salient Object Detection},
  year = {2019}
}

GitHub