Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection

Huajun Zhou, Xiaohua Xie, Jian-Huang Lai, Zixuan Chen, Lingxiao Yang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 9141-9150

Abstract


Recently, contour information largely improves the performance of saliency detection. However, the discussion on the correlation between saliency and contour remains scarce. In this paper, we first analyze such correlation and then propose an interactive two-stream decoder to explore multiple cues, including saliency, contour and their correlation. Specifically, our decoder consists of two branches, a saliency branch and a contour branch. Each branch is assigned to learn distinctive features for predicting the corresponding map. Meanwhile, the intermediate connections are forced to learn the correlation by interactively transmitting the features from each branch to the other one. In addition, we develop an adaptive contour loss to automatically discriminate hard examples during learning process. Extensive experiments on six benchmarks well demonstrate that our network achieves competitive performance with a fast speed around 50 FPS. Moreover, our VGG-based model only contains 17.08 million parameters, which is significantly smaller than other VGG-based approaches. Code has been made available at: https://github.com/moothes/ITSD-pytorch.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhou_2020_CVPR,
author = {Zhou, Huajun and Xie, Xiaohua and Lai, Jian-Huang and Chen, Zixuan and Yang, Lingxiao},
title = {Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}