Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection

By Huajun Zhou, Xiaohua Xie, J. Lai, Zixuan Chen, Lingxiao Yang. Computer Vision and Pattern Recognition, 2020

366 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/174199a4da0eae7d55949aeb43f3baff2400114d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ling Shao
2. Nian Liu
3. Junwei Han
4. Deng-Ping Fan
5. Yuchao Dai
6. Kaiyuan Wan
7. Ni Zhang
8. Jing Zhang

Citations in the corpus

• Visual Saliency Transformer (2021, methodology): “Image Depth GT VST BBS-Net [16] CoNet [25] HDFNet [48] JLDCF [18] UC-Net [76] Image GT VST GateNet [84] CSF [20] LDF [69] MINet [49] ITSD [87] EGNet [82]”
• Uncertainty-aware Joint Salient Object and Camouflaged Object Detection (2021, background): “SCRN [48], F(3)Net [46], ITSD [59], and it can indeed improve model performance.”