Label Decoupling Framework for Salient Object Detection

By Junhang Wei, Shuhui Wang, Zhe Wu, Chi Su, Qingming Huang, Qi Tian. Computer Vision and Pattern Recognition, 2020

337 citations recorded by the source corpus.

To get more accurate saliency maps, recent methods mainly focus on aggregating multi-level features from fully convolutional network (FCN) and introducing edge information as auxiliary supervision. Though remarkable progress has been achieved, we observe that the closer the pixel is to the edge, the more difficult it is to be predicted, because edge pixels have a very imbalance distribution. To address this problem, we propose a label decoupling framework (LDF) which consists of a label decoupling (LD) procedure and a feature interaction network (FIN). LD explicitly decomposes the original saliency map into body map and detail map, where body map concentrates on center areas of objects and detail map focuses on regions around edges. Detail map works better because it involves much more pixels than traditional edge supervision. Different from saliency map, body map discards edge pixels and only pays attention to center areas. This successfully avoids the distraction from edge pixels during training. Therefore, we employ two branches in FIN to deal with body map and detail map respectively. Feature interaction (FI) is designed to fuse the two complementary branches to predict the saliency map, which is then used to refine the two branches again. This iterative refinement is helpful for learning better representations and more precise saliency maps. Comprehensive experiments on six benchmark datasets demonstrate that LDF outperforms state-of-the-art approaches on different evaluation metrics.

Subfields: Computer Vision and Pattern Recognition, Urban Studies

View Paper: https://www.semanticscholar.org/paper/689f87d90ffba1e406199b7faee281650f7dd8a5

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. Huchuan Lu
3. Nian Liu
4. Junwei Han
5. Xiaoqi Zhao
6. Youwei Pang
7. Ming-Ming Cheng
8. Deng-Ping Fan

In Urban Studies

1. Junwei Han

Citations in the corpus

• Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection (2022, methodology): “For a fair comparison on SOD, the proposed model is retrained on DUTS [44] following the training strategies and techniques of [35,46,47,51,64].”
• 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]”
• Infrared and Visible Image Fusion via Decoupling Network (2022, methodology): “With the advent of DL, the DL-based saliency detection methods have become the trend in research, and their robustness and accuracy perform well than handcrafted meth-ods [33], [40].”