Suppress and Balance: A Simple Gated Network for Salient Object Detection

By Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, Lei Zhang. European Conference on Computer Vision, 2020

518 citations recorded by the source corpus.

Most salient object detection approaches use U-Net or feature pyramid networks (FPN) as their basic structures. These methods ignore two key problems when the encoder exchanges information with the decoder: one is the lack of interference control between them, the other is without considering the disparity of the contributions of different encoder blocks. In this work, we propose a simple gated network (GateNet) to solve both issues at once. With the help of multilevel gate units, the valuable context information from the encoder can be optimally transmitted to the decoder. We design a novel gated dual branch structure to build the cooperation among different levels of features and improve the discriminability of the whole network. Through the dual branch design, more details of the saliency map can be further restored. In addition, we adopt the atrous spatial pyramid pooling based on the proposed "Fold" operation (Fold-ASPP) to accurately localize salient objects of various scales. Extensive experiments on five challenging datasets demonstrate that the proposed model performs favorably against most state-of-the-art methods under different evaluation metrics.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a0f9736c164afe7f57e232fe6c3e626ffee333f8

How researchers see this paper

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

In Cognitive Neuroscience

1. Deng-Ping Fan
2. Ling Shao
3. Huchuan Lu
4. Xiaoqi Zhao
5. Youwei Pang
6. Ali Borji
7. Jufeng Yang
8. Junwei Han

In Computer Vision and Pattern Recognition

1. Ling Shao
2. Deng-Ping Fan
3. Huchuan Lu
4. Ming-Ming Cheng
5. Jianbing Shen
6. Ali Borji
7. Nian Liu
8. Junwei Han

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]”
• BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, methodology): “/github.com/zyjwuyan/BBS-Net. 2 RELATED WORKS 2.1 Salient Object Detection Over the past several decades, SOD [38]–[40] has garnered significant research attention due to its diverse applications [41]–[43]. In early years, SOD methods were mainly based on intrinsic prior knowledge such as center-surr”
• Structure-Measure: A New Way to Evaluate Foreground Maps (2017, unknown): “Finally, we also evaluate our measure over SOD dataset, which is a subset of the BSDS dataset.”
• Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection (2021, background): “To solve the ambiguities caused by indistinguishable textures, unlike generic / salient object detection models [9,16,31,32,35,43,59,61], current COD approaches usually distill extra features from the shared context (e.”
• Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection (2022, methodology): “Following the setting of the method [67], in C-Net, we use an ASPP [3] simplified according to our needs as the feature compression layer corresponding to the “layer4” of E-Net and other layers are simply composed of an independent “Conv3×3-BN-ReLU” (3×3 CBR) unit.”