Multi-Scale Interactive Network for Salient Object Detection

By Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu. Computer Vision and Pattern Recognition, 2020

759 citations recorded by the source corpus.

Deep-learning based salient object detection methods achieve great progress. However, the variable scale and unknown category of salient objects are great challenges all the time. These are closely related to the utilization of multi-level and multi-scale features. In this paper, we propose the aggregate interaction modules to integrate the features from adjacent levels, in which less noise is introduced because of only using small up-/down-sampling rates. To obtain more efficient multi-scale features from the integrated features, the self-interaction modules are embedded in each decoder unit. Besides, the class imbalance issue caused by the scale variation weakens the effect of the binary cross entropy loss and results in the spatial inconsistency of the predictions. Therefore, we exploit the consistency-enhanced loss to highlight the fore-/back-ground difference and preserve the intra-class consistency. Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches. The source code will be publicly available at https://github.com/lartpang/MINet.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/2f2457b1182042e8cd3572022f106774fe16771c

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. Deng-Ping Fan
3. Huchuan Lu
4. Junwei Han
5. Ming-Ming Cheng
6. Jianbing Shen
7. Nian Liu
8. Wenguan Wang

In Sensory Systems

1. Junwei Han
2. Nian Liu
3. Ling Shao
4. Huchuan Lu
5. Dingwen Zhang
6. Xiaoqi Zhao
7. Lihe Zhang
8. Deng-Ping Fan

In Human-Computer Interaction

1. Ling Shao
2. Ge-Peng Ji
3. Youwei Pang
4. Xiaoqi Zhao
5. Junwei Han
6. Nian Liu
7. Deng-Ping Fan
8. Lihe Zhang

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].”
• Salient Object Detection via Integrity Learning (2021, methodology): “We compare the proposed approach with 14 very recent state-of-the-art methods, including Condinst [95], PointRend [96], PiCANet [46], RAS [97], AFNet [98], BASNet [52], CPD [58], EGNet [51], SCRN [55], F3Net [54], MINet [38], ITSD [99], GateNet [39] and VST [56].”
• Camouflaged Object Segmentation with Distraction Mining (2021, methodology): “…detection methods DSC [20] and BDRAR [72]; medical image segmentation methods UNet++ [71] and PraNet [13]; salient object detection methods PiCANet [33], BASNet [44], CPD [55], PFANet [69], EGNet [67], F3Net [53], GC-PANet [5], and MINet-R [40]; and camouflaged object segmentation method SINet [12].”
• 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]”
• Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, background): “Therefore, most state-of-the-art saliency detection networks [29,20,69,53,67,70,57,37,33] adopt U-shape as the encoderdecoder architecture.”