Exploring multi-scale deformable context and channel-wise attention for salient object detection
| Autor: | Zuntian Chen, Qiang Zhang, Hang Qi, Yi Liu, Zhen Huo, Lei Li, Mingxing Duanmu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
0209 industrial biotechnology
business.industry Computer science Cognitive Neuroscience Context (language use) Pattern recognition 02 engineering and technology Convolutional neural network Computer Science Applications 020901 industrial engineering & automation Artificial Intelligence Salience (neuroscience) Feature (computer vision) 0202 electrical engineering electronic engineering information engineering Benchmark (computing) 020201 artificial intelligence & image processing Artificial intelligence Scale (map) business Sensory cue Communication channel |
| Zdroj: | Neurocomputing. 428:92-103 |
| ISSN: | 0925-2312 |
| DOI: | 10.1016/j.neucom.2020.11.022 |
| Popis: | Contextual information has played an important role in salient object detection. However, due to the fixed geometric structures of convolution kernels employed by existing Convolutional Neural Networks (CNNs) based methods, it is difficult to extract meaningfully visual contexts for those salient objects with varying sizes and non-rigid shapes. To address this problem, in this paper, we propose a Multi-Scale Deformation Module (MSDM) to capture multi-scale visual cues and varying shapes of salient objects. Moreover, most existing CNNs based methods treat all channels of feature maps equally, which tends to differ from the fact that different channels actually contribute differently to saliency prediction. For that, we involve a novel Channel-Wise Attention Mechanism (CWAM) after MSDM to highlight those informative channels while suppressing those confusing ones. Experimental results on five benchmark datasets demonstrate the superiority of the proposed method over the state-of-the-art approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect