Learning Synergistic Attention for Light Field Salient Object Detection

Abstract

We propose a novel Synergistic Attention Network (SA-Net) to address the light field salient object detection by establishing a synergistic effect between multi-modal features with advanced attention mechanisms. Our SA-Net exploits the rich information of focal stacks via 3D convolutional neural networks, decodes the high-level features of multi-modal light field data with two cascaded synergistic attention modules, and predicts the saliency map using an effective feature fusion module in a progressive manner. Extensive experiments on three widely-used benchmark datasets show that our SA-Net outperforms 28 state-of-the-art models, sufficiently demonstrating its effectiveness and superiority. Our code is available at https://github.com/PanoAsh/SA-Net.

arXiv comment20 pages, 12 figures; Project Page https://github.com/PanoAsh/SA-Net ; Accepted to BMVC-21

References in corpus (7)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• Enhanced-alignment Measure for Binary Foreground Map Evaluation
• Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
• Structure-measure: A New Way to Evaluate Foreground Maps
• Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
• Making a Case for 3D Convolutions for Object Segmentation in Videos

Cited by in corpus (1)

• CMA-Net: A Cascaded Mutual Attention Network for Light Field Salient Object Detection