Learning Synergistic Attention for Light Field Salient Object Detection
This work addresses salient object detection in light field images, a domain-specific computer vision task, with incremental improvements through novel attention modules.
The paper tackled light field salient object detection by proposing a Synergistic Attention Network (SA-Net) that integrates multi-modal features with attention mechanisms, achieving state-of-the-art performance by outperforming 28 existing models on three benchmark datasets.
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.