A learning-based method using data augmentation for light field salient object detection
Xi Zhu, Xucheng Wang, Zhenrong Zheng · 2023
In this paper, a new method is proposed for light field SOD by using convolutional neural networks. First, the light field dataset is extended by geometric transformations such as stretching, cropping, flipping, rotating, etc. The augmented data are then weighted with natural data to train the light field SOD. We propose a mutual attention approach in this process, extracting and fusing features from RGB images as well as depth maps. Therefore, our network can generate an accurate saliency map from the input light field images after training. The obtained saliency map can provide reliable a priori information for tasks such as semantic segmentation, target recognition, and visual tracking.