RGB-T Image Saliency Detection via Collaborative Graph Learning
This work addresses saliency detection for computer vision applications by fusing RGB and thermal data, offering an incremental improvement with a new dataset.
The paper tackles RGB-T image saliency detection by proposing a collaborative graph learning algorithm that uses hierarchical deep features to jointly learn graph affinity and node saliency, achieving favorable performance against state-of-the-art methods on both public and a new dataset of 1000 RGB-T image pairs.
Image saliency detection is an active research topic in the community of computer vision and multimedia. Fusing complementary RGB and thermal infrared data has been proven to be effective for image saliency detection. In this paper, we propose an effective approach for RGB-T image saliency detection. Our approach relies on a novel collaborative graph learning algorithm. In particular, we take superpixels as graph nodes, and collaboratively use hierarchical deep features to jointly learn graph affinity and node saliency in a unified optimization framework. Moreover, we contribute a more challenging dataset for the purpose of RGB-T image saliency detection, which contains 1000 spatially aligned RGB-T image pairs and their ground truth annotations. Extensive experiments on the public dataset and the newly created dataset suggest that the proposed approach performs favorably against the state-of-the-art RGB-T saliency detection methods.