A Unified Transformer Framework for Group-Based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection
Yukun Su, Jingliang Deng, Ruizhou Sun, Guosheng Lin, Hanjing Su, Qingyao Wu
Abstract
Humans tend to mine objects by learning from a group of images or several frames of video since we live in a dynamic world. In the computer vision area, many researchers focus on co-segmentation (CoS), co-saliency detection (CoSD) and video salient object detection (VSOD) to discover the co-occurrent objects. However, previous approaches design different networks for these similar tasks separately, and they are difficult to apply to each other. Besides, they fail to take full advantage of the cues among inter- and intra-feature within a group of images. In this paper, we introduce a unified framework to tackle these issues from a unified view, term as <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">UFGS</b> ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U</b> nified <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</b> ramework for <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</b> roup-based <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b> egmentation). Specifically, we first introduce a transformer block, which views the image feature as a patch token and then captures their long-range dependencies through the self-attention mechanism. This can help the network to excavate the patch-structured similarities among the relevant objects. Furthermore, we propose an intra-MLP learning module to produce self-mask to enhance the network to avoid partial activation. Extensive experiments on four CoS benchmarks (PASCAL, iCoseg Internet and MSRC), three CoSD benchmarks (Cosal2015, CoSOD3k, and CocA) and five VSOD benchmarks (DAVIS <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$_{16}$</tex-math></inline-formula> , FBMS, ViSal, SegV2, and DAVSOD) show that our method outperforms other state-of-the-arts on three different tasks in both accuracy and speed by using the same network architecture, which can reach 140 FPS in real-time.