Salient object detection has been long studied to identify the most visually attractive objects in images/videos. Recently, a growing amount of approaches have been proposed all of which rely on the contour/edge information to improve detection performance. The edge labels are either put into the loss directly or used as extra supervision. The edge and body can also be learned separately and then fused afterward. Both methods either lead to high prediction errors near the edge or cannot be trained in an end-to-end manner. Another problem is that existing methods may fail to detect objects of various sizes due to the lack of efficient and effective feature fusion mechanisms. In this work, we propose to decompose the saliency detection task into two cascaded sub-tasks, \emph{i.e.}, detail modeling and body filling. Specifically, the detail modeling focuses on capturing the object edges by supervision of explicitly decomposed detail label that consists of the pixels that are nested on the edge and near the edge. Then the body filling learns the body part which will be filled into the detail map to generate more accurate saliency map. To effectively fuse the features and handle objects at different scales, we have also proposed two novel multi-scale detail attention and body attention blocks for precise detail and body modeling. Experimental results show that our method achieves state-of-the-art performances on six public datasets.
DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation
Department of Computer Science and Engineering, Lehigh University（计算机科学与工程系，莱恩大学）；Department of Computer Science（计算机科学系）；Engineering, Lehigh University（工程系，莱恩大学）；Qualcomm AI Research（高通人工智能研究）
RGB-D Saliency Detection via Cascaded Mutual Information Minimization
Australian National University（澳大利亚国立大学）；IIAI（起源人工智能研究院）；Northwestern Polytechnical University（西北工业大学）；University of Technology Sydney（悉尼科技大学）；SenseTime（商汤科技）
Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection
Australian National University（澳大利亚国立大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）；Data61；Cognitive Computing Lab, Baidu Research（百度研究院认知计算实验室）
College of Land Science and Technology, China Agricultural University（土地科学与技术学院，中国农业大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（航空信息研究所，中国科学院）；Faculty of Geosciences and Engineering, Southwest Jiaotong University（地质科学与工程学院，西南交通大学）；Helmholtz-Zentrum Dresden-Rossendorf, Helmholtz Institute Freiberg for Resource Technology（德累斯顿-罗斯托克亥姆霍尔茨中心，资源技术亥姆霍尔茨研究所）；Lancaster Environment Centre, Lancaster University（兰卡斯特大学环境研究中心）
