The class activation maps are generated from the final convolutional layer of CNN. They can
highlight discriminative object regions for the class of interest. These discovered object …

Convolutional neural networks (CNNs) are good at extracting contexture features within
certain receptive fields, while transformers can model the global long-range dependency …

As an essential problem in computer vision, salient object detection (SOD) has attracted an
increasing amount of research attention over the years. Recent advances in SOD are …

Salient object detection (SOD) is a long-standing research topic in computer vision with
increasing interest in the past decade. Since light fields record comprehensive information of …

This paper presents a new method for detecting salient objects in images using
convolutional neural networks (CNNs). The proposed network, named PAGE-Net, offers two …

Saliency detection on RGB-D images is receiving more and more research interests
recently. Previous models adopt the early fusion or the result fusion scheme to fuse the input …

Salient object detection is the pixel-level dense prediction task which can highlight the
prominent object in the scene. Recently U-Net framework is widely used, and continuous …

We explore the potential of pooling techniques on the task of salient object detection by
expanding its role in convolutional neural networks. In general, two pooling-based modules …

Segmentation is a fundamental task in medical image analysis. However, most existing
methods focus on primary region extraction and ignore edge information, which is useful for …

Predicting where people look in static scenes, aka visual saliency, has received significant
research interest recently. However, relatively less effort has been spent in understanding …