Results 11 to 20 of about 622,575 (227)
Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects [PDF]
arXiv, 2018 Salient object detection is a problem that has been considered in detail and many solutions proposed. In this paper, we argue that work to date has addressed a problem that is relatively ill-posed. Specifically, there is not universal agreement about what constitutes a salient object when multiple observers are queried.
Md Amirul Islam +2 more
arxiv +3 more sources
A Simple Pooling-Based Design for Real-Time Salient Object Detection [PDF]
Computer Vision and Pattern Recognition, 2019 We solve the problem of salient object detection by investigating how to expand the role of pooling in convolutional neural networks. Based on the U-shape architecture, we first build a global guidance module (GGM) upon the bottom-up pathway, aiming at ...
Jiangjiang Liu +4 more
openalex +3 more sources
Deep Contrast Learning for Salient Object Detection [PDF]
Computer Vision and Pattern Recognition, 2016 Salient object detection has recently witnessed substantial progress due to powerful features extracted using deep convolutional neural networks (CNNs). However, existing CNN-based methods operate at the patch level instead of the pixel level.
Guanbin Li, Yizhou Yu
openalex +3 more sources
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection [PDF]
IEEE International Conference on Computer Vision, 2017 Fully convolutional neural networks (FCNs) have shown outstanding performance in many dense labeling problems. One key pillar of these successes is mining relevant information from features in convolutional layers.
Pingping Zhang +4 more
openalex +3 more sources
Multi-Scale Global Contrast CNN for Salient Object Detection [PDF]
Sensors, 2020 Salient object detection (SOD) is a fundamental task in computer vision, which attempts to mimic human visual systems that rapidly respond to visual stimuli and locate visually salient objects in various scenes.
Weijia Feng +4 more
doaj +2 more sources
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection [PDF]
Computer Vision and Pattern Recognition, 2021 Visual salient object detection (SOD) aims at finding the salient object(s) that attract human attention, while camouflaged object detection (COD) on the contrary intends to discover the camouflaged object(s) that hidden in the surrounding. In this paper,
Aixuan Li +5 more
semanticscholar +1 more source
HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection [PDF]
IEEE transactions on circuits and systems for video technology (Print), 2023 The High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in which the input and output have the same resolution.
Bin Tang +3 more
semanticscholar +1 more source
Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment [PDF]
IEEE Transactions on Geoscience and Remote Sensing, 2023 Recently, relying on convolutional neural networks (CNNs), many methods for salient object detection in optical remote-sensing images (ORSI-SOD) are proposed.
Gongyang Li +3 more
semanticscholar +1 more source
Survey of Salient Object Detection Based on Deep Learning
Jisuanji kexue yu tansuo, 2021 With the development of deep learning, salient object detection based on deep learning has become a research hotspot in the computer vision field. Firstly, existing salient object detection methods based on deep learning are introduced from three aspects,
SHI Caijuan, ZHANG Weiming, CHEN Houru, GE Lulu
doaj +1 more source
Self-Improved Learning for Salient Object Detection
Applied Sciences, 2023 Salient Object Detection (SOD) aims at identifying the most visually distinctive objects in a scene. However, learning a mapping directly from a raw image to its corresponding saliency map is still challenging. First, the binary annotations of SOD impede
Songyuan Li +3 more
doaj +1 more source