.png){kind=icon}
.png){kind=icon}
Return
Salient object detection via light-weight multi-path cascaded networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2020.06.123.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently, deep learning-based saliency detection has achieved fantastic performance over conventional works. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. It is difficult for a network to learn saliency at the boundaries of salient regions. In this paper, a Light-Weight Multi-Path Cascaded Network (LMCN) is proposed for image saliency detection-an encoder-decoder architecture that explicitly exploits all the information available along the down-sampling process to enable full-resolution prediction using long-range residual connections. The Res2Net is adopted as a backbone network to better extract multi-level and multi-scale feature maps by constructing hierarchical residual-like connections within one single residual block. Also, the network is lightweighted by the bottleneck structure and depth-wise convolution, which ultimately reduces the number of parameters by more than 50% while maintaining the same performance. Comprehensive experiments are carried out and new state-of-the-art results are set in eight public datasets. Experiment results show that the proposed approach substantially improves previous state-of-the-art performances. (c) 2020 Elsevier B.V. All rights reserved.
Keywords:
Saliency detection
Light-weight
Res2Net
Multi-level
Multi-scale
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.