F³Net: Fusion, Feedback and Focus for Salient Object Detection
Chinese Academy of Sciences · Institute of Computing Technology · +2 more institutions
Abstract
Most of existing salient object detection models have achieved great progress by aggregating multi-level features extracted from convolutional neural networks. However, because of the different receptive fields of different convolutional layers, there exists big differences between features generated by these layers. Common feature fusion strategies (addition or concatenation) ignore these differences and may cause suboptimal solutions. In this paper, we propose the F3Net to solve above problem, which mainly consists of cross feature module (CFM) and cascaded feedback decoder (CFD) trained by minimizing a new pixel position aware loss (PPA). Specifically, CFM aims to selectively aggregate multi-level features.…
Citation impact
- FWCI
- 43.60
- Percentile
- 100%
- References
- 54
Authors
3- JWJun WeiCorresponding
Chinese Academy of Sciences, Institute of Computing Technology, University of Chinese Academy of Sciences
- SWShuhui Wang
Chinese Academy of Sciences, Institute of Computing Technology
- QHQingming Huang
Chinese Academy of Sciences, Institute of Computing Technology, University of Chinese Academy of Sciences, University College of Applied Science
Topics & keywords
- Concatenation (mathematics)
- Computer science
- Focus (optics)
- Artificial intelligence
- Feature (linguistics)
- Pixel
- Convolutional neural network
- Benchmark (surveying)