Jianfeng Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jianfeng Liu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Chen Pan
China Jiliang University
1 shared publication Feilong Cao
College of Sciences, China Jiliang University, Hangzhou, China
1 shared publicationWei He
College of Information Engineering, China Jiliang University, Hangzhou, China
1 shared publication- Wei Qi Yan
Auckland University of Technology, Auckland, New Zealand
1 shared publication Yongxia Zhou
College of Information Engineering, China Jiliang University, Hangzhou, China
1 shared publication
Latest Publications
- 30 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 4773-4787
Salient Object Detection Based on Visual Perceptual Saturation and Two-Stream Hybrid Networks
Inspired by the perceived saturation of human visual system, this paper proposes a two-stream hybrid networks to simulate binocular vision for salient object detection (SOD). Each stream in our system consists of unsupervised and supervised methods to form a two-branch module, so as to model the interaction between human intuition and memory. The two-branch module parallel processes visual information with bottom-up and top-down SODs, and output two initial saliency maps. Then a polyharmonic neural network with random-weight (PNNRW) is utilized to fuse two-branch’s perception and refine the salient objects by learning online via multi-source cues. Depend on visual perceptual saturation, we can select optimal parameter of superpixel for unsupervised branch, locate sampling regions for PNNRW, and construct a positive feedback loop to facilitate perception saturated after the perception fusion. By comparing the binary outputs of the two-stream, the pixel annotation of predicted object with high saturation degree could be taken as new training samples. The presented method constitutes a semi-supervised learning framework actually. Supervised branches only need to be pre-trained initial, the system can collect the training samples with high confidence level and then train new models by itself. Extensive experiments show that the new framework can improve performance of the existing SOD methods, that exceeds the state-of-the-art methods in six popular benchmarks.
- 30 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 4773-4787
Salient Object Detection Based on Visual Perceptual Saturation and Two-Stream Hybrid Networks
Inspired by the perceived saturation of human visual system, this paper proposes a two-stream hybrid networks to simulate binocular vision for salient object detection (SOD). Each stream in our system consists of unsupervised and supervised methods to form a two-branch module, so as to model the interaction between human intuition and memory. The two-branch module parallel processes visual information with bottom-up and top-down SODs, and output two initial saliency maps. Then a polyharmonic neural network with random-weight (PNNRW) is utilized to fuse two-branch’s perception and refine the salient objects by learning online via multi-source cues. Depend on visual perceptual saturation, we can select optimal parameter of superpixel for unsupervised branch, locate sampling regions for PNNRW, and construct a positive feedback loop to facilitate perception saturated after the perception fusion. By comparing the binary outputs of the two-stream, the pixel annotation of predicted object with high saturation degree could be taken as new training samples. The presented method constitutes a semi-supervised learning framework actually. Supervised branches only need to be pre-trained initial, the system can collect the training samples with high confidence level and then train new models by itself. Extensive experiments show that the new framework can improve performance of the existing SOD methods, that exceeds the state-of-the-art methods in six popular benchmarks.