H
Hongyu Wang
Researcher at Dalian University of Technology
Publications - 39
Citations - 2810
Hongyu Wang is an academic researcher from Dalian University of Technology. The author has contributed to research in topics: Feature extraction & Deep learning. The author has an hindex of 15, co-authored 37 publications receiving 2219 citations.
Papers
More filters
Proceedings ArticleDOI
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
TL;DR: Amulet is presented, a generic aggregating multi-level convolutional feature framework for salient object detection that provides accurate salient object labeling and performs favorably against state-of-the-art approaches in terms of near all compared evaluation metrics.
Proceedings ArticleDOI
Learning Uncertain Convolutional Features for Accurate Saliency Detection
TL;DR: A novel deep fully convolutional network model for accurate salient object detection and an effective hybrid upsampling method to reduce the checkerboard artifacts of deconvolution operators in the authors' decoder network are proposed.
Posted Content
Learning Uncertain Convolutional Features for Accurate Saliency Detection
TL;DR: Zhang et al. as discussed by the authors proposed a deep fully convolutional network model for accurate salient object detection, which is able to incorporate uncertainties for more accurate object boundary inference by introducing a reformulated dropout (R-dropout).
Journal ArticleDOI
High-Resolution SAR Image Classification via Deep Convolutional Autoencoders
TL;DR: The experiments of TerraSAR-X image demonstrate that the DCAE network can extract efficient features and perform better classification result compared with some related algorithms.
Journal ArticleDOI
Spectral–Spatial Classification of Hyperspectral Image Based on Deep Auto-Encoder
Xiaorui Ma,Hongyu Wang,Jie Geng +2 more
TL;DR: Using collaborative representation-based classification with deep features makes the proposed classifier extremely robust under a small training set, and the proposed method provides encouraging results compared with some related techniques.