W
Wei Shen
Researcher at Shanghai Jiao Tong University
Publications - 135
Citations - 6771
Wei Shen is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Segmentation & Convolutional neural network. The author has an hindex of 35, co-authored 127 publications receiving 4954 citations. Previous affiliations of Wei Shen include Shanghai University & Huazhong University of Science and Technology.
Papers
More filters
Proceedings ArticleDOI
Few-Shot Image Recognition by Predicting Parameters from Activations
TL;DR: A novel method that can adapt a pre-trained neural network to novel categories by directly predicting the parameters from the activations is proposed, which achieves the state-of-the-art classification accuracy on Novel categories by a significant margin while keeping comparable performance on the large-scale categories.
Proceedings ArticleDOI
DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection
TL;DR: This work shows that contour detection accuracy can be improved by instead making the use of the deep features learned from convolutional neural networks (CNNs), while rather than using the networks as a blackbox feature extractor, it customize the training strategy by partitioning contour (positive) data into subclasses and fitting each subclass by different model parameters.
Proceedings ArticleDOI
Multi-oriented Text Detection with Fully Convolutional Networks
TL;DR: A novel approach for text detection in natural images that consistently achieves the state-of-the-art performance on three text detection benchmarks: MSRA-TD500, I CDAR2015 and ICDAR2013.
Posted Content
Multi-Oriented Text Detection with Fully Convolutional Networks
TL;DR: In this article, a Fully Convolutional Network (FCN) model is trained to predict the salient map of text regions in a holistic manner, and text line hypotheses are estimated by combining the saliency map and character components.
Book ChapterDOI
Deep Co-Training for Semi-Supervised Image Recognition
TL;DR: Deep Co-training as discussed by the authors exploits adversarial examples to encourage view difference, in order to prevent the networks from collapsing into each other and provide complementary information about the data, which is necessary for the co-training framework to achieve good results.