D
Dong Wang
Researcher at Peking University
Publications - 16
Citations - 648
Dong Wang is an academic researcher from Peking University. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 5, co-authored 10 publications receiving 364 citations.
Papers
More filters
Book ChapterDOI
Learning to Navigate for Fine-grained Classification
TL;DR: In this paper, a self-supervision mechanism is proposed to locate informative regions without the need of bounding-box/part annotations, which consists of a navigator agent, a teacher agent and a scrutinizer agent.
Proceedings ArticleDOI
FocalMix: Semi-Supervised Learning for 3D Medical Image Detection
TL;DR: FocalMix as mentioned in this paper leverages recent advances in semi-supervised learning (SSL) for 3D medical image detection, which can achieve a substantial improvement of up to 17.3% over state-of-the-art supervised learning approaches with 400 unlabeled CT scans.
Posted Content
FocalMix: Semi-Supervised Learning for 3D Medical Image Detection
TL;DR: A novel method is proposed, called FocalMix, which is the first to leverage recent advances in semi-supervised learning (SSL) for 3D medical image detection, and can achieve a substantial improvement over state-of-the-art supervised learning approaches with 400 unlabeled CT scans.
Proceedings ArticleDOI
Neural IR Meets Graph Embedding: A Ranking Model for Product Search
Yuan Zhang,Dong Wang,Yan Zhang +2 more
TL;DR: The recent advances in graph embedding techniques are leveraged to enable neural retrieval models to exploit graph-structured data for automatic feature extraction to overcome the long-tail problem of click-through data and incorporate external heterogeneous information to improve search results.
Posted Content
Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems
TL;DR: A novel Gram-Gauss-Newton (GGN) algorithm to train deep neural networks for regression problems with square loss and provides convergence guarantee for mini-batch GGN algorithm, which is, to the authors' knowledge, the first convergence result for themini-batch version of a second-order method on overparameterized neural networks.