Z
Zhi-Hua Zhou
Researcher at Nanjing University
Publications - 633
Citations - 64307
Zhi-Hua Zhou is an academic researcher from Nanjing University. The author has contributed to research in topics: Semi-supervised learning & Artificial neural network. The author has an hindex of 102, co-authored 626 publications receiving 52850 citations. Previous affiliations of Zhi-Hua Zhou include Michigan State University & Tokyo Institute of Technology.
Papers
More filters
Posted Content
Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming
TL;DR: Zhang et al. as mentioned in this paper proposed Deep Descriptor Transforming (DDT) for evaluating the correlations of descriptors and obtaining the category-consistent regions, which can accurately locate the common object in a set of unlabeled images, i.e., unsupervised object discovery.
Proceedings Article
Boosting-Based Reliable Model Reuse
Yao-Xiang Ding,Zhi-Hua Zhou +1 more
TL;DR: This work proposes MoreBoost, a simple yet powerful boosting algorithm to achieve effective model reuse under the idealized assumption that the reusability indicators are noise-free, and strengthens MoreBoost with an active rectification mechanism, allowing the learner to query ground-truth indicator values from the model providers actively.
Book ChapterDOI
Spiculated lesion detection in digital mammogram based on artificial neural network ensemble
TL;DR: A feature extraction method is applied to generate four feature images for a single mammogram, and then every feature image is partitioned into a series of small square blocks to detect spiculated lesions.
Posted Content
One-Pass Learning with Incremental and Decremental Features
Chenping Hou,Zhi-Hua Zhou +1 more
TL;DR: In this article, the OPID approach attempts to compress important information of vanished features into functions of survived features, and then expand to include the augmented features, which only needs to scan each instance once and does not need to store the whole data, and thus satisfy the evolving streaming data nature.
Posted Content
Isolation Distributional Kernel: A New Tool for Point & Group Anomaly Detection
TL;DR: This paper shows for the first time that an effective kernel based anomaly detector based on kernel mean embedding must employ a characteristic kernel which is data dependent, and introduces an IDK based detector called IDK$^2, which runs orders of magnitude faster than group anomaly detector OCSMM.