X
Xiaohang Zhan
Researcher at The Chinese University of Hong Kong
Publications - 37
Citations - 2223
Xiaohang Zhan is an academic researcher from The Chinese University of Hong Kong. The author has contributed to research in topics: Feature learning & Computer science. The author has an hindex of 15, co-authored 32 publications receiving 937 citations. Previous affiliations of Xiaohang Zhan include University of California, Berkeley & SenseTime.
Papers
More filters
Proceedings ArticleDOI
Large-Scale Long-Tailed Recognition in an Open World
TL;DR: An integrated OLTR algorithm is developed that maps an image to a feature space such that visual concepts can easily relate to each other based on a learned metric that respects the closed-world classification while acknowledging the novelty of the open world.
Posted Content
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
TL;DR: This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images by allowing the generator to be fine-tuned on-the-fly in a progressive manner regularized by feature distance obtained by the discriminator in GAN.
Posted Content
Large-Scale Long-Tailed Recognition in an Open World
TL;DR: Open Long-Tailed Recognition (OLTR) as mentioned in this paper maps an image to a feature space such that visual concepts can easily relate to each other based on a learned metric that respects the closed-world classification while acknowledging the novelty of the open world.
Proceedings ArticleDOI
Learning to Cluster Faces on an Affinity Graph
TL;DR: This work explores a novel approach, namely, learning to cluster instead of relying on hand-crafted criteria, and proposes a framework based on graph convolutional network, which combines a detection and a segmentation module to pinpoint face clusters.
Proceedings ArticleDOI
Online Deep Clustering for Unsupervised Representation Learning
TL;DR: Online deep clustering (ODC) as mentioned in this paper performs clustering and network update simultaneously rather than alternatingly, where the cluster centroids should evolve steadily in keeping the classifier stably updated.