227 citations · 418 across the 20 of their papers we have counts for
5 papers · 1 filter
Open Compound Domain Adaptation
Ziwei Liu, Zhongqi Miao, Xingang Pan +4
A typical domain adaptation approach is to adapt models trained on the annotated data in a source domain (e.g., sunny weather) for achieving high performance on the test data in a…
Learning to Cluster Faces on an Affinity Graph
Lei Yang, Xiaohang Zhan, Dapeng Chen +3
Face recognition sees remarkable progress in recent years, and its performance has reached a very high level. Taking it to a next level requires substantially larger data, which wo…
Self-Supervised Learning via Conditional Motion Propagation
Xiaohang Zhan, Xingang Pan, Ziwei Liu +2
Intelligent agent naturally learns from motion. Various self-supervised algorithms have leveraged motion cues to learn effective visual representations. The hurdle here is that mot…
Large-Scale Long-Tailed Recognition in an Open World
Ziwei Liu, Zhongqi Miao, Xiaohang Zhan +3
Real world data often have a long-tailed and open-ended distribution. A practical recognition system must classify among majority and minority classes, generalize from a few known…
Switchable Whitening for Deep Representation Learning
Xingang Pan, Xiaohang Zhan, Jianping Shi +2
Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixe…