71 citations · 94 across the 6 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
cs.CV2022★ 8 cited
Masked Image Modeling with Denoising Contrast
Kun Yi, Yixiao Ge, Xiaotong Li +5
Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, tha…
cs.CV2022
mc-BEiT: Multi-choice Discretization for Image BERT Pre-training
Xiaotong Li, Yixiao Ge, Kun Yi +3
Image BERT pre-training with masked image modeling (MIM) becomes a popular practice to cope with self-supervised representation learning. A seminal work, BEiT, casts MIM as a class…
cs.CV2022★ 71 cited
Uncertainty Modeling for Out-of-Distribution Generalization
Xiaotong Li, Yongxing Dai, Yixiao Ge +3
Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios…