activity
20192022
most citedParametric Instance Classification for Unsupervised Visual Feature Learning

26 citations · 61 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CV20224 cited

Revealing the Dark Secrets of Masked Image Modeling

Zhenda Xie, Zigang Geng, Jingcheng Hu +3

Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM…

cs.CV20227 cited

iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition

Yixuan Wei, Yue Cao, Zheng Zhang +4

Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning thro…

cs.CV2021

Self-Supervised Learning with Swin Transformers

Zhenda Xie, Yutong Lin, Zhuliang Yao +4

We are witnessing a modeling shift from CNN to Transformers in computer vision. In this work, we present a self-supervised learning approach called MoBY, with Vision Transformers a…

cs.CV202024 cited

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

Zhenda Xie, Yutong Lin, Zheng Zhang +3

Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning…

cs.CV202026 cited

Parametric Instance Classification for Unsupervised Visual Feature Learning

Yue Cao, Zhenda Xie, Bin Liu +3

This paper presents parametric instance classification (PIC) for unsupervised visual feature learning. Unlike the state-of-the-art approaches which do instance discrimination in a…

cs.CV2020

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation

Zhenda Xie, Zheng Zhang, Xizhou Zhu +2

In the feature maps of CNNs, there commonly exists considerable spatial redundancy that leads to much repetitive processing. Towards reducing this superfluous computation, we propo…