Momentum Contrast for Unsupervised Visual Representation Learning
We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic diction...
Publications
3 shownA ConvNet for the 2020s
The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification...
Aggregated Residual Transformations for Deep Neural Networks
We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transfor...
Frequent Co-Authors
Researcher Info
- h-index
- 3
- Publications
- 3
- Citations
- 28,148
- Institution
- Meta (Israel)
External Links
Impact Metrics
h-index
3
h-index: Number of publications with at least h citations each.