Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction. In CVPR, 2017.
The main features of richzhang/splitbrainauto are: Image Representation Learning.
Open-source alternatives to richzhang/splitbrainauto include: facebookresearch/deepcluster — We release paper and code for SwAV, our new self-supervised method. SwAV pushes self-supervised learning to only 1.2%… facebookresearch/noise-as-targets — Unsupervised Learning by Predicting Noise. gidariss/featurelearningrotnet. google/revisiting-self-supervised. hsinyinglee/opn. dongli12/featurelearning — FeatureLearning-ECCV2016.
We release paper and code for SwAV, our new self-supervised method. SwAV pushes self-supervised learning to only 1.2% away from supervised learning on ImageNet with a ResNet-50! It combines online clustering with a multi-crop data augmentation.
Unsupervised Learning by Predicting Noise
