zhirongw/lemniscate.pytorch
PyTorch implementation of a self-supervised learning method for unsupervised feature learning on images via non-parametric instance discrimination.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of an unsupervised learning method that discriminates between individual image instances without labels. The approach uses Noise Contrastive Estimation (NCE) loss and a memory bank mechanism to learn compact 128-dimensional feature representations from ImageNet. It supports nearest neighbor classification on learned features and provides pretrained ResNet models.
Frequently asked
- What is zhirongw/lemniscate.pytorch?
- PyTorch implementation of a self-supervised learning method for unsupervised feature learning on images via non-parametric instance discrimination.
- Is lemniscate.pytorch open source?
- Yes — zhirongw/lemniscate.pytorch is an open-source project tracked on heatdrop.
- What language is lemniscate.pytorch written in?
- zhirongw/lemniscate.pytorch is primarily written in Python.
- How popular is lemniscate.pytorch?
- zhirongw/lemniscate.pytorch has 759 stars on GitHub.
- Where can I find lemniscate.pytorch?
- zhirongw/lemniscate.pytorch is on GitHub at https://github.com/zhirongw/lemniscate.pytorch.