Off the convex path

Use Barlow Twins method for self supervised learning

Code associated to the publication: Scaling self-supervised learning for histopathology with masked image modeling, A. Filiot et al., MedRxiv (2023). We publicly release Phikon 🚀

A beautiful, simple, clean, and responsive Jekyll theme for academics

Simple implementation of OpenAI CLIP model in PyTorch.

Awesome list for research on CLIP (Contrastive Language-Image Pre-Training).

Repository accompanying the paper: Self-supervised Video Object Segmentation by Motion Grouping. C. Yang, H. Lamdouar, E. Lu, A. Zisserman, W. Xie.

Official code for the paper: MAR: Masked Autoencoders for Efficient Action Recognition

Contrastive Learning Representations for Images and Text Pairs. Colab implementation of ConVIRT for transfer learning with insufficient data volume.

🤖 🩻 Pytorch implementation of the ConVIRT Paper. Pioneer Image-Text Contrastive Learning approach for Radiology

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

[NeurIPS 2021] Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning

Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.

21st Place Solution - Representation Is All You Need

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

My solution to Web Traffic Predictions competition on Kaggle.

AI challenger 2018 TOP3 Solution

1st place solution

AI Challenger 2018 Weather Forecasting - 1st Place Solution

Spatial Transformer Networks in Pytorch.

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

Dual Attention Network for Scene Segmentation (CVPR2019)

Scene Segmentation with Dual Relation-aware Attention Network (TNNLS2020)

Pytorch implementent of the fast style transfer paper "Perceptual Losses for Real-Time Style Transfer and Super-Resolution".

Implementation of "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" in PyTorch

PyTorch implementation of "Perceptual Losses for Real-Time Style Transfer and Super-Resolution"

PASTA: Learning Parameter-specific Affine Transformation for Medical Images Registration

End-to-end weakly-supervised semantic alignment