sayakpaul / probing-vits
Probing the representations of Vision Transformers.
☆316Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for probing-vits
- Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.☆318Updated last year
- ☆177Updated last year
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆203Updated last year
- Masked Siamese Networks for Label-Efficient Learning (https://arxiv.org/abs/2204.07141)☆449Updated 2 years ago
- Code to reproduce the results in the FAIR research papers "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting V…☆487Updated last year
- EsViT: Efficient self-supervised Vision Transformers☆408Updated last year
- VICRegL official code base☆224Updated last year
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆128Updated last year
- Pytorch implementation of LOST unsupervised object discovery method☆236Updated last year
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆247Updated 2 years ago
- Code release for "Dropout Reduces Underfitting"☆312Updated last year
- MultiMAE: Multi-modal Multi-task Masked Autoencoders, ECCV 2022☆548Updated last year
- A library to inspect and extract intermediate layers of PyTorch models.☆470Updated 2 years ago
- A modular PyTorch library for vision transformer models☆163Updated last year
- Self-Supervised Learning in PyTorch☆127Updated 7 months ago
- Compare neural networks by their feature similarity☆342Updated last year
- Code release for SLIP Self-supervision meets Language-Image Pre-training☆746Updated last year
- [ICML 2023] Official PyTorch implementation of Global Context Vision Transformers☆425Updated 10 months ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆336Updated 2 months ago
- ☆216Updated 3 years ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆511Updated 2 weeks ago
- Lucid library adapted for PyTorch☆608Updated 5 months ago
- A Pytorch-Lightning implementation of self-supervised algorithms☆535Updated 2 years ago
- ☆193Updated last year
- PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning☆130Updated 4 months ago
- This repository contains an overview of important follow-up works based on the original Vision Transformer (ViT) by Google.☆145Updated 2 years ago
- (ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"☆806Updated 2 years ago
- [ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmen…☆444Updated last year
- An alternative to convolution in neural networks☆250Updated 7 months ago
- [CVPR 2022] Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization☆229Updated last year