ArthurZucker / RecvisProject
In this project, we propose to study Vision Transformers trained using the Barlow Twins self-supervised method, and compare the results with DINO. We demonstrate the effectiveness of the Barlow Twins method by showing that networks pretrained on the small PASCAL VOC 2012 dataset are able to generalize well. Authors: Apavou Clément & Zucker Arthu…
☆15Updated last year
Alternatives and similar repositories for RecvisProject:
Users that are interested in RecvisProject are comparing it to the libraries listed below
- Visualizing representations with diffusion based conditional generative model.☆94Updated last year
- ☆50Updated 10 months ago
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"☆50Updated 11 months ago
- Code release for "Improved baselines for vision-language pre-training"☆60Updated 11 months ago
- JAX implementation ViT-VQGAN☆82Updated 2 years ago
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆127Updated 2 years ago
- Natural Language Descriptions of Deep Visual Features, ICLR 2022☆63Updated last year
- understanding model mistakes with human annotations☆106Updated 2 years ago
- ☆65Updated 6 months ago
- Implementation of Discrete Key / Value Bottleneck, in Pytorch☆87Updated last year
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆207Updated last year
- Implementation of Zorro, Masked Multimodal Transformer, in Pytorch☆97Updated last year
- Official PyTorch Implementation of "Rosetta Neurons: Mining the Common Units in a Model Zoo"☆30Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).☆218Updated this week
- This is a offical PyTorch/GPU implementation of SupMAE.☆78Updated 2 years ago
- Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detection☆52Updated 7 months ago
- Code for the paper "Hyperbolic Image-Text Representations", Desai et al, ICML 2023☆159Updated last year
- A compilation of network architectures for vision and others without usage of self-attention mechanism☆79Updated 2 years ago
- Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI☆87Updated 3 years ago
- ☆22Updated 3 months ago
- ☆31Updated 3 months ago
- ☆51Updated 10 months ago
- Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"☆98Updated 2 weeks ago
- [NeurIPS 2024] Code for the paper: B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable.☆30Updated last month
- WIP☆93Updated 8 months ago
- Official code and data for NeurIPS 2023 paper "ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial …☆38Updated last year
- Memory-Efficient CUDA kernels for training ConvNets with PyTorch.☆40Updated 2 months ago
- Implementation of MaMMUT, a simple vision-encoder text-decoder architecture for multimodal tasks from Google, in Pytorch☆100Updated last year
- Official code for "TOAST: Transfer Learning via Attention Steering"☆189Updated last year
- Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in P…☆203Updated last year