yukimasano / PASS
The PASS dataset: pretrained models and how to get the data
☆262Updated 2 years ago
Related projects: ⓘ
- Labels and other data for the paper "Are we done with ImageNet?"☆181Updated 2 years ago
- Code to reproduce the results in the FAIR research papers "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting V…☆486Updated last year
- VICRegL official code base☆223Updated last year
- Official repository for "Revisiting Weakly Supervised Pre-Training of Visual Perception Models". https://arxiv.org/abs/2201.08371.☆171Updated 2 years ago
- Pytorch implementation of LOST unsupervised object discovery method☆234Updated last year
- Pre-trained NFNets with 99% of the accuracy of the official paper "High-Performance Large-Scale Image Recognition Without Normalization".☆159Updated 3 years ago
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆199Updated last year
- understanding model mistakes with human annotations☆104Updated last year
- Probing the representations of Vision Transformers.☆311Updated last year
- A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude.☆135Updated 2 years ago
- Official code Cross-Covariance Image Transformer (XCiT)☆654Updated 2 years ago
- The correct way to resize images or tensors. For Numpy or Pytorch (differentiable).☆543Updated last year
- TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.☆87Updated 2 years ago
- ☆175Updated 11 months ago
- Official PyTorch implementation of the paper: "Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results" (2022)☆191Updated last year
- Code release for "Dropout Reduces Underfitting"☆311Updated last year
- Is the attention layer even necessary? (https://arxiv.org/abs/2105.02723)☆480Updated 3 years ago
- EsViT: Efficient self-supervised Vision Transformers☆407Updated last year
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆124Updated last year
- Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.☆318Updated last year
- Repository providing a wide range of self-supervised pretrained models for computer vision tasks.☆61Updated 3 years ago
- Pytorch augmentation☆118Updated 9 months ago
- Official implementation of "Active Image Indexing"☆58Updated last year
- Train ImageNet *fast* in 500 lines of code with FFCV☆135Updated 4 months ago
- Optimized library for large-scale extraction of frames and audio from video.☆202Updated last year
- Dense Unsupervised Learning for Video Segmentation (NeurIPS*2021)☆182Updated 2 years ago
- Code release for SLIP Self-supervision meets Language-Image Pre-training☆743Updated last year
- An alternative to convolution in neural networks☆248Updated 5 months ago
- A toolbox for receptive field analysis and visualizing neural network architectures☆113Updated last month
- ☆395Updated last year