facebookresearch / data2vec_vision
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
☆78Updated 2 years ago
Related projects: ⓘ
- Visual Language Transformer Interpreter - An interactive visualization tool for interpreting vision-language transformers☆85Updated last year
- Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training☆130Updated last year
- Patching open-vocabulary models by interpolating weights☆88Updated 11 months ago
- code release of research paper "Exploring Long-Sequence Masked Autoencoders"☆99Updated last year
- This is a offical PyTorch/GPU implementation of SupMAE.☆76Updated 2 years ago
- PyTorch code for MUST☆105Updated last year
- ☆32Updated 2 years ago
- Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, de…☆96Updated 2 years ago
- This code provides a PyTorch implementation for OTTER (Optimal Transport distillation for Efficient zero-shot Recognition), as described …☆64Updated 2 years ago
- Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch☆116Updated 3 years ago
- A PyTorch implementation of Mugs proposed by our paper "Mugs: A Multi-Granular Self-Supervised Learning Framework".☆82Updated 7 months ago
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆124Updated last year
- A compilation of network architectures for vision and others without usage of self-attention mechanism☆77Updated last year
- Implementation of Online Label Smoothing in PyTorch☆94Updated last year
- ☆111Updated last year
- PyTorch code for "Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention" (WACV 2023)☆32Updated last year
- [ECCV2024][ICCV2023] Official PyTorch implementation of SeiT++ and SeiT☆51Updated last month
- A task-agnostic vision-language architecture as a step towards General Purpose Vision☆92Updated 3 years ago
- Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI☆74Updated 2 years ago
- Official repository for "Revisiting Weakly Supervised Pre-Training of Visual Perception Models". https://arxiv.org/abs/2201.08371.☆171Updated 2 years ago
- MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)☆105Updated 2 years ago
- [BMVC22] Official Implementation of ViCHA: "Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment"☆52Updated last year
- https://arxiv.org/abs/2209.15162☆48Updated last year
- Command-line tool for downloading and extending the RedCaps dataset.☆45Updated 9 months ago
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆149Updated 9 months ago
- understanding model mistakes with human annotations☆104Updated last year
- Code for the paper titled "CiT Curation in Training for Effective Vision-Language Data".☆78Updated last year
- ECCV2022,Bootstrapped Masked Autoencoders for Vision BERT Pretraining☆98Updated last year
- Implementation of Cross Transformer for spatially-aware few-shot transfer, in Pytorch☆50Updated 3 years ago
- PyTorch implementation of Asymmetric Siamese (https://arxiv.org/abs/2204.00613)☆100Updated 2 years ago