facebookresearch / SWAG
Official repository for "Revisiting Weakly Supervised Pre-Training of Visual Perception Models". https://arxiv.org/abs/2201.08371.
☆178Updated 2 years ago
Alternatives and similar repositories for SWAG:
Users that are interested in SWAG are comparing it to the libraries listed below
- A PyTorch implementation of Mugs proposed by our paper "Mugs: A Multi-Granular Self-Supervised Learning Framework".☆83Updated last year
- PyTorch code for MUST☆106Updated last year
- ☆245Updated 2 years ago
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆78Updated 2 years ago
- Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training☆134Updated last year
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆159Updated last year
- Open-source code for Generic Grouping Network (GGN, CVPR 2022)☆109Updated 2 months ago
- code release of research paper "Exploring Long-Sequence Masked Autoencoders"☆99Updated 2 years ago
- Unofficial implementation of Pix2SEQ☆165Updated 3 years ago
- CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet☆211Updated 2 years ago
- Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, de…☆98Updated 2 years ago
- BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training☆396Updated 3 months ago
- EsViT: Efficient self-supervised Vision Transformers☆411Updated last year
- understanding model mistakes with human annotations☆106Updated last year
- [NeurIPS 2021] ORL: Unsupervised Object-Level Representation Learning from Scene Images☆58Updated 3 years ago
- Official PyTorch implementation of A-ViT: Adaptive Tokens for Efficient Vision Transformer (CVPR 2022)☆152Updated 2 years ago
- A compilation of network architectures for vision and others without usage of self-attention mechanism☆77Updated 2 years ago
- Official PyTorch implementation of the paper: "Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results" (2022)☆191Updated 2 years ago
- [ECCV2022] New benchmark for evaluating pre-trained model; New supervised contrastive learning framework.☆107Updated last year
- [CVPR 2023] Learning Visual Representations via Language-Guided Sampling☆146Updated last year
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆127Updated 2 years ago
- Code for the paper titled "CiT Curation in Training for Effective Vision-Language Data".☆78Updated 2 years ago
- A task-agnostic vision-language architecture as a step towards General Purpose Vision☆92Updated 3 years ago
- Code and models for the paper "The effectiveness of MAE pre-pretraining for billion-scale pretraining" https://arxiv.org/abs/2303.13496☆86Updated 6 months ago
- PyTorch Implementation of Region Similarity Representation Learning (ReSim)☆89Updated 3 years ago
- Bamboo: 4 times larger than ImageNet; 2 time larger than Object365; Built by active learning.☆173Updated 10 months ago
- [ICCV 2023] You Only Look at One Partial Sequence☆340Updated last year
- TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers (ECCV 2022)☆93Updated 2 years ago
- [ICLR 2022] "As-ViT: Auto-scaling Vision Transformers without Training" by Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wa…☆76Updated 3 years ago
- This is a offical PyTorch/GPU implementation of SupMAE.☆77Updated 2 years ago