facebookresearch / ssl-data-curation
PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning
☆141Updated 6 months ago
Alternatives and similar repositories for ssl-data-curation:
Users that are interested in ssl-data-curation are comparing it to the libraries listed below
- ☆198Updated last year
- When do we not need larger vision models?☆355Updated last month
- ☆62Updated 3 months ago
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆306Updated 7 months ago
- Learning from synthetic data - code and models☆307Updated last year
- Code release for "Improved baselines for vision-language pre-training"☆58Updated 8 months ago
- Official code for "TOAST: Transfer Learning via Attention Steering"☆186Updated last year
- The official repo for the paper "VeCLIP: Improving CLIP Training via Visual-enriched Captions"☆238Updated 4 months ago
- Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.☆155Updated 9 months ago
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆158Updated last year
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆436Updated 6 months ago
- Python Library to evaluate VLM models' robustness across diverse benchmarks☆181Updated 3 weeks ago
- VLM Evaluation: Benchmark for VLMs, spanning text generation tasks from VQA to Captioning☆97Updated 4 months ago
- [CVPR 2023] Learning Visual Representations via Language-Guided Sampling☆146Updated last year
- Object Recognition as Next Token Prediction (CVPR 2024 Highlight)☆169Updated 3 weeks ago
- Code for experiments for "ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy"☆100Updated 4 months ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆256Updated 8 months ago
- The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A su…☆218Updated this week
- Patching open-vocabulary models by interpolating weights☆91Updated last year
- Supercharge Your PyTorch Image Models: Bag of Tricks to 8x Faster Inference with ONNX Runtime & Optimizations☆22Updated 3 months ago
- (ICLR 2023) Official PyTorch implementation of "What Do Self-Supervised Vision Transformers Learn?"☆105Updated 10 months ago
- ☆479Updated 2 months ago
- Densely Captioned Images (DCI) dataset repository.☆167Updated 6 months ago
- Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.☆179Updated last year
- Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training☆133Updated last year
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆202Updated last year
- A framework for merging models solving different tasks with different initializations into one multi-task model without any additional tr…☆291Updated last year
- Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR …☆263Updated last year
- Code and models for the paper "The effectiveness of MAE pre-pretraining for billion-scale pretraining" https://arxiv.org/abs/2303.13496☆81Updated 5 months ago
- Sparse Linear Concept Embeddings☆80Updated 5 months ago