facebookresearch / diht
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
☆137Updated 2 years ago
Alternatives and similar repositories for diht:
Users that are interested in diht are comparing it to the libraries listed below
- Toolkit for Elevater Benchmark☆70Updated last year
- Code for the paper titled "CiT Curation in Training for Effective Vision-Language Data".☆78Updated 2 years ago
- PyTorch code for MUST☆105Updated 2 years ago
- Code and Models for "GeneCIS A Benchmark for General Conditional Image Similarity"☆58Updated last year
- SVIT: Scaling up Visual Instruction Tuning☆163Updated 10 months ago
- [CVPR2023] The code for 《Position-guided Text Prompt for Vision-Language Pre-training》☆152Updated last year
- A task-agnostic vision-language architecture as a step towards General Purpose Vision☆92Updated 3 years ago
- Densely Captioned Images (DCI) dataset repository.☆177Updated 9 months ago
- Official repository for the General Robust Image Task (GRIT) Benchmark☆54Updated 2 years ago
- [ACL 2023] Official PyTorch code for Singularity model in "Revealing Single Frame Bias for Video-and-Language Learning"☆134Updated last year
- [BMVC22] Official Implementation of ViCHA: "Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment"☆55Updated 2 years ago
- A Unified Framework for Video-Language Understanding☆57Updated last year
- ☆64Updated last year
- PyTorch code for "VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks" (CVPR2022)☆205Updated 2 years ago
- ☆83Updated 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☆214Updated 2 years ago
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆164Updated last year
- ☆108Updated 2 years ago
- [ECCV2022] Contrastive Vision-Language Pre-training with Limited Resources☆44Updated 2 years ago
- ☆26Updated last year
- ☆58Updated last year
- Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone☆129Updated last year
- UniTAB: Unifying Text and Box Outputs for Grounded VL Modeling, ECCV 2022 (Oral Presentation)☆86Updated last year
- PyTorch implementation of the paper "MILAN: Masked Image Pretraining on Language Assisted Representation" https://arxiv.org/pdf/2208.0604…☆82Updated 2 years ago
- [NeurIPS2023] Official implementation and model release of the paper "What Makes Good Examples for Visual In-Context Learning?"☆173Updated last year
- Patching open-vocabulary models by interpolating weights☆91Updated last year
- 📍 Official pytorch implementation of paper "ProtoCLIP: Prototypical Contrastive Language Image Pretraining" (IEEE TNNLS)☆52Updated last year
- ☆50Updated 2 years ago
- Command-line tool for downloading and extending the RedCaps dataset.☆46Updated last year
- Visual Language Transformer Interpreter - An interactive visualization tool for interpreting vision-language transformers☆91Updated last year