facebookresearch / dihtLinks
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
Sorting:
- Code for the paper titled "CiT Curation in Training for Effective Vision-Language Data".☆78Updated 2 years ago
- Toolkit for Elevater Benchmark☆72Updated last year
- [CVPR2023] The code for 《Position-guided Text Prompt for Vision-Language Pre-training》☆152Updated 2 years ago
- A task-agnostic vision-language architecture as a step towards General Purpose Vision☆92Updated 3 years ago
- PyTorch code for MUST☆107Updated last month
- [ACL 2023] Official PyTorch code for Singularity model in "Revealing Single Frame Bias for Video-and-Language Learning"☆134Updated 2 years ago
- Code and Models for "GeneCIS A Benchmark for General Conditional Image Similarity"☆59Updated 2 years ago
- Official repository for the General Robust Image Task (GRIT) Benchmark☆54Updated 2 years ago
- A Unified Framework for Video-Language Understanding☆57Updated 2 years ago
- ☆83Updated 3 years ago
- UniTAB: Unifying Text and Box Outputs for Grounded VL Modeling, ECCV 2022 (Oral Presentation)☆87Updated 2 years ago
- Official implementation for the paper "Prompt Pre-Training with Over Twenty-Thousand Classes for Open-Vocabulary Visual Recognition"☆258Updated last year
- PyTorch code for "VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks" (CVPR2022)☆205Updated 2 years ago
- [BMVC22] Official Implementation of ViCHA: "Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment"☆55Updated 2 years ago
- [ECCV2022] Contrastive Vision-Language Pre-training with Limited Resources☆45Updated 2 years ago
- ☆108Updated 2 years ago
- [NeurIPS 2023] Text data, code and pre-trained models for paper "Improving CLIP Training with Language Rewrites"☆282Updated last year
- [ECCV2022] New benchmark for evaluating pre-trained model; New supervised contrastive learning framework.☆108Updated last year
- SVIT: Scaling up Visual Instruction Tuning☆163Updated last year
- PyTorch implementation of the paper "MILAN: Masked Image Pretraining on Language Assisted Representation" https://arxiv.org/pdf/2208.0604…☆83Updated 2 years ago
- ☆27Updated last year
- ☆59Updated last year
- Official code for "What Makes for Good Visual Tokenizers for Large Language Models?".☆58Updated last year
- Command-line tool for downloading and extending the RedCaps dataset.☆48Updated last year
- [SIGIR 2022] CenterCLIP: Token Clustering for Efficient Text-Video Retrieval. Also, a text-video retrieval toolbox based on CLIP + fast p…☆131Updated 3 years ago
- Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone☆129Updated last year
- Official repository of ICCV 2021 - Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models☆113Updated last month
- CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet☆218Updated 2 years ago
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆167Updated this week
- ☆30Updated last year