google-research-datasets / conceptual-12mLinks
Conceptual 12M is a dataset containing (image-URL, caption) pairs collected for vision-and-language pre-training.
☆409Updated 4 months ago
Alternatives and similar repositories for conceptual-12m
Users that are interested in conceptual-12m are comparing it to the libraries listed below
Sorting:
- Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm☆669Updated 3 years ago
- Code release for SLIP Self-supervision meets Language-Image Pre-training☆784Updated 2 years ago
- Implementation of Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic☆280Updated 3 years ago
- A concise but complete implementation of CLIP with various experimental improvements from recent papers☆719Updated 2 years ago
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆320Updated last year
- Get hundred of million of image+url from the crawling at home dataset and preprocess them☆223Updated last year
- 🧀 Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".☆484Updated 2 years ago
- [CVPR 2022] Official code for "Unified Contrastive Learning in Image-Text-Label Space"☆403Updated 2 years ago
- Reliably download millions of images efficiently☆118Updated 4 years ago
- CLIP-like model evaluation☆792Updated this week
- Language Models Can See: Plugging Visual Controls in Text Generation☆259Updated 3 years ago
- DataComp: In search of the next generation of multimodal datasets☆752Updated 7 months ago
- ☆230Updated last year
- Generate text captions for images from their embeddings.☆116Updated 2 years ago
- CLIPScore EMNLP code☆241Updated 2 years ago
- Multi-modality pre-training☆505Updated last year
- A PyTorch Lightning solution to training OpenAI's CLIP from scratch.☆717Updated 3 years ago
- GIT: A Generative Image-to-text Transformer for Vision and Language☆578Updated 2 years ago
- An ever-growing playground of notebooks showcasing CLIP's impressive zero-shot capabilities☆175Updated 3 years ago
- [ICLR 2022] code for "How Much Can CLIP Benefit Vision-and-Language Tasks?" https://arxiv.org/abs/2107.06383☆419Updated 3 years ago
- Conceptual Captions is a dataset containing (image-URL, caption) pairs designed for the training and evaluation of machine learned image …☆556Updated 4 years ago
- Large-scale text-video dataset. 10 million captioned short videos.☆665Updated last year
- Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]☆378Updated 3 years ago
- PyTorch code for MUST☆107Updated 7 months ago
- MERLOT: Multimodal Neural Script Knowledge Models☆225Updated 3 years ago
- Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)☆183Updated 5 months ago
- Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training☆138Updated 2 years ago
- DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models (ICCV 2023)☆143Updated 5 months ago
- ☆96Updated last week
- PyTorch code for "Fine-grained Image Captioning with CLIP Reward" (Findings of NAACL 2022)☆246Updated 5 months ago