google-research-datasets / witLinks
WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.
β1,058Updated 8 months ago
Alternatives and similar repositories for wit
Users that are interested in wit are comparing it to the libraries listed below
Sorting:
- Implementation of 𦩠Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorchβ1,244Updated 2 years ago
- OpenAI CLIP text encoders for multiple languages!β799Updated 2 years ago
- Code release for SLIP Self-supervision meets Language-Image Pre-trainingβ767Updated 2 years ago
- A concise but complete implementation of CLIP with various experimental improvements from recent papersβ711Updated last year
- Conceptual 12M is a dataset containing (image-URL, caption) pairs collected for vision-and-language pre-training.β391Updated 2 years ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorchβ866Updated last year
- A PyTorch Lightning solution to training OpenAI's CLIP from scratch.β694Updated 3 years ago
- Oscar and VinVLβ1,049Updated last year
- CLIP-like model evaluationβ721Updated 2 weeks ago
- PyTorch code for "Unifying Vision-and-Language Tasks via Text Generation" (ICML 2021)β371Updated last year
- Research code for pixel-based encoders of language (PIXEL)β335Updated last year
- [CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learningβ¦β721Updated last year
- Language Models Can See: Plugging Visual Controls in Text Generationβ256Updated 3 years ago
- [ICLR 2022] code for "How Much Can CLIP Benefit Vision-and-Language Tasks?" https://arxiv.org/abs/2107.06383β411Updated 2 years ago
- Conceptual Captions is a dataset containing (image-URL, caption) pairs designed for the training and evaluation of machine learned image β¦β541Updated 3 years ago
- Simple image captioning modelβ1,372Updated 11 months ago
- Robust fine-tuning of zero-shot modelsβ705Updated 3 years ago
- π§ Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".β482Updated last year
- TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.β1,604Updated last week
- DataComp: In search of the next generation of multimodal datasetsβ714Updated last month
- GIT: A Generative Image-to-text Transformer for Vision and Languageβ566Updated last year
- β1,008Updated 2 years ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathwaysβ823Updated 2 years ago
- Multi Task Vision and Languageβ812Updated 3 years ago
- Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"β793Updated 3 years ago
- Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Lβ¦β2,502Updated last year
- NL-Augmenter π¦ β π A Collaborative Repository of Natural Language Transformationsβ786Updated last year
- Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"β535Updated 2 years ago
- MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.β930Updated 2 months ago
- Vision-Language Pre-training for Image Captioning and Question Answeringβ419Updated 3 years ago