🌟 Single Foundation Model Supports A Wide Range of Applications

As a foundation model, Meta-Transformer can handle data from 12 modalities, which determines that it can support a wide range of applications. As shown in this figure, Meta-Transformer can provide services for downstream tasks including stock analysis 📈, weather forecasting ☀️ ☔ ☁️ ❄️ ⛄ ⚡, remote sensing 📡, autonomous driving 🚗, social network 🌍, speech recognition 🔉, etc.

Table 1: Meta-Transformer is capable of handling up to 12 modalities, including natural language , RGB images , point clouds , audios , videos , tabular data , graph , time series data , hyper-spectral images , IMU , medical images , and infrared images .

🚩🚩🚩 Shared-Encoder, Unpaired Data, More Modalities

This repository is built to explore the potential and extensibility of transformers for multimodal learning. We utilize the advantages of Transformers to deal with length-variant sequences. Then we propose the Data-to-Sequence tokenization following a meta-scheme, then we apply it to 12 modalities including text, image, point cloud, audio, video, infrared, hyper-spectral, X-Ray, tabular, graph, time-series, and Inertial Measurement Unit (IMU) data.

After obtaining the token sequence, we employ a modality-shared encoder to extract representation across different modalities. With task-specific heads, Meta-Transformer can handle various tasks on the different modalities, such as: classification, detection, and segmentation.

🌟 News

• 2023.7.25: 🎉🎉🎉 We have released a well-documented code for graph data understanding. The implementation for Tabular data and point cloud will be released very soon.
• 2023.7.23: We have released the code and pretrained weights for image understanding and time-series forcasting.
• 2023.7.22: 🌟🌟🌟 Pretrained weights and a usage demo for our Meta-Transformer have been released. Comprehensive documentation and implementation of the image modality are underway and will be released soon. Stay tuned for more exciting updates!⌛⌛⌛
• 2023.7.21: Paper is released at arxiv, and code will be gradually released.
• 2023.7.8: Github Repository Initialization.

🔓 Model Zoo

from timm.models.vision_transformer import Block
ckpt = torch.load("Meta-Transformer_base_patch16_encoder.pth")
encoder = nn.Sequential(*[
            Block(
                dim=768,
                num_heads=12,
                mlp_ratio=4.,
                qkv_bias=True,
                norm_layer=nn.LayerNorm,
                act_layer=nn.GELU
            )
            for i in range(12)])
encoder.load_state_dict(ckpt,strict=True)

🕙 ToDo

• Meta-Transformer with Large Language Models.
• Multimodal Joint Training with Meta-Transformer.
• Support More Modalities and More Tasks.

Contact

🚀🚀🚀 We aspire to shape this repository into a formidable foundation for mainstream AI perception tasks across diverse modalities. Your contributions can play a significant role in this endeavor, and we warmly welcome your participation in our project!

To contact us, never hestitate to send an email to yiyuanzhang.ai@gmail.com ,kaixionggong@gmail.com, zhangkaipeng@pjlab.org.cn, or xyyue@ie.cuhk.edu.hk!

Citation

If the code and paper help your research, please kindly cite:

@article{zhang2023metatransformer,
        title={Meta-Transformer: A Unified Framework for Multimodal Learning}, 
        author={Zhang, Yiyuan and Gong, Kaixiong and Zhang, Kaipeng and Li, Hongsheng and Qiao, Yu and Ouyang, Wanli and Yue, Xiangyu},
        year={2023},
        journal={arXiv preprint arXiv:2307.10802},
  }

License

This project is released under the Apache 2.0 license.

Acknowledgement

This code is developed based on excellent open-sourced projects including MMClassification, MMDetection, MMsegmentation, OpenPoints, Time-Series-Library, Graphomer, SpectralFormer, and ViT-Adapter.