google-research/maxvit
Multi-axis vision transformer model for image classification, detection, and segmentation tasks.
Not currently ranked — collecting fresh signals.
star history
This is the official TensorFlow implementation of MaxViT, a multi-axis vision transformer published at ECCV 2022. It provides state-of-the-art foundation models for image classification, object detection, semantic segmentation, image quality assessment, and generative modeling tasks. The architecture combines dilated local attention with grid attention across both spatial axes.
Frequently asked
- What is google-research/maxvit?
- Multi-axis vision transformer model for image classification, detection, and segmentation tasks.
- Is maxvit open source?
- Yes — google-research/maxvit is open source, released under the Apache-2.0 license.
- What language is maxvit written in?
- google-research/maxvit is primarily written in Jupyter Notebook.
- How popular is maxvit?
- google-research/maxvit has 501 stars on GitHub.
- Where can I find maxvit?
- google-research/maxvit is on GitHub at https://github.com/google-research/maxvit.