speedinghzl/CCNet
PyTorch implementation of a semantic segmentation model using Criss-Cross Attention for capturing long-range dependencies in images.
Not currently ranked — collecting fresh signals.
star history
CCNet is a research implementation of a semantic segmentation architecture that uses a novel Criss-Cross Attention mechanism to model long-range contextual dependencies efficiently. The model is built on PyTorch and achieves state-of-the-art results on the Cityscapes dataset. This branch contains the pure Python implementation of the original work.
Frequently asked
- What is speedinghzl/CCNet?
- PyTorch implementation of a semantic segmentation model using Criss-Cross Attention for capturing long-range dependencies in images.
- Is CCNet open source?
- Yes — speedinghzl/CCNet is open source, released under the MIT license.
- What language is CCNet written in?
- speedinghzl/CCNet is primarily written in Python.
- How popular is CCNet?
- speedinghzl/CCNet has 1.5k stars on GitHub.
- Where can I find CCNet?
- speedinghzl/CCNet is on GitHub at https://github.com/speedinghzl/CCNet.