speedinghzl/CCNet

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1484 stars · 275 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official PyTorch implementation of CCNet, a Criss-Cross Attention network for semantic segmentation published at ICCV 2019 and TPAMI 2020. It provides a recurrent criss-cross attention module that captures long-range pixel dependencies efficiently for scene parsing tasks.

Use cases

• implement semantic segmentation with criss-cross attention
• train scene parsing models on Cityscapes
• capture long-range contextual dependencies in images
• reproduce CCNet paper results
• use attention modules for dense pixel prediction
• segment urban street scenes

When to choose

• you need efficient long-range context modeling for segmentation
• you want a GPU-memory-friendly alternative to non-local attention
• you are reproducing ICCV/TPAMI segmentation baselines on Cityscapes

When to avoid

• you need a maintained production segmentation toolkit
• you require the latest transformer-based segmentation architectures
• you need Windows or non-PyTorch support

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning python semantic-segmentation attention-mechanism pytorch scene-parsing cityscapes research-code gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="speedinghzl/CCNet")