# speedinghzl/CCNet

CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).

Repository: https://github.com/speedinghzl/CCNet
Canonical: https://ross.abutalabs.com/products/ccnet
Language: Python
License: MIT
License Family: permissive
Topics: cityscape, semantic-segmentation, self-attention, pytorch, scene-parsing, segmentation
Last push: 2021-03-19T07:13:45+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2837, "days_push": 1993, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1484, forks 275 (observed 2026-08-28T04:04:51.312688+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: semantic-segmentation, attention-mechanism, pytorch, scene-parsing, cityscapes, research-code, gpu, linux

## Member repositories
- speedinghzl/CCNet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:51.312688+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:34:01.095052+00:00, confidence not recorded.
  - readme: https://github.com/speedinghzl/CCNet (fetched 2026-08-28T04:04:51.312688+00:00, sha 9022a9d2877c)
- Data as of 2026-08-30T08:39:29.467469+00:00.