Papers › CCNet: Criss-Cross Attention for Semantic Segmentation

CCNet: Criss-Cross Attention for Semantic Segmentation

28 Nov 2018ICCV 2019 10arXiv:1811.11721archive 2025-07-28

Zilong Huang, Xinggang Wang, Yunchao Wei, Lichao Huang, Humphrey Shi, Wenyu Liu, Thomas S. Huang

Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Concretely, for each pixel, a novel criss-cross attention module harvests the contextual information of all the pixels on its criss-cross path. By taking a further recurrent operation, each pixel can finally capture the full-image dependencies. Besides, a category consistent loss is proposed to enforce the criss-cross attention module to produce more discriminative features. Overall, CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage. 2) High computational efficiency. The recurrent criss-cross attention significantly reduces FLOPs by about 85% of the non-local block. 3) The state-of-the-art performance. We conduct extensive experiments on semantic segmentation benchmarks including Cityscapes, ADE20K, human parsing benchmark LIP, instance segmentation benchmark COCO, video segmentation benchmark CamVid. In particular, our CCNet achieves the mIoU scores of 81.9%, 45.76% and 55.47% on the Cityscapes test set, the ADE20K validation set and the LIP validation set respectively, which are the new state-of-the-art results. The source codes are available at \url{https://github.com/speedinghzl/CCNet}.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1811.11721")

Code

Syntology Ran 9 of 14 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong; 4 ran · fixture could not drive it.

By repository: official repository: 9 samples from 1 repository, 8 ran; community (archive-listed): 5 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

speedinghzl/CCNet officialmentioned in papermentioned on GitHubpytorchMIT report
justld/CCNet_paddle mentioned on GitHubpaddleApache-2.0 report
open-mmlab/mmsegmentation pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 9 ran; 2 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
4ran · fixture could not drive it
5unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

INF speedinghzl/CCNet/cc_attention/functions.py official repository ran · fixture could not drive it MIT (permissive) · 349015c9fdf7266b · report
conv3x3 speedinghzl/CCNet/networks/ccnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
get_palette speedinghzl/CCNet/evaluate.py official repository ran · honoured contract fingerprinted MIT (permissive) · 26664d79586aad5a · report
iou speedinghzl/CCNet/loss/lovasz_losses.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · d94639b28b2134ff · report
iou_binary speedinghzl/CCNet/loss/lovasz_losses.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 1211530cd527bd0b · report
lovasz_grad speedinghzl/CCNet/loss/lovasz_losses.py official repository ran · violated contract fingerprinted MIT (permissive) · e85b5d21dc5b8382 · report
outS speedinghzl/CCNet/networks/ccnet.py official repository ran · honoured contract fingerprinted MIT (permissive) · 27504cbeb5811ea6 · report
pad_image speedinghzl/CCNet/evaluate.py official repository ran · fixture could not drive it MIT (permissive) · 6ec02fe7ffee8530 · report
predict_sliding speedinghzl/CCNet/evaluate.py official repository unverified MIT (permissive) · e3543651d7594983 · report
partition_list justld/CCNet_paddle/paddleseg/core/predict.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2f75a098ce9f7b0e · report
flip_combination justld/CCNet_paddle/paddleseg/core/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · 95bccf5957a196e4 · report
get_reverse_list justld/CCNet_paddle/paddleseg/core/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · a5dbdd4f2d59692e · report
get_test_config justld/CCNet_paddle/predict.py community (archive-listed) unverified Apache-2.0 (permissive) · 0b3ec74bd2e5ed5d · report
get_test_config justld/CCNet_paddle/val.py community (archive-listed) unverified Apache-2.0 (permissive) · 0c97512ed5e1d7e1 · report

Tasks

Computational EfficiencyHuman ParsingInstance SegmentationObject DetectionSegmentationSemantic SegmentationThermal Image SegmentationVideo SegmentationVideo Semantic Segmentationobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation Cityscapes test CCNet Mean IoU (class) 81.4% #41 of 105 Archive leaderboard report
Semantic Segmentation FoodSeg103 CCNet (ResNet-50) mIoU 35.5 #7 of 7 Archive leaderboard report
Thermal Image Segmentation MFN Dataset CCNet mIOU 43.3 #51 of 55 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: CCNet

1x1 ConvolutionCCNetNon-Local BlockNon-Local OperationResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections