Methods › Computer Vision › Semantic Segmentation Models › CCNet

Criss-Cross Network

CCNet

6 papers tagged archive 2025-07-28

Introduced by Zilong Huang et al. in CCNet: Criss-Cross Attention for Semantic Segmentation

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Criss-Cross Network (CCNet) aims to obtain full-image contextual information in an 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. CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11× 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.

Paper Source

Papers archive 2025-07-28

6 shown of 6, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Context-Aware Palmprint Recognition via a Relative Similarity Metric
15 Apr 2025 · 0 repositories · arXiv:2504.11306
Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration
17 Dec 2024 · 1 repository · arXiv:2412.12628

Syntology ran 0 of 14 samples · 14 unverified · 14 pointer-only (licence)
Towards Context-aware Convolutional Network for Image Restoration
15 Dec 2024 · 0 repositories · arXiv:2412.11008
Comprehensive Competition Mechanism in Palmprint Recognition
17 Aug 2023 · 1 repository
The Web Is Your Oyster -- Knowledge-Intensive NLP against a Very Large Web Corpus
18 Dec 2021 · 2 repositories · arXiv:2112.09924
CCNet: Criss-Cross Attention for Semantic Segmentation
28 Nov 2018 · 4 repositories · arXiv:1811.11721

Syntology ran 9 of 14 samples · 5 unverified

Tasks archive 2025-07-28

20 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Common Sense Reasoning	1
Computational Efficiency	1
Deblurring	1
GPU	1
Human Parsing	1
Image Dehazing	1
Image Restoration	1
Instance Segmentation	1
Object Detection	1
Representation Learning	1
Retrieval	1
Scene Understanding	1
Segmentation	1
Semantic Segmentation	1
Thermal Image Segmentation	1
Video Segmentation	1
Video Semantic Segmentation	1
audio-visual event localization	1
audio-visual learning	1
object-detection	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (6 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Semantic Segmentation Models

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