{"url":"/method/ccnet","slug":"ccnet","name":"CCNet","full_name":"Criss-Cross Network","full_name_withheld":false,"description_markdown":"**Criss-Cross Network** (**CCNet**) aims to obtain full-image contextual information in an effective and efficient way. Concretely,\r\nfor 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\r\nmerits: **1)** GPU memory friendly. Compared with the [non-local block](https://paperswithcode.com/method/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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"CCNet: Criss-Cross Attention for Semantic Segmentation","paper":"/paper/ccnet-criss-cross-attention-for-semantic","first_author":"Zilong Huang","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/ccnet-criss-cross-attention-for-semantic"},"source":{"url":"https://arxiv.org/abs/1811.11721v2","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Semantic Segmentation Models","url":"/methods/category/semantic-segmentation-models","pwc_aliases":["segmentation-models"]}],"n_papers_tagged":6,"archive_num_papers":6,"papers_newest_first":[{"paper":null,"title":"Context-Aware Palmprint Recognition via a Relative Similarity Metric","date":"2025-04-15","arxiv_id":"2504.11306","n_code_links":0,"syntology":null},{"paper":"/paper/dense-audio-visual-event-localization-under","title":"Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration","date":"2024-12-17","arxiv_id":"2412.12628","n_code_links":1,"syntology":{"ran":0,"of":14,"unverified":14,"pointer_only":14}},{"paper":null,"title":"Towards Context-aware Convolutional Network for Image Restoration","date":"2024-12-15","arxiv_id":"2412.11008","n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-competition-mechanism-in","title":"Comprehensive Competition Mechanism in Palmprint Recognition","date":"2023-08-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/the-web-is-your-oyster-knowledge-intensive","title":"The Web Is Your Oyster -- Knowledge-Intensive NLP against a Very Large Web Corpus","date":"2021-12-18","arxiv_id":"2112.09924","n_code_links":2,"syntology":null},{"paper":"/paper/ccnet-criss-cross-attention-for-semantic","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","date":"2018-11-28","arxiv_id":"1811.11721","n_code_links":4,"syntology":{"ran":9,"of":14,"unverified":5,"pointer_only":0}}],"papers_shown":6,"tasks":[{"task":"/task/common-sense-reasoning","name":"Common Sense Reasoning","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/deblurring","name":"Deblurring","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/human-parsing","name":"Human Parsing","papers":1},{"task":"/task/image-dehazing","name":"Image Dehazing","papers":1},{"task":"/task/image-restoration","name":"Image Restoration","papers":1},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/scene-understanding","name":"Scene Understanding","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1},{"task":"/task/thermal-image-segmentation","name":"Thermal Image Segmentation","papers":1},{"task":"/task/video-segmentation","name":"Video Segmentation","papers":1},{"task":"/task/video-semantic-segmentation","name":"Video Semantic Segmentation","papers":1},{"task":"/task/audio-visual-event-localization","name":"audio-visual event localization","papers":1},{"task":"/task/audio-visual-learning","name":"audio-visual learning","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":20,"n_tasks":20,"usage_by_year":[{"year":"2018","papers":1},{"year":"2021","papers":1},{"year":"2023","papers":1},{"year":"2024","papers":2},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/ccnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}