Description
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.
Papers Using This Method
Context-Aware Palmprint Recognition via a Relative Similarity Metric2025-04-15Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration2024-12-17Towards Context-aware Convolutional Network for Image Restoration2024-12-15Comprehensive Competition Mechanism in Palmprint Recognition2023-08-17The Web Is Your Oyster -- Knowledge-Intensive NLP against a Very Large Web Corpus2021-12-18CCNet: Criss-Cross Attention for Semantic Segmentation2018-11-28