CCNet: Criss-Cross Attention for Semantic Segmentation

Huazhong University of Science and Technology · University of Technology Sydney · +3 more institutions

PubMed
Indexed incrossrefpubmed

Abstract

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…

Citation impact

544
total citations
FWCI
30.50
Percentile
100%
References
70
Citations per year

Authors

7

Topics & keywords

Keywords
  • Computer science
  • Benchmark (surveying)
  • Discriminative model
  • Artificial intelligence
  • Segmentation
  • Parsing
  • Block (permutation group theory)
  • Pixel
UN Sustainable Development Goals
  • Reduced inequalities
No related works found for this paper.

Funding