CCNet: Criss-Cross Attention for Semantic Segmentation
Huazhong University of Science and Technology · University of Technology Sydney · +3 more institutions
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
- FWCI
- 30.50
- Percentile
- 100%
- References
- 70
Authors
7Topics & keywords
- Computer science
- Benchmark (surveying)
- Discriminative model
- Artificial intelligence
- Segmentation
- Parsing
- Block (permutation group theory)
- Pixel
- Reduced inequalities