(ICCV 2018) Ccnet:Criss-cross attention for semantic segmentation

Keyword [Segmentation] [Recurrent Criss-cross Attention Module]

Huang Z, Wang X, Huang L, et al. Ccnet: Criss-cross attention for semantic segmentation[C]//Proceedings of the IEEE International Conference on Computer Vision. 2019: 603-612.

1. Overview

In this paper, it proposes
1) Criss-cross Network (CCNet) with GPU memory friendly, High computational efficiency.

2) Criss-cross Attention Module (CCA).

3) Recurrent Criss-cross Attention Module (RCCA) to propagate information.

2. Experiments

2.1. Ablation Study

2.2. Comparison