CCNet CrissCross Attention for Semantic Segmentation Zilong Huang
- Slides: 11
CCNet: Criss-Cross Attention for Semantic Segmentation Zilong Huang 1, Xinggang Wang 1, Lichao Huang 2, Chang Huang 2, Yunchao Wei 3, Wenyu Liu 1 1 School of EIC, Huazhong University of Science and Technology 2 Horizon Robotics 3 Beckman Institute, University of Illinois at Urbana-Champaign Speaker: Zhixuan Li 2019/03/11 Zhixuan Li 1
Retrospect DANet 2019/03/11 Zhixuan Li 2
Retrospect DANet • Computation Cost Expensive: • Each pixel has to multiply with all pixels in the feature map 2019/03/11 Zhixuan Li 3
About CCNet • CCNet is the computation cost saving version of DANet • RCCA Module 2019/03/11 Zhixuan Li 4
Two RCCA modules are necessary • A simple example, after the first RCCA module, the value in position C contains the information of A and D. • And in the same time, the value in A contains the information of B and C. • So after the second RCCA module, position C can capture the relationship between C and B indirectly by computing the distance with the new value in position A. 2019/03/11 Zhixuan Li 5
Ablation studies • The effect of attention module 2019/03/11 Zhixuan Li 6
Ablation studies • Comparison of context aggregation approaches on Cityscapes validation set • • PSP : Pyramid Spatial Pooling ASPP : Atrous PSP NL : DANet RCCA : CCNet 2019/03/11 Zhixuan Li 7
Rank of the experiment result 2019/03/11 Zhixuan Li 8
Visualization of Attention Map 2019/03/11 Zhixuan Li 9
Conclusion • Advantages • The decomposition greatly reduce the complexity in time and space from O((H x W)) to O((H x W)(H + W - 1)). 2019/03/11 Zhixuan Li 10
Conclusion • Disadvantages • At the second RCCA module, when computing C, A is used twice but B is used just once when computing A. • So maybe A makes more affect to C than B does. • It's unreasonable for B maybe more important for C than A. 2019/03/11 Zhixuan Li 11
- Ccnet: criss-cross attention for semantic segmentation
- Examples of criss cross method
- Criss cross method steps
- Michelle benjamin phd
- Deconvolution이란
- Denseaspp for semantic segmentation in street scenes
- Dual super-resolution learning for semantic segmentation
- Market segmentation wiki
- What cultural hearth was in the huang he river basin?
- Zeku huang
- Dugen huang
- Why did the shang rulers become powerful