search

speedinghzl / CCNet

CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).
MIT License
1.42k stars 277 forks source link

About the improvement of ccnet #30

Open shangqingchen opened 5 years ago

shangqingchen commented 5 years ago

I understand the question about the evaluation result of ccnet. Thank you very much for your reply. I also have another question about the improvement point of ccnet. Whether we can only pay cross attention to four nodes around the blue information point when we do cross-focus, can we improve the computing efficiency? I do a test as if it is feasible. I am eager to get your academic guidance. Thank you very much.

speedinghzl commented 5 years ago

It may be feasible. It's difficult to predict the result of the local and sparser attention. This is ICCV17 paper about local attention, hope it helps.

lxtGH commented 5 years ago

I disgree. No global information are embedded.

shangqingchen commented 5 years ago

Baidu ZhiHu has a CCNET article on it and a comment on it below. If you look at it, the overall situation will not be lost, and the author thinks it is feasible.

shangqingchen commented 5 years ago

I am making this improvement and will use the validation set to analyze the success of the improvement.

lxtGH commented 5 years ago

It is feasible if you stack more layers to get final global results.