I am doing some research on the visual attention mechanism in remote sensing domain (where the features learnt from one layer are highlighted using the attention mask derived from another layer). From what I have observed, the attention mask is learnt in a similar fashion as any other branch in CNN. So, what is so special about the visual attention mask that makes it different from a regular two branch CNN? The reference papers are provided below:

Visual Attention-Driven Hyperspectral Image Classification (IEEE, 2019)

A Two-Branch CNN Architecture for Land Cover Classification of PAN and MS Imagery (MDPI, 2019)

  • 1
    $\begingroup$ Welcome to SE:AI! (I've edited to include the titles of the papers, and publication journal and year--always better to be explicit in service of search.) $\endgroup$ – DukeZhou May 18 at 22:00

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.