search

researchmm / LightTrack

[CVPR21] LightTrack: Finding Lightweight Neural Network for Object Tracking via One-Shot Architecture Search
MIT License
396 stars 59 forks source link

About the pixel_corr_mat method #5

Closed TCBocean closed 3 years ago

TCBocean commented 3 years ago

I noticed that the method of cross-correlation is different from the general siam tracker. In the code, the matrix multiplication method is used as the pixel cross-correlation, and the channel separable convolution method is generally used as the channel cross-correlation. What are the advantages of using pixel correlation? Looking forward to your reply, thank you very much!

MasterBin-IIAU commented 3 years ago

Hi, thanks for your interest to our work :) LightTrack uses pixel-wise correlation to fuse the features of the template and the search region. More details about the difference between the pixel-wise correlation and the depth-wise correlation can be found in the paper AlphaRefine's section 3.2 Thanks

TCBocean commented 3 years ago

Thank you for your reply, it is very helpful to me.