search

aimerykong / Low-Rank-Bilinear-Pooling

CVPR2017 - an ultra-compact bilinear model for fine-grained classification
https://www.cs.cmu.edu/~shuk/lr_bilinear.html
149 stars 36 forks source link

what is the demo 1 mean? #1

Open iFighting opened 7 years ago

iFighting commented 7 years ago

so you did not implement the Low-Rank-Bilinear-Pooling model in the paper(cvpr 2017) using Caffe?

so,i have i problem, what is the demo 1 mean?

aimerykong commented 7 years ago

No, there is no caffe version of the low-rank bilinear method. There are several reasons in providing demo 1 --

  1. Caffe runs a little faster than matconvnet, so simply applying PCA to do dimensionality reduction and the bilinear training using caffe is a fast combo to play with.
  2. It seems combining our low-rank theory plus other kernel methods achieves faster training and better performance.

On Fri, May 19, 2017 at 2:43 AM, iFighting notifications@github.com wrote:

so you did not implement the Low-Rank-Bilinear-Pooling model in the paper(cvpr 2017) using Caffe?

so,i have i problem, what is the demo 1 mean?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/aimerykong/Low-Rank-Bilinear-Pooling/issues/1, or mute the thread https://github.com/notifications/unsubscribe-auth/AGKZJHY1UTqBqKCaVR61sND83iPY80ADks5r7WRUgaJpZM4NgTha .