search

wielandbrendel / bag-of-local-features-models

Pretrained bag-of-local-features neural networks
Other
312 stars 45 forks source link

Confusion about visualizations #15

Open rbunn80110 opened 5 years ago

rbunn80110 commented 5 years ago

I have found your work to be very fascinating, especially the potential for much better visualizations of what has been learned by the network. I was playing around with the notebook you uploaded, but can't seem to get the visualizations to look like the ones that are shown in your paper. Unfortunately, I don't know the index numbers of those specific images so I couldn't do an exact comparison. However, the images I did go through didn't seem to be comparable at all in quality to the ones in the paper. How would I reproduce the images you used as examples in your paper? Thank you for publishing such great work here for everyone to learn from.

ferjad commented 5 years ago

@rbunn80110 The visualization is dependent on the task at hand and can be noisy for certain images in ImageNet, your best bet is to iterate through some random images from ImageNet. The ImageNet samples imported from FoolBox are not the best indication of the potential of the model and maybe the authors can change them to avoid confusion.

wielandbrendel commented 5 years ago

@rbunn80110 Could you elaborate what you mean by that the visualisations you get are not as good as in the paper? Could you post an example?

rbunn80110 commented 4 years ago

"Unfortunately, I don't know the index numbers of those specific images so I couldn't do an exact comparison."