Poor reconstruction quality

[nblauch]

Hi Felix -

Thanks for providing the toolbox. It's great to have this functionality in MatConvnet. However, I'm having one serious problem. I'm not able to generate good reconstructions. I've tried starting from the zero image as well as the noise image, as suggested in the function description, and have gone up to 10,000 runs with little success at moving the image towards its target. I believe Yosinski generated his activation-maximization results with less than 1000 iterations, so I don't think the number of runs is the issue. I haven't tried messing with the regularization parameters, as I assume you set the defaults to the ones that worked best in practice, and which were established by prior work.

Can you supply an example in which you get a good reconstruction?

Thanks.

-Nick

[FelixGruen]

Hi Nick,

you are right, the values I set for default don't seem to work. It's on the to-do list.

I had tested the implementation of the regularizers and it works fine, but there must be something wrong with the default values for the balancing factors. The values are based on Mahendran & Vedaldi (2014).

Unfortunately I'm busy this week and the next, but I'll investigate it further at the beginning of August.

Best,
Felix