Unexpected results

Question

Unexpected results

oferavni opened this issue 7 years ago · comments

Hi,
I'm running the demo as is, and seem to get unexpected results such as:

Would appreciate any ideas.
Thanks,
Ofer

Ignacio Rocco · Answer 1 · Thu Oct 19 2017 22:56:47 GMT+0800 (China Standard Time)

Hi,

This method is only obtaining about 57% PCK in PF. This means that about 40% of points will be wrong, so expect some bad cases.

However, you should also get some other results which look good.

Best,
Ignacio

oferavni · Answer 2 · Thu Oct 19 2017 23:46:58 GMT+0800 (China Standard Time)

Hi Ignacio,

Still, there's some inconsistency I'd like to resolve. Figure 8 in the article shows:

but when I run the demo on (what I assume are the same images), I get:

Could these images be slightly different (e.g. resolution)? Do you expect slight differences to render such difference in the results?

Thanks so much for your prompt reply!
Ofer

Ignacio Rocco · Answer 3 · Fri Oct 20 2017 02:58:39 GMT+0800 (China Standard Time)

Hi,

You are right. I believe the images from the paper where generated with another version of the model, with slightly less overall performance.

However, for the particular example you are pointing out, the previous model was working better.

oferavni · Answer 4 · Fri Oct 20 2017 03:14:50 GMT+0800 (China Standard Time)

Hi,

Do you have some non-trivial examples where the current model works well? Hope this may allow for some insights of what it does.

Thanks!
Ofer

Ignacio Rocco · Answer 5 · Fri Oct 20 2017 14:23:59 GMT+0800 (China Standard Time)

Hi,

I'm sorry to hear that you are not satisfied with the results of the algorithm. This is ongoing research, I hope the next paper will be more satisfactory for you :)

Please make sure to check out some newer work by other colleagues such as SCNet www.di.ens.fr/willow/research/scnet/

Best,
Ignacio