Research identifies key weakness in modern computer vision systems

Re:Research identifies key weakness in modern computer visio... by nmca on Saturday August 11, 2018 @07:40AM (#17739290)

Hm, this seems vaguely interesting-if-true but:

1) It's not published in a good CV journal.

2) It seems quite likely that they've just identified the problems described and fixed by [0, 1] (of which [0] is the much better paper).

In brief, CNNs guarantee translation invariance (ignoring boundary effects) through translation equivariance of their feature maps; this borks certain problems, most importantly a commonly used mechanism for instance segmentation as described in [0]. Consider trying to instance-segment two copy/pasted faces; translation equivariance and global pooling clearly make it impossible.

I strongly suspect that the problem described in the paper originates from a similar place, and thus could be solved in a week or so. I doubt it's a "key weakness of modern cv systems".

[0] https://arxiv.org/abs/1807.10712 [1] https://arxiv.org/abs/1807.03247

EDIT - a little further investigation shows that it was accepted as a workshop paper at ICLR, also provides the reviewers comments. https://openreview.net/forum?id=HymuJz-A-

So perhaps I'm being overly negative. Can't find any code release for it, would be interested if anyone can.

EDIT2 - Entertainingly, the workshop paper version of this and the CoordConv paper seem to use the same name for different toy tasks, "Not-so-CLEVR".

[ Parent | on HN ]

Re:Research identifies key weakness in modern computer visio... by mannykannot on Saturday August 11, 2018 @09:32AM (#17739606)

Thanks for the link to the reviewers' comments. I am not an academic, and I found some of the objections surprising, such as this one that might be seen as suggesting that the authors just had the wrong attitude:

"However, I think there's some chance that if the same tasks were in the hands of people who wanted CNNs or CNN+RN to work well, the results might have been different."

The reviewer goes on to write that he cannot say what people with the proper attitude would do differently.

[ Parent | on HN ]

Re:Research identifies key weakness in modern computer visio... by ColanR on Saturday August 11, 2018 @01:32PM (#17740638)

> if the same tasks were in the hands of people who wanted CNNs or CNN+RN to work well, the results might have been different.

I guess that's an undesirable symptom of CNNs (etc.) still being an empirical rather than theoretical science.

[ Parent | on HN ]