Do vision transformers see like convolutional neural networks?

Re:Do vision transformers see like convolutional neural netw... by codeflo on Wednesday August 25, 2021 @01:49PM (#28304553)

Those pictures are definitely NSFW when viewed at low res/from far away, which is how coworkers typically see your monitor contents. An argument that starts with “Well, technically” is unlikely to carry much weight in a discussion with HR (and probably rightfully so).

[ Parent | on HN ]

Re:Do vision transformers see like convolutional neural netw... by gugagore on Wednesday August 25, 2021 @06:27PM (#28307939)

I think the scientific point here is that visual processing is not a one-shot process. Tasked with object detection, some scenes demand more careful processing and more computation.

Almost all neural network architectures process a given input size in the same amount of time, and some applications and datasets would benefit from an "anytime" approach, where the output is gradually refined given more time.

I understand the point you are making, but it's kind of irrelevant. The task is to produce an answer for the image at the given resolution. It is an accident and coincidence that the neural network produces an answer that is arguably correct for a blurrier version of the image.

[ Parent | on HN ]

Re:Do vision transformers see like convolutional neural netw... by codeflo on Wednesday August 25, 2021 @04:18PM (#28306398)

Counter argument in addition to downvote, please?

[ Parent | on HN ]

Re:Do vision transformers see like convolutional neural netw... by Dylan16807 on Thursday August 26, 2021 @12:48AM (#28310818)

Probably because "Well, technically" is a really unfair way to characterize that argument.

It's not porn. It's not simulated porn. It's a hallway, and if you're not setting it as your desktop background to trick people on purpose then you're not doing anything wrong.

[ Parent | on HN ]