Re learning reverse graphics - ok, maybe it is indeed the main feature of your work. I’d need to look into that, because from skimming your paper it’s not immediately clear what’s going on there.
Re convnet accuracy on Norb - I’m willing to make that effort for cifar-10 as soon as you have the results.
Actually, I'm comparing it to recent models, including XLNet, MT-DNN, Snorkel, and (of course) BERT. AFAIK, convnets have not been able to outperform multihead self-attention, even on pretrained embeddings.
> Re learning reverse graphics - ok, maybe it is indeed the main feature of your work. I’d need to look into that, because from skimming your paper it’s not immediately clear what’s going on there.
I agree, it's not immediately clear. Nonetheless, I find it kind of unbelievable that a model with so few parameters can seem to do it. (I was shocked when I first saw the plots.)
> Re convnet accuracy on Norb - I’m willing to make that effort for cifar-10 as soon as you have the results.
That's a little disappointing... but OK.
Thank you so much for all your questions :-)
Actually, it looks like you got a solid paper. I recommend submitting either to CVPR or ICML, especially if you can get good results on cifar.
Yes, I think this has legs.
Maximizing "bang per bit" (a) seems truly a new idea, as opposed to some minor tweak on the same old thing, and (b) the evidence so far shows it works better than previous methods.
(FWIW, we've been using this algorithm internally at work with similar outperformance over other methods, in yet another domain that is neither vision nor language... but I cannot share those results publicly.)
Before submitting this anywhere, I'd like to get more informal feedback from other AI researchers. I've reached out to people at Google Brain, Facebook AI, DeepMind, OpenAI, and a handful of top academic institutions and research groups. So far, the response has been positive, but I expect it will take everyone at least a couple of weeks, and probably longer, to read and understand the draft paper in sufficient detail to give me more than superficial comments.
New things often look like toys at first. :-)
I'll take a look at submitting it to CVPR.
In the meantime, please circulate my work. It's on record, online. The more people who are aware that others have seen it, the less likely someone will try to plagiarize it.
I'm not under any kind of academic pressure, so I don't need citations, conference slots, etc. But I do deserve credit for this, don't you think?
PS. And now that you mention it, a couple of people to whom I reached out mentioned they were under deadline over the next two weeks.
PPS. Send me an email!
Let me know when you have CIFAR-10 results, I will try to match your accuracy using the same number of parameters in a regular convnet. I actually implemented the original, vector based capsnet a while ago: https://github.com/michaelklachko/CapsNet but I haven't really explored it. Your success on CIFAR-10 would definitely provide motivation for me to do so.
FWIW, a while back I reimplemented and tinkered a bit with the Sabour et al. version too... and did not see much promise in it.
Note that the routing algorithm I've proposed generalizes to vectors (by setting the dimension of the covector space d_cov to 1).
As far as I know, regular convnets have failed to outperform query-key-value self-attention models (i.e., transformers based on Vaswani et al.'s work) on pretty much every sequence task, including natural language tasks.
> Learning to do “reverse graphics” is only useful if you can show it is the reason behind performance improvement.
I would strongly disagree. Building systems that can learn "reverse graphics" on their own has long been a goal of computer vision. It seems a prerequisite for building machines that can build internal representations of the state of the physical world around them. Hinton et al.'s 2018 paper has a summary of recent efforts on this front on the "Related Work" section.
> What I’m saying is - no one has yet demonstrated a clear superiority of any capsules based model to the best available plain convnet.
No one is saying otherwise. :-) Convnets are still the right tool for most production systems in visual recognition today.
That said, I don't think a convnet can achieve 99.1% accuracy on smallNORB with only 272K parameters, after training from scratch without using any additional data or metadata of any kind -- like the model using my routing algorithm. If you think you can do that with a convnet, do it and put it up online (I'd love to see it :-)