Closed StellaAthena closed 1 year ago
Would you see any other applications of the same idea outside the field of vision for instance ?
Would you see any other applications of the same idea outside the field of vision for instance ?
Definitely! I'm actually very interested in the idea of using Temporal Coherence (4.5.1) for time series analysis and potentially story-telling models (see my prior work on storytelling with @LouisCastricato here, here, and here)
diffusion models for storytelling are extremely promising- especially now since we can control the iterative refinement with CARP.
@excitingtimes what is your discord username.
@LouisCastricato here's my discord --> rohan42#3508 :)
@excitingtimes should I put you down as working on this?
Not yet @StellaAthena as this is not my primary research interest as of now, but will definitely ping you on this chan once I start working on it :)
@StellaAthena I would like to work on this, here's my fork, made a few changes
@hmen97 Awesome! Go ham :) I’m quite interested in seeing how it goes. DM me on Discord to talk about compute resources.
hey, @hmen97 @StellaAthena I'd be psyched to work on this. I've focused on the VAE from a cognitive science perspective for a bit. gonna read the paper, watch yannick's vid b/w now and Monday, and review the fork b/w now and Monday. lmk if anyone wants to chat.
@StellaAthena , Is anyone working on this? I can go through the material and try to get the code up and running for cifar-10, and cifar-100.
If we are ambitious enough, we can try out cub-200, oxford flowers, standard cars dataset too. These datasets are known for fine grained image classification where the classes are hard to distinguish. More details here. (https://paperswithcode.com/task/fine-grained-image-classification)
No one is working on this.
@LouisCastricato , So is this abandoned, Just curious? Might try my hand at it if it's not abandoned.
@imr555 You're quite welcome to work on it. I would need to refresh to get back up to speed but I think this is still a worthwhile project.
No worries, Thank You, @StellaAthena ...... Reason for the interest is, I had a brief stint with Capsules and VAEs back in 2020. I will look into it.
Background
A recent interesting paper in topological deep learning unfortunately only experiments on MNIST. Let’s try it on something more interesting.
Topographic VAEs learn Equivariant Capsules ArXiV abstract: https://arxiv.org/abs/2109.01394 Yannic's video: https://www.youtube.com/watch?v=pBau7umFhjQ Code: https://github.com/AKAndyKeller/TopographicVAE
What to Replicate?
It should be the same amount of work to replicate the entire paper as a subset of it I imagine?
Modifications
How about CIFAR-10 and CIFAR-100 for starters, maybe ImageNet if the initial results are good.
Related Papers/Frameworks
n/a