Discover and read the best of Twitter Threads about #tadaaa
Most recents (1)
🚨 ICLR SPOTLIGHT 🚨
Unsupervised denoising, i.e. removing noise in data without having ground truth, has a new state-of-the-art. A short 🧵 about why this rocks...
openreview.net/forum?id=DfMql…
Spoiler: it can also remove structured noise & gives diverse solutions for ambiguous data
Unsupervised denoising, i.e. removing noise in data without having ground truth, has a new state-of-the-art. A short 🧵 about why this rocks...
openreview.net/forum?id=DfMql…
Spoiler: it can also remove structured noise & gives diverse solutions for ambiguous data
Our method, called HDN, employs a hierarchical VAE to learn a latent representation of structures occuring in a noisy body of data. Hence, we can later use the model to sample a space of sensible ‘data interpretations’.
Without any further tricks this leads to SOTA results for removing pixel noises!
(And the sampling discussed above is a super useful bonus feature other methods typically can't offer...)
(And the sampling discussed above is a super useful bonus feature other methods typically can't offer...)
