Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Disentangling by Factorising

About

We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon $\beta$-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

Hyunjik Kim, Andriy Mnih• 2018

Related benchmarks

TaskDatasetResultRank
Time Series ForecastingETTh1
MSE0.484
836
Time Series ForecastingETTh1 (test)
MSE0.87
398
Time Series ForecastingETTm1
MSE2.326
363
Time Series ForecastingETTm1 (test)
MSE2.326
315
Time Series ForecastingTraffic (test)
MSE0.982
272
Time Series ForecastingWeather (test)
MSE0.53
248
Time Series ForecastingTraffic
MSE0.936
211
Time Series ForecastingElectricity (test)
MSE0.807
130
Image ReconstructionCelebA-HQ (test)
FID (Reconstruction)87.19
50
Time Series ForecastingWind
MSE0.898
46
Showing 10 of 71 rows
...

Other info

Follow for update