02/02/2021

SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations

Hao-Zhe Feng, Kezhi Kong, Minghao Chen, Tianye Zhang, Minfeng Zhu, Wei Chen

Keywords:

Abstract Paper Similar Papers

Abstract: Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference results.In this paper, we investigate and propose two causes of this problem: (1) The ELBO objective cannot utilize the label information directly. (2) A bottleneck value exists, and continuing to optimize ELBO after this value will not improve inference accuracy. On the basis of the experiment results, we propose SHOT-VAE to address these problems without introducing additional prior knowledge. The SHOT-VAE offers two contributions: (1) A new ELBO approximation named smooth-ELBO that integrates the label predictive loss into ELBO. (2) An approximation based on optimal interpolation that breaks the ELBO value bottleneck by reducing the margin between ELBO and the data likelihood. The SHOT-VAE achieves good performance with 25.30% error rate on CIFAR-100 with 10k labels and reduces the error rate to 6.11% on CIFAR-10 with 4k labels.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38947762
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 15:31 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 4:50 
 0
 0
 0
 0
 3:05 
 0
 0
 0
 0
 4:43 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 14:30 
 0
 0
 0
 0
 6:10 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 10:53 
 0
 0
 0
 0
 14:58 
 0
 0
 0
 0
 15:05 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 14:05 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 15:35 
 0
 0
 0
 0
 4:46 
 1
 0
 0
 0
 3:21 
 0
 0
 0
 0
 5:20 
 0
 0
 0
 0
 14:13 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 13:34 
 0
 0
 0
 0
 4:23 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 13:37 
 0
 0
 0
 0
 3:14 
 0
 0
 0
 0
 14:07 
 0
 0
 0
 0
 8:24 
 0
 0
 0
 0
 14:48 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:19 
 0
 0
 0
 0
 14:52 
 0
 0
 0
 0
 13:58 
 0
 0
 0
 0
 15:06 
 0
 0
 0
 0
 11:24 
 0
 0
 0
 0
 13:04 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 2:48 
 0
 0
 0
 0
 3:05