Variance Loss in Variational Autoencoders

• URL: http://arxiv.org/abs/2002.09860v2
• Date: Fri, 22 May 2020 20:55:37 GMT
• Title: Variance Loss in Variational Autoencoders
• Authors: Andrea Asperti
• Abstract summary: variance of generated data is significantly lower than that of training data. Problem is particularly relevant in a two stage setting, where we use a second VAE to sample in the latent space of the first VAE. Renormalizing the output of the second VAE towards the expected normal spherical distribution, we obtain a sudden burst in the quality of generated samples.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this article, we highlight what appears to be major issue of Variational Autoencoders, evinced from an extensive experimentation with different network architectures and datasets: the variance of generated data is significantly lower than that of training data. Since generative models are usually evaluated with metrics such as the Frechet Inception Distance (FID) that compare the distributions of (features of) real versus generated images, the variance loss typically results in degraded scores. This problem is particularly relevant in a two stage setting, where we use a second VAE to sample in the latent space of the first VAE. The minor variance creates a mismatch between the actual distribution of latent variables and those generated by the second VAE, that hinders the beneficial effects of the second stage. Renormalizing the output of the second VAE towards the expected normal spherical distribution, we obtain a sudden burst in the quality of generated samples, as also testified in terms of FID.

Related papers

• FedUV: Uniformity and Variance for Heterogeneous Federated Learning [5.9330433627374815]
  Federated learning is a promising framework to train neural networks with widely distributed data. Recent work has shown this is due to the final layer of the network being most prone to local bias. We investigate the training dynamics of the classifier by applying SVD to the weights motivated by the observation that freezing weights results in constant singular values.
  arXiv  Detail & Related papers  (2024-02-27T15:53:15Z)
• Structured Uncertainty in the Observation Space of Variational Autoencoders [20.709989481734794]
  In image synthesis, sampling from such distributions produces spatially-incoherent results with uncorrelated pixel noise. We propose an alternative model for the observation space, encoding spatial dependencies via a low-rank parameterisation. In contrast to pixel-wise independent distributions, our samples seem to contain semantically meaningful variations from the mean allowing the prediction of multiple plausible outputs.
  arXiv  Detail & Related papers  (2022-05-25T07:12:50Z)
• SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation [77.71161225100927]
  Anomaly detection is a fundamental yet challenging problem in machine learning. We propose a novel and powerful framework, dubbed as SLA$2$P, for unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2021-11-25T03:53:43Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)
• Predicting with Confidence on Unseen Distributions [90.68414180153897]
  We connect domain adaptation and predictive uncertainty literature to predict model accuracy on challenging unseen distributions. We find that the difference of confidences (DoC) of a classifier's predictions successfully estimates the classifier's performance change over a variety of shifts. We specifically investigate the distinction between synthetic and natural distribution shifts and observe that despite its simplicity DoC consistently outperforms other quantifications of distributional difference.
  arXiv  Detail & Related papers  (2021-07-07T15:50:18Z)
• Optimization Variance: Exploring Generalization Properties of DNNs [83.78477167211315]
  The test error of a deep neural network (DNN) often demonstrates double descent. We propose a novel metric, optimization variance (OV), to measure the diversity of model updates.
  arXiv  Detail & Related papers  (2021-06-03T09:34:17Z)
• Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach [38.45568741734893]
  Inference in our GP model is done by a single feed forward pass through the network, significantly faster than semi-amortized methods. We show that our approach attains higher test data likelihood than the state-of-the-arts on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-02-05T13:01:12Z)
• Addressing Variance Shrinkage in Variational Autoencoders using Quantile Regression [0.0]
  Probable Variational AutoEncoder (VAE) has become a popular model for anomaly detection in applications such as lesion detection in medical images. We describe an alternative approach that avoids the well-known problem of shrinkage or underestimation of variance. Using estimated quantiles to compute mean and variance under the Gaussian assumption, we compute reconstruction probability as a principled approach to outlier or anomaly detection.
  arXiv  Detail & Related papers  (2020-10-18T17:37:39Z)
• Temporal Action Localization with Variance-Aware Networks [12.364819165688628]
  This work addresses the problem of temporal action localization with Variance-Aware Networks (VAN) VANp is a network that propagates the mean and the variance throughout the network to deliver outputs with second order statistics. Results show that VANp surpasses the accuracy of virtually all other two-stage networks without involving any additional parameters.
  arXiv  Detail & Related papers  (2020-08-25T20:12:59Z)
• Recent Developments Combining Ensemble Smoother and Deep Generative Networks for Facies History Matching [58.720142291102135]
  This research project focuses on the use of autoencoders networks to construct a continuous parameterization for facies models. We benchmark seven different formulations, including VAE, generative adversarial network (GAN), Wasserstein GAN, variational auto-encoding GAN, principal component analysis (PCA) with cycle GAN, PCA with transfer style network and VAE with style loss.
  arXiv  Detail & Related papers  (2020-05-08T21:32:42Z)
• Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data [87.61504710345528]
  We propose two strategies for freeing a neural network from tuning with OoD data, while improving its OoD detection performance. We specifically propose to decompose confidence scoring as well as a modified input pre-processing method. Our further analysis on a larger scale image dataset shows that the two types of distribution shifts, specifically semantic shift and non-semantic shift, present a significant difference.
  arXiv  Detail & Related papers  (2020-02-26T04:18:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.