A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers

• URL: http://arxiv.org/abs/2006.05389v3
• Date: Fri, 9 Oct 2020 12:15:02 GMT
• Title: A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers
• Authors: Niccol\`o Antonello, Philip N. Garner
• Abstract summary: Neural Network (NN) classifiers can assign extreme probabilities to samples that have not appeared during training. One of the causes for this unwanted behaviour lies in the use of the standard softmax operator. In this paper, a novel operator is proposed that is derived using $t$-distributions which are capable of providing a better description of uncertainty.
• Score: 14.567354306568296
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural Network (NN) classifiers can assign extreme probabilities to samples that have not appeared during training (out-of-distribution samples) resulting in erroneous and unreliable predictions. One of the causes for this unwanted behaviour lies in the use of the standard softmax operator which pushes the posterior probabilities to be either zero or unity hence failing to model uncertainty. The statistical derivation of the softmax operator relies on the assumption that the distributions of the latent variables for a given class are Gaussian with known variance. However, it is possible to use different assumptions in the same derivation and attain from other families of distributions as well. This allows derivation of novel operators with more favourable properties. Here, a novel operator is proposed that is derived using $t$-distributions which are capable of providing a better description of uncertainty. It is shown that classifiers that adopt this novel operator can be more robust to out of distribution samples, often outperforming NNs that use the standard softmax operator. These enhancements can be reached with minimal changes to the NN architecture.

Related papers

• Variational Classification [51.2541371924591]
  We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders. Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency. We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
  arXiv  Detail & Related papers  (2023-05-17T17:47:19Z)
• Improved uncertainty quantification for neural networks with Bayesian last layer [0.0]
  Uncertainty quantification is an important task in machine learning. We present a reformulation of the log-marginal likelihood of a NN with BLL which allows for efficient training using backpropagation.
  arXiv  Detail & Related papers  (2023-02-21T20:23:56Z)
• Uncertainty Modeling for Out-of-Distribution Generalization [56.957731893992495]
  We argue that the feature statistics can be properly manipulated to improve the generalization ability of deep learning models. Common methods often consider the feature statistics as deterministic values measured from the learned features. We improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.
  arXiv  Detail & Related papers  (2022-02-08T16:09:12Z)
• Exponentially Tilted Gaussian Prior for Variational Autoencoder [3.52359746858894]
  Recent studies show that probabilistic generative models can perform poorly on this task. We propose the exponentially tilted Gaussian prior distribution for the Variational Autoencoder (VAE) We show that our model produces high quality image samples which are more crisp than that of a standard Gaussian VAE.
  arXiv  Detail & Related papers  (2021-11-30T18:28:19Z)
• On some theoretical limitations of Generative Adversarial Networks [77.34726150561087]
  It is a general assumption that GANs can generate any probability distribution. We provide a new result based on Extreme Value Theory showing that GANs can't generate heavy tailed distributions.
  arXiv  Detail & Related papers  (2021-10-21T06:10:38Z)
• 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)
• Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise [51.080620762639434]
  We propose a more efficient parameterization of the posterior approximation for sampling-free variational inference. Our approach yields competitive results for standard regression problems and scales well to large-scale image classification tasks.
  arXiv  Detail & Related papers  (2021-03-15T16:16:18Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Being Bayesian about Categorical Probability [6.875312133832079]
  We consider a random variable of a categorical probability over class labels. In this framework, the prior distribution explicitly models the presumed noise inherent in the observed label. Our method can be implemented as a plug-and-play loss function with negligible computational overhead.
  arXiv  Detail & Related papers  (2020-02-19T02:35:32Z)

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.