Understanding Classifier Mistakes with Generative Models
- URL: http://arxiv.org/abs/2010.02364v1
- Date: Mon, 5 Oct 2020 22:13:21 GMT
- Title: Understanding Classifier Mistakes with Generative Models
- Authors: La\"etitia Shao, Yang Song, Stefano Ermon
- Abstract summary: Deep neural networks are effective on supervised learning tasks, but have been shown to be brittle.
In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize.
Our approach is agnostic to class labels from the training set which makes it applicable to models trained in a semi-supervised way.
- Score: 88.20470690631372
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Although deep neural networks are effective on supervised learning tasks,
they have been shown to be brittle. They are prone to overfitting on their
training distribution and are easily fooled by small adversarial perturbations.
In this paper, we leverage generative models to identify and characterize
instances where classifiers fail to generalize. We propose a generative model
of the features extracted by a classifier, and show using rigorous hypothesis
testing that errors tend to occur when features are assigned low-probability by
our model. From this observation, we develop a detection criteria for samples
on which a classifier is likely to fail at test time. In particular, we test
against three different sources of classification failures: mistakes made on
the test set due to poor model generalization, adversarial samples and
out-of-distribution samples. Our approach is agnostic to class labels from the
training set which makes it applicable to models trained in a semi-supervised
way.
Related papers
- Revealing Model Biases: Assessing Deep Neural Networks via Recovered
Sample Analysis [9.05607520128194]
This paper proposes a straightforward and cost-effective approach to assess whether a deep neural network (DNN) relies on the primary concepts of training samples.
The proposed method does not require any test or generalization samples, only the parameters of the trained model and the training data that lie on the margin.
arXiv Detail & Related papers (2023-06-10T11:20:04Z) - Prototypical Classifier for Robust Class-Imbalanced Learning [64.96088324684683]
We propose textitPrototypical, which does not require fitting additional parameters given the embedding network.
Prototypical produces balanced and comparable predictions for all classes even though the training set is class-imbalanced.
We test our method on CIFAR-10LT, CIFAR-100LT and Webvision datasets, observing that Prototypical obtains substaintial improvements compared with state of the arts.
arXiv Detail & Related papers (2021-10-22T01:55:01Z) - Training on Test Data with Bayesian Adaptation for Covariate Shift [96.3250517412545]
Deep neural networks often make inaccurate predictions with unreliable uncertainty estimates.
We derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters.
We show that our method improves both accuracy and uncertainty estimation.
arXiv Detail & Related papers (2021-09-27T01:09:08Z) - Predicting Unreliable Predictions by Shattering a Neural Network [145.3823991041987]
Piecewise linear neural networks can be split into subfunctions.
Subfunctions have their own activation pattern, domain, and empirical error.
Empirical error for the full network can be written as an expectation over subfunctions.
arXiv Detail & Related papers (2021-06-15T18:34:41Z) - Defuse: Harnessing Unrestricted Adversarial Examples for Debugging
Models Beyond Test Accuracy [11.265020351747916]
Defuse is a method to automatically discover and correct model errors beyond those available in test data.
We propose an algorithm inspired by adversarial machine learning techniques that uses a generative model to find naturally occurring instances misclassified by a model.
Defuse corrects the error after fine-tuning while maintaining generalization on the test set.
arXiv Detail & Related papers (2021-02-11T18:08:42Z) - Debugging Tests for Model Explanations [18.073554618753395]
Methods tested are able to diagnose a spurious background bug, but not conclusively identify mislabeled training examples.
We complement our analysis with a human subject study, and find that subjects fail to identify defective models using attributions, but instead rely, primarily, on model predictions.
arXiv Detail & Related papers (2020-11-10T22:23:25Z) - Identifying Wrongly Predicted Samples: A Method for Active Learning [6.976600214375139]
We propose a simple sample selection criterion that moves beyond uncertainty.
We show state-of-the-art results and better rates at identifying wrongly predicted samples.
arXiv Detail & Related papers (2020-10-14T09:00:42Z) - Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers.
We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model.
Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
arXiv Detail & Related papers (2020-06-22T21:12:31Z) - Certified Robustness to Label-Flipping Attacks via Randomized Smoothing [105.91827623768724]
Machine learning algorithms are susceptible to data poisoning attacks.
We present a unifying view of randomized smoothing over arbitrary functions.
We propose a new strategy for building classifiers that are pointwise-certifiably robust to general data poisoning attacks.
arXiv Detail & Related papers (2020-02-07T21:28:30Z)
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.