Understanding Classifiers with Generative Models
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 that we test against different sources of classification mistakes: 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Two-sample testingSimilar Papers 제목 키워드 기반
On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding
Multimodal Large Language Models (MLLMs) have advanced open-world action understanding and can be adapted as generative classifiers for closed-set settings by autoregressively generating action labels as text. However, t…
Action UnderstandingTowards Understanding the Generative Capability of Adversarially Robust Classifiers
Recently, some works found an interesting phenomenon that adversarially robust classifiers can generate good images comparable to generative models. We investigate this phenomenon from an energy perspective and provide a…
Image GenerationRevisiting Autoregressive Models for Generative Image Classification
Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In t…
Image ClassificationYour VAR Model is Secretly an Efficient and Explainable Generative Classifier
Generative classifiers, which leverage conditional generative models for classification, have recently demonstrated desirable properties such as robustness to distribution shifts. However, recent progress in this area ha…
class-incremental learningA Unified View of cGANs with and without Classifiers
Conditional Generative Adversarial Networks (cGANs) are implicit generative models which allow to sample from class-conditional distributions. Existing cGANs are based on a wide range of different discriminator designs a…