paper-with-me

Papers

Understanding Classifiers with Generative Models

2021-01-01 · Laëtitia Shao, Yang song, Stefano Ermon

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Two-sample testing

Similar Papers 제목 키워드 기반

On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding

2026-03-03 · Zhanzhong Pang, Dibyadip Chatterjee, Fadime Sener, Angela Yao arxiv

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 Understanding

Towards Understanding the Generative Capability of Adversarially Robust Classifiers

2021-08-20 · ICCV 2021 10 · Yao Zhu, Jiacheng Ma, Jiacheng Sun, Zewei Chen 외

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 Generation

Revisiting Autoregressive Models for Generative Image Classification

2026-03-19 · Ilia Sudakov, Artem Babenko, Dmitry Baranchuk arxiv

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 Classification

Your VAR Model is Secretly an Efficient and Explainable Generative Classifier

2025-10-14 · Yi-Chung Chen, David I. Inouye, Jing Gao arxiv

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 learning

A Unified View of cGANs with and without Classifiers

2021-11-01 · NeurIPS 2021 12 · Si-An Chen, Chun-Liang Li, Hsuan-Tien Lin

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…