# Generative Classifiers as a Basis for Trustworthy Image Classification

Source: [Generative Classifiers as a Basis for Trustworthy Image Classification](<https://www.sota2.com/research/paper/68fa68d41e209131cea1e70f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:46:52.640Z

Authors: Radek Mackowiak, Lynton Ardizzone, Ullrich K\\"othe, Carsten Rother

Published: 2020-07-29T18:09:48.000Z

## Abstract

With the maturing of deep learning systems, trustworthiness is becoming increasingly important for model assessment. We understand trustworthiness as the combination of explainability and robustness. Generative classifiers (GCs) are a promising class of models that are said to naturally accomplish these qualities. However, this has mostly been demonstrated on simple datasets such as MNIST and CIFAR in the past. In this work, we firstly develop an architecture and training scheme that allows GCs to operate on a more relevant level of complexity for practical computer vision, namely the ImageNet challenge. Secondly, we demonstrate the immense potential of GCs for trustworthy image classification. Explainability and some aspects of robustness are vastly improved compared to feed-forward models, even when the GCs are just applied naively. While not all trustworthiness problems are solved completely, we observe that GCs are a highly promising basis for further algorithms and modifications. We release our trained model for download in the hope that it serves as a starting point for other generative classification tasks, in much the same way as pretrained ResNet architectures do for discriminative classification.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on ImageNet-Sketch](<https://www.sota2.com/research/sota/image-classification-on-imagenet-sketch.md>): Image Classification; ImageNet-Sketch; Top-1 Accuracy: 14.6.

- [Image Classification on ImageNet-R](<https://www.sota2.com/research/sota/image-classification-on-imagenet-r.md>): Image Classification; ImageNet-R; Top-1 Acc: 13.2.

- [Image Classification on ImageNet A](<https://www.sota2.com/research/sota/image-classification-on-imagenet-a.md>): Image Classification; ImageNet A; Top-1 Acc: 3.2.

- [Image Classification on ImageNet V2](<https://www.sota2.com/research/sota/image-classification-on-imagenet-v2.md>): Image Classification; ImageNet V2; Top-1 Acc: 40.9.

- [Image Classification on ObjectNet](<https://www.sota2.com/research/sota/image-classification-on-objectnet.md>): Image Classification; ObjectNet; Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2007.15036>)

[PDF](<https://arxiv.org/pdf/2007.15036.pdf>)