Score-Based Generative Classifiers
This work addresses the challenge of applying generative models to classification tasks for natural images, showing progress in accuracy but highlighting limitations in robustness, which is incremental as it builds on prior generative classifier research.
The authors tackled the problem of using score-based generative models for classification on natural images, achieving state-of-the-art classification accuracy for generative classifiers on CIFAR-10 with competitive likelihood values, but found they offer only slight or no improvement in robustness to out-of-distribution tasks and adversarial perturbations compared to discriminative baselines.
The tremendous success of generative models in recent years raises the question whether they can also be used to perform classification. Generative models have been used as adversarially robust classifiers on simple datasets such as MNIST, but this robustness has not been observed on more complex datasets like CIFAR-10. Additionally, on natural image datasets, previous results have suggested a trade-off between the likelihood of the data and classification accuracy. In this work, we investigate score-based generative models as classifiers for natural images. We show that these models not only obtain competitive likelihood values but simultaneously achieve state-of-the-art classification accuracy for generative classifiers on CIFAR-10. Nevertheless, we find that these models are only slightly, if at all, more robust than discriminative baseline models on out-of-distribution tasks based on common image corruptions. Similarly and contrary to prior results, we find that score-based are prone to worst-case distribution shifts in the form of adversarial perturbations. Our work highlights that score-based generative models are closing the gap in classification accuracy compared to standard discriminative models. While they do not yet deliver on the promise of adversarial and out-of-domain robustness, they provide a different approach to classification that warrants further research.