REVIEW 4 cited by
Classification Accuracy Score for Conditional Generative Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Classification Accuracy Score for Conditional Generative Models
read the original abstract
Deep generative models (DGMs) of images are now sufficiently mature that they produce nearly photorealistic samples and obtain scores similar to the data distribution on heuristics such as Frechet Inception Distance (FID). These results, especially on large-scale datasets such as ImageNet, suggest that DGMs are learning the data distribution in a perceptually meaningful space and can be used in downstream tasks. To test this latter hypothesis, we use class-conditional generative models from a number of model classes---variational autoencoders, autoregressive models, and generative adversarial networks (GANs)---to infer the class labels of real data. We perform this inference by training an image classifier using only synthetic data and using the classifier to predict labels on real data. The performance on this task, which we call Classification Accuracy Score (CAS), reveals some surprising results not identified by traditional metrics and constitute our contributions. First, when using a state-of-the-art GAN (BigGAN-deep), Top-1 and Top-5 accuracy decrease by 27.9\% and 41.6\%, respectively, compared to the original data; and conditional generative models from other model classes, such as Vector-Quantized Variational Autoencoder-2 (VQ-VAE-2) and Hierarchical Autoregressive Models (HAMs), substantially outperform GANs on this benchmark. Second, CAS automatically surfaces particular classes for which generative models failed to capture the data distribution, and were previously unknown in the literature. Third, we find traditional GAN metrics such as Inception Score (IS) and FID neither predictive of CAS nor useful when evaluating non-GAN models. Furthermore, in order to facilitate better diagnoses of generative models, we open-source the proposed metric.
Forward citations
Cited by 4 Pith papers
-
Concordia: Self-Improving Synthetic Tables for Federated LLMs
Concordia aligns synthetic table generation with federated validation utility via client-side utility scorers and group-relative policy optimization to improve LLM adaptation on non-IID tabular tasks.
-
Improved Denoising Diffusion Probabilistic Models
Targeted tweaks to DDPMs produce competitive likelihoods and high-quality samples, with learned reverse variances enabling 10x faster sampling and predictable scaling with compute.
-
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
VTAB is a 19-task benchmark that measures representation quality by few-shot adaptation performance across diverse vision domains, with a controlled large-scale comparison of popular pretraining methods.
-
Concordia: Self-Improving Synthetic Tables for Federated LLMs
Concordia aligns synthetic table generation with federated validation utility via client-level LoRA training, utility scorers, and outer GRPO refinement to boost performance over static synthetic baselines.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.