Pith. sign in

REVIEW 2 cited by

Analyzing Bias in Diffusion-based Face Generation 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

arxiv 2305.06402 v1 pith:YJAZTNSD submitted 2023-05-10 cs.CV

classification cs.CV
keywords modelsbiasgenerationattributesdiffusionfaceacrossapplications
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Diffusion models are becoming increasingly popular in synthetic data generation and image editing applications. However, these models can amplify existing biases and propagate them to downstream applications. Therefore, it is crucial to understand the sources of bias in their outputs. In this paper, we investigate the presence of bias in diffusion-based face generation models with respect to attributes such as gender, race, and age. Moreover, we examine how dataset size affects the attribute composition and perceptual quality of both diffusion and Generative Adversarial Network (GAN) based face generation models across various attribute classes. Our findings suggest that diffusion models tend to worsen distribution bias in the training data for various attributes, which is heavily influenced by the size of the dataset. Conversely, GAN models trained on balanced datasets with a larger number of samples show less bias across different attributes.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Palette Aligned Image Diffusion

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Palette-Adapter conditions text-to-image diffusion on a sparse color palette treated as a histogram, with entropy and distance controls and a negative-color guidance mechanism.

  2. Training-Free Debiasing of Diffusion Models via CLIP-Guided Denoising Optimization

    cs.CV 2026-07 unverdicted novelty 5.0 of 10

    TES applies early global alignment then iterative CLIP-guided refinement to text embeddings in Stable Diffusion to mitigate bias while preserving quality.

Pith tools