# Diff-CA: Separating Common and Salient Factors with Diffusion Models Source: [Diff-CA: Separating Common and Salient Factors with Diffusion Models]() Collection index: [llms.txt]() Data updated: 2026-06-06T05:00:11.965Z Authors: Micha\\"el Soumm, Alexandre Fournier Montgieux, Yunlong He, Pietro Gori, Alasdair Newson Published: 2026-06-04T13:07:18.000Z ## Abstract Contrastive Analysis aims to separate factors that are common between two data distributions from those that are salient to only one of them. Existing contrastive methods are based on generative models (e.g., VAEs or GANs) that often suffer from limited reconstruction and image quality, which hampers effective latent factor separation and limits their applicability to high-fidelity image generation and edition. We propose a novel conditioning framework for diffusion models that enables contrastive decomposition without compromising generation quality. We first train a prompt-free, image-conditioned diffusion model, and then learn to decompose the conditioning into a common and a salient factor, using weak supervision. We prove that the additive contrastive factorization, commonly assumed in prior work, is identifiable under mild conditions. This factorization enables targeted operations by swapping or interpolating only the salient factor. ## 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 Reconstruction on FFHQ (SSIM, LPIPS, ID-Sim)](): Image Reconstruction; FFHQ; SSIM: 61. - [Salient Attribute Swapping on FFHQ Glasses Attribute](): Salient Attribute Swapping; FFHQ Glasses Attribute; Accuracy: 94.5. ## Original sources and implementation [Original paper]() [PDF]()