Enregistré dans:
Détails bibliographiques
Auteurs principaux: Faye, Bilal, Azzag, Hanane, Lebbah, Mustapha
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.09922
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908724187103232
author Faye, Bilal
Azzag, Hanane
Lebbah, Mustapha
author_facet Faye, Bilal
Azzag, Hanane
Lebbah, Mustapha
contents Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead yet lose fine detail, while retrieval-augmented methods improve efficiency but rely on large memory banks, static similarity models, and rigid infrastructures. We introduce the Prototype Diffusion Model (PDM), which embeds prototype learning into the diffusion process to provide adaptive, memory-free conditioning. Instead of retrieving references, PDM learns compact visual prototypes from clean features via contrastive learning, then aligns noisy representations with semantically relevant patterns during denoising. Experiments demonstrate that PDM sustains high generation quality while lowering computational and storage costs, offering a scalable alternative to retrieval-based conditioning.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09922
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prototype-Guided Diffusion: Visual Conditioning without External Memory
Faye, Bilal
Azzag, Hanane
Lebbah, Mustapha
Machine Learning
Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead yet lose fine detail, while retrieval-augmented methods improve efficiency but rely on large memory banks, static similarity models, and rigid infrastructures. We introduce the Prototype Diffusion Model (PDM), which embeds prototype learning into the diffusion process to provide adaptive, memory-free conditioning. Instead of retrieving references, PDM learns compact visual prototypes from clean features via contrastive learning, then aligns noisy representations with semantically relevant patterns during denoising. Experiments demonstrate that PDM sustains high generation quality while lowering computational and storage costs, offering a scalable alternative to retrieval-based conditioning.
title Prototype-Guided Diffusion: Visual Conditioning without External Memory
topic Machine Learning
url https://arxiv.org/abs/2508.09922