paper-with-me

Papers

Exploring Continual Learning of Diffusion Models

2023-03-27 · Michał Zając, Kamil Deja, Anna Kuzina, Jakub M. Tomczak, Tomasz Trzciński, Florian Shkurti, Piotr Miłoś

Diffusion models have achieved remarkable success in generating high-quality images thanks to their novel training procedures applied to unprecedented amounts of data. However, training a diffusion model from scratch is computationally expensive. This highlights the need to investigate the possibility of training these models iteratively, reusing computation while the data distribution changes. In this study, we take the first step in this direction and evaluate the continual learning (CL) properties of diffusion models. We begin by benchmarking the most common CL methods applied to Denoising Diffusion Probabilistic Models (DDPMs), where we note the strong performance of the experience replay with the reduced rehearsal coefficient. Furthermore, we provide insights into the dynamics of forgetting, which exhibit diverse behavior across diffusion timesteps. We also uncover certain pitfalls of using the bits-per-dimension metric for evaluating CL.

📄 PDF Abstract BibTeX arXiv:2303.15342

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingContinual LearningDenoising

Methods 이 논문이 사용한 방법론

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA

2023-04-12 · James Seale Smith, Yen-Chang Hsu, Lingyu Zhang, Ting Hua 외

Recent works demonstrate a remarkable ability to customize text-to-image diffusion models while only providing a few example images. What happens if you try to customize such models using multiple, fine-grained concepts …

Continual Learningimage-classificationImage Classification

Mining Your Own Secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models

2024-10-01 · Saurav Jha, Shiqi Yang, Masato Ishii, Mengjie Zhao 외

Personalized text-to-image diffusion models have grown popular for their ability to efficiently acquire a new concept from user-defined text descriptions and a few images. However, in the real world, a user may wish to p…

Continual Learning

Continual Learning of Diffusion Models with Generative Distillation

2023-11-23 · Sergi Masip, Pau Rodriguez, Tinne Tuytelaars, Gido M. van de Ven

Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning wou…

Continual LearningDenoisingImage Generation

Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models

2026-05-27 · Ken Takeda, Masafumi Oizumi, Ryo Karakida arxiv

Generative models, including diffusion models, are increasingly used as foundation models and adapted through sequential fine-tuning, making continual learning an essential problem setting. However, continual learning in…

Continual Learning

One-for-More: Continual Diffusion Model for Anomaly Detection

2025-02-27 · CVPR 2025 1 · Xiaofan Li, Xin Tan, Zhuo Chen, Zhizhong Zhang 외

With the rise of generative models, there is a growing interest in unifying all tasks within a generative framework. Anomaly detection methods also fall into this scope and utilize diffusion models to generate or reconst…

Anomaly Detectioncontinual anomaly detectionContinual LearningHallucination