Continual Learning of Diffusion Models with Generative Distillation

• URL: http://arxiv.org/abs/2311.14028v2
• Date: Mon, 20 May 2024 17:08:43 GMT
• Title: Continual Learning of Diffusion Models with Generative Distillation
• Authors: Sergi Masip, Pau Rodriguez, Tinne Tuytelaars, Gido M. van de Ven,
• Abstract summary: Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. In this paper, we propose generative distillation, an approach that distils the entire reverse process of a diffusion model.
• Score: 34.52513912701778
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 would allow for incrementally learning new tasks and accumulating knowledge, thus enabling the reuse of trained models for further learning. One potentially suitable continual learning approach is generative replay, where a copy of a generative model trained on previous tasks produces synthetic data that are interleaved with data from the current task. However, standard generative replay applied to diffusion models results in a catastrophic loss in denoising capabilities. In this paper, we propose generative distillation, an approach that distils the entire reverse process of a diffusion model. We demonstrate that our approach substantially improves the continual learning performance of generative replay with only a modest increase in the computational costs.

Related papers

• Joint Diffusion models in Continual Learning [4.013156524547073]
  We introduce JDCL - a new method for continual learning with generative rehearsal based on joint diffusion models. Generative-replay-based continual learning methods try to mitigate this issue by retraining a model with a combination of new and rehearsal data sampled from a generative model. We show that such shared parametrization, combined with the knowledge distillation technique allows for stable adaptation to new tasks without catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-11-12T22:35:44Z)
• Energy-Based Diffusion Language Models for Text Generation [126.23425882687195]
  Energy-based Diffusion Language Model (EDLM) is an energy-based model operating at the full sequence level for each diffusion step. Our framework offers a 1.3$times$ sampling speedup over existing diffusion models.
  arXiv  Detail & Related papers  (2024-10-28T17:25:56Z)
• Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion Sampling [2.91204440475204]
  Diffusion Probabilistic Models (DPMs) have emerged as a powerful class of deep generative models. They rely on sequential denoising steps during sample generation. We propose a novel method that integrates denoising phases directly into the model's architecture.
  arXiv  Detail & Related papers  (2024-05-31T08:19:44Z)
• Heat Death of Generative Models in Closed-Loop Learning [63.83608300361159]
  We study the learning dynamics of generative models that are fed back their own produced content in addition to their original training dataset. We show that, unless a sufficient amount of external data is introduced at each iteration, any non-trivial temperature leads the model to degenerate.
  arXiv  Detail & Related papers  (2024-04-02T21:51:39Z)
• DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception [78.26734070960886]
  Current perceptive models heavily depend on resource-intensive datasets. We introduce perception-aware loss (P.A. loss) through segmentation, improving both quality and controllability. Our method customizes data augmentation by extracting and utilizing perception-aware attribute (P.A. Attr) during generation.
  arXiv  Detail & Related papers  (2024-03-20T04:58:03Z)
• On the Stability of Iterative Retraining of Generative Models on their own Data [56.153542044045224]
  We study the impact of training generative models on mixed datasets. We first prove the stability of iterative training under the condition that the initial generative models approximate the data distribution well enough. We empirically validate our theory on both synthetic and natural images by iteratively training normalizing flows and state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2023-09-30T16:41:04Z)
• BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping [64.54271680071373]
  Diffusion models have demonstrated excellent potential for generating diverse images. Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few. We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
  arXiv  Detail & Related papers  (2023-06-08T20:30:55Z)
• Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling [69.60713300418467]
  Learning to jump is a general recipe for generative modeling of various types of data. We demonstrate when learning to jump is expected to perform comparably to learning to denoise, and when it is expected to perform better.
  arXiv  Detail & Related papers  (2023-05-28T05:38:28Z)
• Image retrieval outperforms diffusion models on data augmentation [36.559967424331695]
  diffusion models are proposed to augment training datasets for downstream tasks, such as classification. It remains unclear if they generalize enough to improve over directly using the additional data of their pre-training process for augmentation. Personalizing diffusion models towards the target data outperforms simpler prompting strategies. However, using the pre-training data of the diffusion model alone, via a simple nearest-neighbor retrieval procedure, leads to even stronger downstream performance.
  arXiv  Detail & Related papers  (2023-04-20T12:21:30Z)
• Exploring Continual Learning of Diffusion Models [24.061072903897664]
  We evaluate the continual learning (CL) properties of diffusion models. We provide insights into the dynamics of forgetting, which exhibit diverse behavior across diffusion timesteps.
  arXiv  Detail & Related papers  (2023-03-27T15:52:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.