paper-with-me

Papers

Self-Improving Diffusion Models with Synthetic Data

2024-08-29 · Sina AlEMohammad, Ahmed Imtiaz Humayun, Shruti Agarwal, John Collomosse, Richard Baraniuk

The artificial intelligence (AI) world is running out of real data for training increasingly large generative models, resulting in accelerating pressure to train on synthetic data. Unfortunately, training new generative models with synthetic data from current or past generation models creates an autophagous (self-consuming) loop that degrades the quality and/or diversity of the synthetic data in what has been termed model autophagy disorder (MAD) and model collapse. Current thinking around model autophagy recommends that synthetic data is to be avoided for model training lest the system deteriorate into MADness. In this paper, we take a different tack that treats synthetic data differently from real data. Self-IMproving diffusion models with Synthetic data (SIMS) is a new training concept for diffusion models that uses self-synthesized data to provide negative guidance during the generation process to steer a model's generative process away from the non-ideal synthetic data manifold and towards the real data distribution. We demonstrate that SIMS is capable of self-improvement; it establishes new records based on the Fr\'echet inception distance (FID) metric for CIFAR-10 and ImageNet-64 generation and achieves competitive results on FFHQ-64 and ImageNet-512. Moreover, SIMS is, to the best of our knowledge, the first prophylactic generative AI algorithm that can be iteratively trained on self-generated synthetic data without going MAD. As a bonus, SIMS can adjust a diffusion model's synthetic data distribution to match any desired in-domain target distribution to help mitigate biases and ensure fairness.

📄 PDF Abstract BibTeX arXiv:2408.16333

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessImage Generation

Methods 이 논문이 사용한 방법론

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

Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation

2023-09-25 · Quang Nguyen, Truong Vu, Anh Tran, Khoi Nguyen

Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce im…

Dataset GenerationSegmentationSemantic Segmentation

Dataset Diffusion: Diffusion-based Synthetic Data Generation for Pixel-Level Semantic Segmentation

2023-09-21 · NeurIPS 2023 11

Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce im…

DiNO-Diffusion. Scaling Medical Diffusion via Self-Supervised Pre-Training

2024-07-16 · Guillermo Jimenez-Perez, Pedro Osorio, Josef Cersovsky, Javier Montalt-Tordera 외

Diffusion models (DMs) have emerged as powerful foundation models for a variety of tasks, with a large focus in synthetic image generation. However, their requirement of large annotated datasets for training limits their…

AnatomyData AugmentationImage GenerationZero Shot Segmentation

Stabilizing Self-Consuming Diffusion Models with Latent Space Filtering

2025-11-16 · Zhongteng Cai, Yaxuan Wang, Yang Liu, Xueru Zhang arxiv

As synthetic data proliferates across the Internet, it is often reused to train successive generations of generative models. This creates a ``self-consuming loop" that can lead to training instability or \textit{model co…

Principal Component Clustering for Semantic Segmentation in Synthetic Data Generation

2024-06-25 · Felix Stillger, Frederik Hasecke, Tobias Meisen

This technical report outlines our method for generating a synthetic dataset for semantic segmentation using a latent diffusion model. Our approach eliminates the need for additional models specifically trained on segmen…

ClusteringImage SegmentationSegmentationSemantic Segmentation+1