UniFL: Improve Latent Diffusion Model via Unified Feedback Learning

• URL: http://arxiv.org/abs/2404.05595v3
• Date: Tue, 26 Nov 2024 12:12:50 GMT
• Title: UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
• Authors: Jiacheng Zhang, Jie Wu, Yuxi Ren, Xin Xia, Huafeng Kuang, Pan Xie, Jiashi Li, Xuefeng Xiao, Weilin Huang, Shilei Wen, Lean Fu, Guanbin Li,
• Abstract summary: We present UniFL, a unified framework that leverages feedback learning to enhance diffusion models comprehensively. UniFL consists of three key components: perceptual feedback learning, which enhances visual quality; decoupled feedback learning, which improves aesthetic appeal; and adversarial feedback learning, which accelerates inference. In-depth experiments and extensive user studies validate the superior performance of our method in enhancing generation quality and inference acceleration.
• Score: 61.66652875042845
• License:
• Abstract: Latent diffusion models (LDM) have revolutionized text-to-image generation, leading to the proliferation of various advanced models and diverse downstream applications. However, despite these significant advancements, current diffusion models still suffer from several limitations, including inferior visual quality, inadequate aesthetic appeal, and inefficient inference, without a comprehensive solution in sight. To address these challenges, we present UniFL, a unified framework that leverages feedback learning to enhance diffusion models comprehensively. UniFL stands out as a universal, effective, and generalizable solution applicable to various diffusion models, such as SD1.5 and SDXL. Notably, UniFL consists of three key components: perceptual feedback learning, which enhances visual quality; decoupled feedback learning, which improves aesthetic appeal; and adversarial feedback learning, which accelerates inference. In-depth experiments and extensive user studies validate the superior performance of our method in enhancing generation quality and inference acceleration. For instance, UniFL surpasses ImageReward by 17% user preference in terms of generation quality and outperforms LCM and SDXL Turbo by 57% and 20% general preference with 4-step inference.

Related papers

• GeFL: Model-Agnostic Federated Learning with Generative Models [3.4546761246181696]
  Federated learning (FL) is a promising paradigm in distributed learning while preserving the privacy of users. We propose Generative Model-Aided Federated Learning (GeFL), incorporating a generative model that aggregates global knowledge across users of heterogeneous models. We empirically demonstrate the consistent performance gains of GeFL-F, while demonstrating better privacy preservation and robustness to a large number of clients.
  arXiv  Detail & Related papers  (2024-12-24T14:39:47Z)
• Distillation-Free One-Step Diffusion for Real-World Image Super-Resolution [81.81748032199813]
  We propose a Distillation-Free One-Step Diffusion model. Specifically, we propose a noise-aware discriminator (NAD) to participate in adversarial training. We improve the perceptual loss with edge-aware DISTS (EA-DISTS) to enhance the model's ability to generate fine details.
  arXiv  Detail & Related papers  (2024-10-05T16:41:36Z)
• DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
  We propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder. DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
  arXiv  Detail & Related papers  (2024-05-24T05:46:04Z)
• Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memory [27.651921957220004]
  We introduce a novel data-free federated class incremental learning framework with diffusion-based generative memory (DFedDGM) We design a new balanced sampler to help train the diffusion models to alleviate the common non-IID problem in FL. We also introduce an entropy-based sample filtering technique from an information theory perspective to enhance the quality of generative samples.
  arXiv  Detail & Related papers  (2024-05-22T20:59:18Z)
• Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation [59.184980778643464]
  Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI) In this paper, we introduce an innovative technique called self-play fine-tuning for diffusion models (SPIN-Diffusion) Our approach offers an alternative to conventional supervised fine-tuning and RL strategies, significantly improving both model performance and alignment.
  arXiv  Detail & Related papers  (2024-02-15T18:59:18Z)
• LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement [118.83316133601319]
  Current deep learning methods for low-light image enhancement (LLIE) typically rely on pixel-wise mapping learned from paired data. We propose a degradation-aware learning scheme for LLIE using diffusion models, which effectively integrates degradation and image priors into the diffusion process.
  arXiv  Detail & Related papers  (2023-07-27T07:22:51Z)
• Training Diffusion Models with Reinforcement Learning [82.29328477109826]
  Diffusion models are trained with an approximation to the log-likelihood objective. In this paper, we investigate reinforcement learning methods for directly optimizing diffusion models for downstream objectives. We describe how posing denoising as a multi-step decision-making problem enables a class of policy gradient algorithms.
  arXiv  Detail & Related papers  (2023-05-22T17:57:41Z)
• Learning Enhancement From Degradation: A Diffusion Model For Fundus Image Enhancement [21.91300560770087]
  We introduce a novel diffusion model based framework, named Learning Enhancement from Degradation (LED) LED learns degradation mappings from unpaired high-quality to low-quality images. LED is able to output enhancement results that maintain clinically important features with better clarity.
  arXiv  Detail & Related papers  (2023-03-08T14:14:49Z)

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.