Diffusion Fuzzy System: Fuzzy Rule Guided Latent Multi-Path Diffusion Modeling

2025-12-01

AI Summary

Diffusion models suffer from feature conflicts and high computational overhead when generating images with heterogeneous features due to insufficient coordination among parallel generation paths. To address this, we propose a fuzzy rule-guided latent multi-path diffusion model. First, we design a fuzzy rule chain reasoning mechanism to enable dynamic inter-path coordination during generation. Second, we introduce a fuzzy-membership-driven latent space compression strategy that reduces redundant computation while enhancing modeling capacity for heterogeneous features. Crucially, the model jointly learns feature classification and performs efficient cooperative generation within a unified latent space. Experiments on LSUN Bedroom, LSUN Church, and MS COCO demonstrate improved training stability and faster convergence. Our method achieves superior FID and CLIP Score compared to state-of-the-art approaches, significantly advancing both image fidelity and text–image alignment performance.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Diffusion models have emerged as a leading technique for generating images due to their ability to create high-resolution and realistic images. Despite their strong performance, diffusion models still struggle in managing image collections with significant feature differences. They often fail to capture complex features and produce conflicting results. Research has attempted to address this issue by learning different regions of an image through multiple diffusion paths and then combining them. However, this approach leads to inefficient coordination among multiple paths and high computational costs. To tackle these issues, this paper presents a Diffusion Fuzzy System (DFS), a latent-space multi-path diffusion model guided by fuzzy rules. DFS offers several advantages. First, unlike traditional multi-path diffusion methods, DFS uses multiple diffusion paths, each dedicated to learning a specific class of image features. By assigning each path to a different feature type, DFS overcomes the limitations of multi-path models in capturing heterogeneous image features. Second, DFS employs rule-chain-based reasoning to dynamically steer the diffusion process and enable efficient coordination among multiple paths. Finally, DFS introduces a fuzzy membership-based latent-space compression mechanism to reduce the computational costs of multi-path diffusion effectively. We tested our method on three public datasets: LSUN Bedroom, LSUN Church, and MS COCO. The results show that DFS achieves more stable training and faster convergence than existing single-path and multi-path diffusion models. Additionally, DFS surpasses baseline models in both image quality and alignment between text and images, and also shows improved accuracy when comparing generated images to target references.

Problem

• Manages image collections with significant feature differences
• Reduces inefficient coordination among multiple diffusion paths
• Lowers computational costs in multi-path diffusion modeling

Innovation

• Multiple diffusion paths for specific feature classes
• Rule-chain reasoning for dynamic diffusion coordination
• Fuzzy membership-based latent-space compression for efficiency