Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits

2026-02-17

AI Summary

This work proposes a unified coupled diffusion framework that jointly models the distributions of input signals and classifier logits, addressing the limitations of traditional pipeline approaches that separately handle signal enhancement and classification in noisy environments. By enabling bidirectional mutual guidance, the framework achieves synergistic optimization: enhanced signals improve classification accuracy, while logits guide the reconstruction process to focus on discriminative manifolds. Notably, the method requires no retraining of the classifier and is applicable across diverse tasks such as image classification and speech recognition. Experimental results demonstrate consistent and significant performance gains over conventional sequential enhancement strategies under various noise conditions, yielding more robust and flexible system performance.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Robust classification in noisy environments remains a fundamental challenge in machine learning. Standard approaches typically treat signal enhancement and classification as separate, sequential stages: first enhancing the signal and then applying a classifier. This approach fails to leverage the semantic information in the classifier's output during denoising. In this work, we propose a general, domain-agnostic framework that integrates two interacting diffusion models: one operating on the input signal and the other on the classifier's output logits, without requiring any retraining or fine-tuning of the classifier. This coupled formulation enables mutual guidance, where the enhancing signal refines the class estimation and, conversely, the evolving class logits guide the signal reconstruction towards discriminative regions of the manifold. We introduce three strategies to effectively model the joint distribution of the input and the logit. We evaluated our joint enhancement method for image classification and automatic speech recognition. The proposed framework surpasses traditional sequential enhancement baselines, delivering robust and flexible improvements in classification accuracy under diverse noise conditions.

Problem

• robust classification
• noisy environments
• signal enhancement
• joint modeling
• semantic guidance

Innovation

• coupled diffusion models
• joint enhancement and classification
• logits-guided denoising
• domain-agnostic framework
• mutual guidance