DLC：一种用于多目标训练的度量引导动态损失控制器
DLC: A Metric-Guided Dynamic Loss Controller for Multi-Objective Training
浏览论文内容
中文总结 AI 辅助
本文提出DLC这一即插即用的动态损失控制器，用于多目标图像恢复，通过LLM基于度量动态调整损失权重，在低光增强、去雨、超分辨率等任务中引导模型达到平衡工作点。
中文摘要 AI 辅助
本文提出了一种用于多目标图像恢复的度量引导动态损失控制器（DLC）。传统图像恢复流水线通常采用多个损失的固定加权组合进行训练，在优化过程中不会改变保真度、感知相似度和无参考质量的相对重要性。DLC是一种与架构和损失项无关的训练时控制器：它不修改恢复架构，也不引入新的可微损失项，而是动态重新加权现有训练损失。训练期间，DLC会定期在一个小型固定反馈子集上评估当前模型，并利用得到的质量度量通过基于大语言模型（LLM）的控制器更新损失权重向量。由于DLC作用于现有损失项而非特定任务架构，相同的控制器公式可应用于不同的图像恢复训练流水线。我们在三个恢复领域（低光图像增强、去雨、真实场景超分辨率）上评估DLC，同时使用参考型和无参考型质量度量。在这些设置中，DLC在优化过程中考虑依赖于度量的权衡，引导训练达到保真度与感知质量之间的平衡工作点。结果表明，DLC可将模型推向不同恢复领域中更有利的工作点，支持其作为多目标图像恢复的实用即插即用控制器的作用。
英文摘要
In this paper, we introduce a metric-guided dynamic loss controller (DLC) for multi-objective image restoration. Conventional image restoration pipelines usually train with a fixed weighted combination of multiple losses, without changing the relative importance of fidelity, perceptual similarity, and no-reference quality during optimization. DLC is an architecture- and loss-term-agnostic training-time controller: it does not modify the restoration architecture or introduce new differentiable loss terms, but dynamically reweights the existing training losses. During training, DLC periodically evaluates the current model on a small fixed feedback subset and uses the resulting quality metrics to update the loss-weight vector through an LLM-based controller. Because DLC operates on existing loss terms rather than task-specific architectures, the same controller formulation can be instantiated across diverse image restoration training pipelines. We evaluate DLC on three restoration domains: low-light image enhancement, deraining, and real-world super-resolution, using both reference-based and no-reference quality metrics. Across these settings, DLC considers metric-dependent trade-offs during optimization and guides training toward balanced operating points across fidelity and perceptual quality. The results show that DLC can move models toward more favorable operating points across different restoration domains, supporting its role as a practical plug-in controller for multi-objective image restoration.
发表机构
- Kyungpook National University（庆北国立大学）
机构由 AI 辅助整理，请以论文原文为准。
