DLC: A Metric-Guided Dynamic Loss Controller for Multi-Objective Training

Key points

• 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.1
• 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.1
• 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.1
• 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.1

Sources (1)

• [1]DLC: A Metric-Guided Dynamic Loss Controller for Multi-Objective Training
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 07:56 AM

  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.

Extractive summary: sentences quoted from the sources.