Metraipolis › archive › dc_92796fb520df

DLC: A Metric-Guided Dynamic Loss Controller for Multi-Objective Training — arXiv:2610.11433

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11433
License (as archived)
CC0-1.0
Archived
2026-10-09T06:30:32.822Z
SHA-256 of the archived text
3bb4f904a2d346c6d082917a5da8be828d8f5803949b4bc1e58733696322c7b6
Stable URL of this page
https://metraipolis.com/documento/dc_92796fb520df

How to cite

DLC: A Metric-Guided Dynamic Loss Controller for Multi-Objective Training — arXiv:2610.11433 — arXiv (en), https://arxiv.org/abs/2610.11433 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_92796fb520df (Metraipolis archive dc_92796fb520df, sha256 3bb4f904a2d346c6d082917a5da8be828d8f5803949b4bc1e58733696322c7b6)
BibTeX
@misc{dc92796fb520df,
  title = {DLC: A Metric-Guided Dynamic Loss Controller for Multi-Objective Training — arXiv:2610.11433},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11433},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_92796fb520df; sha256 3bb4f904a2d346c6d082917a5da8be828d8f5803949b4bc1e58733696322c7b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11433. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.11433 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:55:07.395Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).