paper-with-me

Papers

LuminanceL1Loss: A loss function which measures percieved brightness and colour differences

2023-11-08 · Dominic De Jonge

We introduce LuminanceL1Loss, a novel loss function designed to enhance the performance of image restoration tasks. We demonstrate its superiority over MSE when applied to the Retinexformer, BUIFD and DnCNN architectures. Our proposed LuminanceL1Loss leverages a unique approach by transforming images into grayscale and subsequently computing the MSE loss for both grayscale and color channels. Experimental results demonstrate that this innovative loss function consistently outperforms traditional methods, showcasing its potential in image denoising and other related tasks in image reconstruction. It demonstrates gains up to 4.7dB. The results presented in this study highlight the efficacy of LuminanceL1Loss for various image restoration tasks.

📄 PDF Abstract BibTeX arXiv:2311.04614

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage DenoisingImage ReconstructionImage Restoration

Similar Papers 제목 키워드 기반

Ranking Measures and Loss Functions in Learning to Rank

2009-12-01 · NeurIPS 2009 12 · Wei Chen, Tie-Yan Liu, Yanyan Lan, Zhi-Ming Ma 외

Learning to rank has become an important research topic in machine learning. While most learning-to-rank methods learn the ranking function by minimizing the loss functions, it is the ranking measures (such as NDCG and M…

General ClassificationLearning-To-Rank

A surrogate loss function for optimization of $F_β$ score in binary classification with imbalanced data

2021-04-03 · Namgil Lee, Heejung Yang, Hojin Yoo

The $F_\beta$ score is a commonly used measure of classification performance, which plays crucial roles in classification tasks with imbalanced data sets. However, the $F_\beta$ score cannot be used as a loss function by…

Binary ClassificationClassificationGeneral Classification

Loss Functions and Operators Generated by f-Divergences

2025-01-30 · Vincent Roulet, Tianlin Liu, Nino Vieillard, Michael E. Sander 외

The logistic loss (a.k.a. cross-entropy loss) is one of the most popular loss functions used for multiclass classification. It is also the loss function of choice for next-token prediction in language modeling. It is ass…

Language ModelingLanguage Modelling

CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences -- Version 1

2021-06-17 · Imme Ebert-Uphoff, Ryan Lagerquist, Kyle Hilburn, Yoonjin Lee 외

Neural networks are increasingly used in environmental science applications. Furthermore, neural network models are trained by minimizing a loss function, and it is crucial to choose the loss function very carefully for …

Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures

2017-07-01 · ACL 2017 7 · Iryna Haponchyk, Aless Moschitti, ro

An interesting aspect of structured prediction is the evaluation of an output structure against the gold standard. Especially in the loss-augmented setting, the need of finding the max-violating constraint has severely l…

coreference-resolutionCoreference ResolutionStructured Prediction