A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification

2020-09-29 · Hichame Yessou, Gencer Sumbul, Begüm Demir

This paper analyzes and compares different deep learning loss functions in the framework of multi-label remote sensing (RS) image scene classification problems. We consider seven loss functions: 1) cross-entropy loss; 2) focal loss; 3) weighted cross-entropy loss; 4) Hamming loss; 5) Huber loss; 6) ranking loss; and 7) sparseMax loss. All the considered loss functions are analyzed for the first time in RS. After a theoretical analysis, an experimental analysis is carried out to compare the considered loss functions in terms of their: 1) overall accuracy; 2) class imbalance awareness (for which the number of samples associated to each class significantly varies); 3) convexibility and differentiability; and 4) learning efficiency (i.e., convergence speed). On the basis of our analysis, some guidelines are derived for a proper selection of a loss function in multi-label RS scene classification problems.

📄 PDF Abstract BibTeX arXiv:2009.13935

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification image-classification Image Classification Remote Sensing Image Classification Scene Classification

Methods 이 논문이 사용한 방법론

Sparsemax Sparsemax is a type of activation/output function similar to the traditional softmax, but able to output sparse probabilities.…

A Comparative Study of Invariance-Aware Loss Functions for Deep Learning-based Gridless Direction-of-Arrival Estimation

2025-03-16 · Kuan-Lin Chen, Bhaskar D. Rao

Covariance matrix reconstruction has been the most widely used guiding objective in gridless direction-of-arrival (DoA) estimation for sparse linear arrays. Many semidefinite programming (SDP)-based methods fall under th…

Deep Learning Direction of Arrival Estimation

Robust Loss Functions under Label Noise for Deep Neural Networks

2017-12-27 · Aritra Ghosh, Himanshu Kumar, P. S. Sastry

In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques p…

Binary Classification Classification General Classification

Loss Functions in Diffusion Models: A Comparative Study

2025-07-02 · Dibyanshu Kumar, Philipp Vaeth, Magda Gregorová arxiv

Diffusion models have emerged as powerful generative models, inspiring extensive research into their underlying mechanisms. One of the key questions in this area is the loss functions these models shall train with. Multi…

Multimodal HIE Lesion Segmentation in Neonates: A Comparative Study of Loss Functions

2025-02-13 · Annayah Usman, Abdul Haseeb, Tahir Syed

Segmentation of Hypoxic-Ischemic Encephalopathy (HIE) lesions in neonatal MRI is a crucial but challenging task due to diffuse multifocal lesions with varying volumes and the limited availability of annotated HIE lesion …

Lesion Segmentation Segmentation

Comparison of Loss Functions for Robust Deep Learning-based Echocardiography Segmentation when Learning with Partially Labelled Data from Multiple Domains

2026-07-06 · Iman Islam, Esther Puyol-Antón, Bram Ruijsink, Andrew J. Reader 외 arxiv

Echocardiography is the first imaging modality used for assessing cardiac function, and accurate segmentation of cardiac structures is essential for deriving biomarkers. However, the development of effective automated se…