Work

Mask-Aware Cropping: Mitigating Mask Imbalance in Segmentation Tasks

Year: 2025

Type: conference-paper

Abstract: Data imbalance can take various forms, such as uneven class distributions in the dataset.Solutions like data augmentation, sampling techniques and weighted loss functions are commonly used to address this issue.However, in segmentation tasks, an additional type of imbalance may occur at the pixel-level, with most of them belonging to the background class.This work introduces Mask-Aware Cropping (MAC), a technique to reduce pixel-level imbalance by cropping image regions containing key information about the minority class.

Source: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)

DOI: 10.14428/esann/2025.es2025-3

Authors: Robin Ghyselinck, Valentin Delchevalerie, Benoit Frénay, Bruno Dumas

Institution: University of Namur

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Reduced inequalities

Open Access status: bronze

OpenAlex ID: W4409455412

FWCI:

Cites:

Cited by:

Related to: 10