Publication

Deep image segmentation via discriminant feature learning

Conference Article

Conference

IEEE International Conference on Image Processing (ICIP)

Edition

2026

Doc link

http://dx.doi.org/10.1109/ICIP61757.2026.11630079

File

Download the digital copy of the doc pdf document

Abstract

Accurate image segmentation remains challenging, particularly in generating sharp, confident boundaries. While modern architectures have advanced the field, many of them still rely on standard loss functions like Cross-Entropy and Dice, which often neglect the discriminative structure of learned features, leading to inaccurate boundaries. This work introduces Deep Discriminant Analysis (DDA), a differentiable, architecture-agnostic loss function that embeds classical discriminant principles for network training. DDA explicitly maximizes between-class variance while minimizing within-class one, promoting compact and separable feature distributions without increasing inference cost. Evaluations on the DIS5K benchmark demonstrate that DDA consistently improves segmentation accuracy, boundary sharpness, and model confidence across various architectures. Our results show that integrating discriminant analysis offers a simple, effective path for building more robust segmentation models.

Categories

computer vision, optimisation.

Author keywords

Image segmentation, discriminant analysis, deep feature learning, loss optimization.

Scientific reference

A. Sztamborski, R. Pérez and A. Agudo. Deep image segmentation via discriminant feature learning, 2026 IEEE International Conference on Image Processing, 2026, Tampere, Finland.