Deep Image Segmentation via Discriminant Feature Learning
For researchers in image segmentation, DDA offers a simple, architecture-agnostic loss that enhances boundary quality without added inference cost, though it is an incremental improvement over existing methods.
The paper introduces Deep Discriminant Analysis (DDA), a loss function that improves segmentation accuracy, boundary sharpness, and model confidence by maximizing between-class variance and minimizing within-class variance. On the DIS5K benchmark, DDA consistently outperforms standard losses across various architectures.
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.