SOURCE-LINKED INTELLIGENCE

Difficulty-Aware Sample Allocation for Adaptive Data Augmentation in Semantic Segmentation

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Data augmentation is a standard component of modern semantic segmentation pipelines, but most augmentation techniques allocate transformations uniformly across training samples or adapt to a single difficulty signal such as loss. This ignores the fact that segmentation difficulty is multi-factorial, since ambiguous predictions, persistent optimization errors, rare classes, and complex object boundaries can each make a sample informative in different ways. This paper introduces Difficulty-Aware Sample Allocation (DASA), an architecture-agnostic framework that assigns stronger augmentation to sa

Read original source ↗ Open in workspace

recordType

paper

region

Global