AI RESEARCH
When Labels Have Structure: Improving Image Classification with Hierarchy-Aware Cross-Entropy
arXiv CS.LG
•
ArXi:2605.06274v1 Announce Type: new Standard cross-entropy is the default classification loss across virtually all of machine learning, yet it treats all misclassifications equally, ignoring the semantic distances that a class hierarchy encodes. We propose Hierarchy-Aware Cross-Entropy (HACE), a drop-in replacement for standard cross-entropy that incorporates a known class hierarchy directly into the loss.