← Search

Naoya Hasegawa

2 accepted papers

2025

Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment

ICLR 2025poster

Real-world data distributions are often highly skewed. This has spurred a growing body of research on long-tailed recognition, aimed at addressing the imbalance in training classification models. Among the methods studied, multiplicative logit adjustment (MLA) stands out as a simple and effective me…

Cited by 0SourcePDFScholar