Jul 2026
Beyond Static Costs: Learning-Dynamics Aware Loss Functions for Long-Tailed Classification
Experimental results on multiple benchmark datasets demonstrate that the proposed LDAL approach significantly surpasses state-of-the-art reweighting loss functions, providing an optimal trade-off between accuracy and generalizability.
Varad Shinde, Nikhil Kumar Shrey, Magesh Rajasekaran et al.
· arXiv.org · 0 citations