works on
class imbalance 1learning dynamics 1long-tailed classification 1loss functions 1reweighting 1

From the 1 of 5 linked papers with an AI index.

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2026

Beyond Static Costs: Learning-Dynamics Aware Loss Functions for Long-Tailed Classification

Varad Shinde, Nikhil Kumar Shrey, Magesh Rajasekaran +5

The paper introduces a Learning‑Dynamics Aware Loss (LDAL) that continuously adjusts class weights during training based on feature strength, prediction entropy, and inter‑epoch ch…

cs.CV2026★ 5 cited

COMBOOD: A Semiparametric Approach for Detecting Out-of-distribution Data for Image Classification

Magesh Rajasekaran, Md Saiful Islam Sajol, Frej Berglind +2

Identifying out-of-distribution (OOD) data at inference time is crucial for many machine learning applications, especially for automation. We present a novel unsupervised semi-para…