Long-tail learning via logit adjustment

AK Menon, S Jayasumana, AS Rawat, H Jain… - ar** with label shift via distributionally robust optimisation
J Zhang, A Menon, A Veit, S Bhojanapalli… - arxiv preprint arxiv …, 2020 - arxiv.org
The label shift problem refers to the supervised learning setting where the train and test
label distributions do not match. Existing work addressing label shift usually assumes …

Risk-adaptive approaches to stochastic optimization: A survey

JO Royset - SIAM Review, 2025 - SIAM
Uncertainty is prevalent in engineering design and data-driven problems and, more broadly,
in decision making. Due to inherent risk-averseness and ambiguity about assumptions, it is …

Bayesian nonparametric submodular video partition for robust anomaly detection

H Sapkota, Q Yu - Proceedings of the IEEE/CVF conference …, 2022 - openaccess.thecvf.com
Multiple-instance learning (MIL) provides an effective way to tackle the video anomaly
detection problem by modeling it as a weakly supervised problem as the labels are usually …