AI RESEARCH
Beyond Toy Benchmarks: A Systematic Evaluation of OOD Detection Methods For Plant Pathology Classification
arXiv CS.LG
•
ArXi:2605.08618v1 Announce Type: cross Out-of-distribution (OOD) detection is essential for reliable deployment of deep learning systems, yet the majority of existing methods are evaluated on small, visually homogeneous benchmarks. In this work, we study six OOD detection methods spanning post-hoc scoring, auxiliary objectives, energy-based models, and constrained optimization on the Plant Pathology 2021 dataset, a fine-grained task with natural distribution shifts.