SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.08618 · 2026

Beyond Toy Benchmarks: A Systematic Evaluation of OOD Detection Methods For Plant Pathology Classification

Devesh Shah

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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. Energy-based fine-tuning performs best across OOD settings, improving detection over the softmax baseline while preserving indistribution accuracy. Analysis shows these gains stem from both a restructuring of the embedding space alongside calibration of the scoring function. We further document practical training instabilities that arise when scaling constrained optimization methods to moderate-sized datasets, findings that are largely absent from existing literature. Our results demonstrate that principled OOD detection is achievable on real-world domain-specific data and that benchmark evaluations alone may not capture the challenges that emerge in practice.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2605.08618")
get_code_for_paper("2605.08618")
have("2605.08618")

Connect an agent — have() is free.