A Comparative Study of Machine Learning and Deep Learning for Out-of-Distribution Detection
2026-05-11 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors studied how to detect unusual or unexpected medical images, which is important for trustworthy AI. They compared traditional machine learning (ML) methods with deep learning (DL) on a large set of eye images. Both methods were very accurate, but ML was much faster and used less computing power. This suggests that for simpler image detection tasks, ML can be just as good as DL while being more efficient. Their findings help decide which type of AI to use in real medical applications.
Out-of-distribution detectionDeep learningMachine learningMedical imagingAUROCFundus imagesModel accuracyComputational efficiencyValidation setsLatency
Authors
Jihyeon Baek, Seunghoon Lee, Gitaek Kwon, Doohyun Park
Abstract
Out-of-distribution (OOD) detection is essential for building reliable AI systems, as models that produce outputs for invalid inputs cannot be trusted. Although deep learning (DL) is often assumed to outperform traditional machine learning (ML), medical imaging data are typically acquired under standardized protocols, leading to relatively constrained image variability in OOD detection tasks. This motivates a direct comparison between ML and DL approaches in this setting. The two approaches are evaluated on open datasets comprising over 60,000 fundus and non-fundus images across multiple resolutions. Both approaches achieved an AUROC of 1.000 and accuracies between 0.999 and 1.000 on internal and external validation sets, showing comparable detection performance. The ML approach, however, exhibited substantially lower end-to-end latency while maintaining equivalent accuracy, indicating greater computational efficiency. These results suggest that for OOD detection tasks of limited visual complexity, lightweight ML approaches can achieve DL-level performance with significantly reduced computational cost, supporting practical real-world deployment.