Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors
We focus on the problem of producing well-calibrated out-of-distribution (OOD) detectors, in order to enable safe deployment of medical image classifiers. Motivated by the difficulty of curating suitable calibration datasets, synthetic augmentations have become highly prevalent for inlier/outlier specification. While there have been rapid advances in data augmentation techniques, this paper makes a striking finding that the space in which the inliers and outliers are synthesized, in addition to the type of augmentation, plays a critical role in calibrating OOD detectors. Using the popular energy-based OOD detection framework, we find that the optimal protocol is to synthesize latent-space inliers along with diverse pixel-space outliers. Based on empirical studies with multiple medical imaging benchmarks, we demonstrate that our approach consistently leads to superior OOD detection ($15\% - 35\%$ in AUROC) over the state-of-the-art in a variety of open-set recognition settings.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationOpen Set LearningOut-of-Distribution DetectionOut of Distribution (OOD) DetectionSelf-Driving CarsSimilar Papers 제목 키워드 기반
Outlier Preserving Distribution Mapping Autoencoders
State-of-the-art deep outlier detection methods map data into a latent space with the aim of having outliers far away from inliers in this space. Unfortunately, this often fails as the divergence penalty they adopt pus…
Outlier DetectionVersatile Anomaly Detection with Outlier Preserving Distribution Mapping Autoencoders
State-of-the-art deep learning methods for outlier detection make the assumption that anomalies will appear far away from inlier data in the latent space produced by distribution mapping deep networks. However, this ass…
Anomaly DetectionOutlier DetectionUnsupervised Outlier Detection using Memory and Contrastive Learning
Outlier detection is one of the most important processes taken to create good, reliable data in machine learning. The most methods of outlier detection leverage an auxiliary reconstruction task by assuming that outliers …
Contrastive LearningOutlier DetectionCoherence Pursuit: Fast, Simple, and Robust Subspace Recovery
This paper presents a remarkably simple, yet powerful, algorithm for robust Principal Component Analysis (PCA). In the proposed approach, an outlier is set apart from an inlier by comparing their coherence with the …
Learning Discriminative Reconstructions for Unsupervised Outlier Removal
We study the problem of automatically removing outliers from noisy data, with application for removing outlier images from an image collection. We address this problem by utilizing the reconstruction errors of an autoenc…