paper-with-me

홈 › Papers

Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors

2022-07-12 · Vivek Narayanaswamy, Yamen Mubarka, Rushil Anirudh, Deepta Rajan, Andreas Spanias, Jayaraman J. Thiagarajan

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.

📄 PDF Abstract BibTeX arXiv:2207.05286

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationOpen Set LearningOut-of-Distribution DetectionOut of Distribution (OOD) DetectionSelf-Driving Cars

Similar Papers 제목 키워드 기반

Outlier Preserving Distribution Mapping Autoencoders

2021-01-01 · Walter Gerych, Elke Rundensteiner, Emmanuel Agu

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 Detection

Versatile Anomaly Detection with Outlier Preserving Distribution Mapping Autoencoders

2019-09-25 · Walter Gerych, Elke Rundensteiner, Emmanuel Agu

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 Detection

Unsupervised Outlier Detection using Memory and Contrastive Learning

2021-07-27 · Ning Huyan, Dou Quan, Xiangrong Zhang, Xuefeng Liang 외

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 Detection

Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery

2017-08-01 · ICML 2017 8 · Mostafa Rahmani, George Atia

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

2015-12-01 · ICCV 2015 12 · Yan Xia, Xudong Cao, Fang Wen, Gang Hua 외

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…