Data Invariants to Understand Unsupervised Out-of-Distribution Detection

Doorenbos, Lars; Sznitman, Raphael; Márquez-Neila, Pablo

doi:10.1007/978-3-031-19821-2_8

Cited by 5 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiments revealed that the benefits of MahaAD observed for a variety of scenarios on 2D images [ 16 ] translate well to temporal iiOCT scans with high levels of noise and limited lateral view. Another benefit is its computational efficiency, allowing it to cope with high-frequency A-scan acquisition with minimal latency.…”

Section: Discussionmentioning

confidence: 99%

“…In this context, we leverage the MahaAD method proposed by Rippel et al [ 14 ] to learn the appearance of M-scans in the training dataset and detect when novel M-scans are too far from the training distribution to be safely processed by r . We select this model as it has been shown to be highly effective in a large number of cases while being interpretable and computationally lean [ 16 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised out-of-distribution detection for safer robotically guided retinal microsurgery

et al. 2023

Self Cite

View full text Add to dashboard Cite

Purpose A fundamental problem in designing safe machine learning systems is identifying when samples presented to a deployed model differ from those observed at training time. Detecting so-called out-of-distribution (OoD) samples is crucial in safety-critical applications such as robotically guided retinal microsurgery, where distances between the instrument and the retina are derived from sequences of 1D images that are acquired by an instrument-integrated optical coherence tomography (iiOCT) probe. Methods This work investigates the feasibility of using an OoD detector to identify when images from the iiOCT probe are inappropriate for subsequent machine learning-based distance estimation. We show how a simple OoD detector based on the Mahalanobis distance can successfully reject corrupted samples coming from real-world ex vivo porcine eyes. Results Our results demonstrate that the proposed approach can successfully detect OoD samples and help maintain the performance of the downstream task within reasonable levels. MahaAD outperformed a supervised approach trained on the same kind of corruptions and achieved the best performance in detecting OoD cases from a collection of iiOCT samples with real-world corruptions. Conclusion The results indicate that detecting corrupted iiOCT data through OoD detection is feasible and does not need prior knowledge of possible corruptions. Consequently, MahaAD could aid in ensuring patient safety during robotically guided microsurgery by preventing deployed prediction models from estimating distances that put the patient at risk.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Unsupervised out-of-distribution detection for safer robotically guided retinal microsurgery

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…To tackle these challenges, a transformative approach has emerged, wherein anomaly detection is reimagined as an out-of-distribution (OOD) problem [6][7][8]. Unsupervised anomaly detection models are trained using datasets devoid of anomalies, referred to as anomaly-free datasets [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Anomaly Detection Models for Industrial Applications through SVM-Based False Positive Classification

Qiu,

Shi,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Unsupervised anomaly detection models are crucial for the efficiency of industrial applications. However, frequent false alarms hinder the widespread adoption of unsupervised anomaly detection, especially in fault detection tasks. To this end, our research delves into the dependence of false alarms on the baseline anomaly detector by analyzing the high-response regions in anomaly maps. We introduce an SVM-based false positive classifier as a post-processing module, which identifies false alarms from positive predictions at the object level. Moreover, we devise a sample synthesis strategy that generates synthetic false positives from the trained baseline detector while producing synthetic defect patch features from fuzzy domain knowledge. Following comprehensive evaluations, we showcase substantial performance enhancements in two advanced out-of-distribution anomaly detection models, Cflow and Fastflow, across image and pixel-level anomaly detection performance metrics. Substantive improvements are observed in two distinct industrial applications, with notable instances of elevating the image-level F1-score from 46.15% to 78.26% in optimal scenarios and boosting pixel-level AUROC from 72.36% to 94.74%.

show abstract