ATOM: Robustifying Out-of-Distribution Detection Using Outlier Mining

Chen, Jiefeng; Li, Yixuan; Wu, Xi; Liang, Yingyu; Jha, Somesh

doi:10.1007/978-3-030-86523-8_26

Cited by 58 publications

(31 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method can be categorized as a distance-based OOD detection method by exploiting the hyperspherical embedding space. While some works assume access to auxiliary outlier datasets during training [3,13,30,36], our method does not rely on any external information and is hence more generally applicable and flexible.…”

Section: Related Workmentioning

confidence: 99%

CIDER: Exploiting Hyperspherical Embeddings for Out-of-Distribution Detection

Yifei¹,

Sun²,

Dia³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Out-of-distribution (OOD) detection is a critical task for reliable machine learning. Recent advances in representation learning give rise to developments in distance-based OOD detection, where testing samples are detected as OOD if they are relatively far away from the centroids or prototypes of in-distribution (ID) classes. However, prior methods directly take off-theshelf loss functions that suffice for classifying ID samples, but are not optimally designed for OOD detection. In this paper, we propose CIDER, a simple and effective representation learning framework by exploiting hyperspherical embeddings for OOD detection. CIDER jointly optimizes two losses to promote strong ID-OOD separability: (1) a dispersion loss that promotes large angular distances among different class prototypes, and (2) a compactness loss that encourages samples to be close to their class prototypes. We show that CIDER is effective under various settings and establishes state-of-the-art performance. On a hard OOD detection task CIFAR-100 vs. CIFAR-10, our method substantially improves the AUROC by 14.20% compared to the embeddings learned by the cross-entropy loss.

show abstract

Section: Related Workmentioning

confidence: 99%

CIDER: Exploiting Hyperspherical Embeddings for Out-of-Distribution Detection

Yifei¹,

Sun²,

Dia³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our general framework can be applied to these existing OOD detection methods by choosing a suitable intermediate layer for concept-based interpretation 6 . To further improve the OOD uncertainty estimation, several works attempt to finetune the DNN classifier using auxiliary OOD training data [4,42,8]. Complementary to these, our work is a post-hoc method that aims to explain an already-trained DNN model and its paired OOD detector.…”

Section: Concept-based Explanations For Ood Detectorsmentioning

confidence: 99%

“…Recently, the problem of learning OOD detectors with better performance is receiving increased attention [7,6,5,8]. However, the related problem of explaining the decisions of an OOD detector has remained largely unexplored.…”

Section: Introductionmentioning

confidence: 99%

Concept-based Explanations for Out-Of-Distribution Detectors

Choi¹,

Raghuram²,

Feng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Out-of-distribution (OOD) detection plays a crucial role in ensuring the safe deployment of deep neural network (DNN) classifiers. While a myriad of methods have focused on improving the performance of OOD detectors, a critical gap remains in interpreting their decisions. We help bridge this gap by providing explanations for OOD detectors based on learned high-level concepts. We first propose two new metrics for assessing the effectiveness of a particular set of concepts for explaining OOD detectors: 1) detection completeness, which quantifies the sufficiency of concepts for explaining an OOD-detector's decisions, and 2) concept separability, which captures the distributional separation between in-distribution and OOD data in the concept space. Based on these metrics, we propose a framework for learning a set of concepts that satisfy the desired properties of detection completeness and concept separability and demonstrate the framework's effectiveness in providing concept-based explanations for diverse OOD techniques. We also show how to identify prominent concepts that contribute to the detection results via a modified Shapley value-based importance score.

show abstract

“…As in OOD detection, OSR, AD and ND, being robust against adversarial attacks is crucial. Recent works in OSR [133], [134], ND [18], [135], and OOD detection [136], [137] have investigated the effects of adversarial attacks on models. However more is needed.…”

Section: Adversarial Robustnessmentioning

confidence: 99%

A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges

Salehi¹,

Mirzaei²,

Hendrycks³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning models often encounter samples that are diverged from the training distribution. Failure to recognize an out-of-distribution (OOD) sample, and consequently assign that sample to an in-class label significantly compromises the reliability of a model. The problem has gained significant attention due to its importance for safety deploying models in open-world settings. Detecting OOD samples is challenging due to the intractability of modeling all possible unknown distributions. To date, several research domains tackle the problem of detecting unfamiliar samples, including anomaly detection, novelty detection, one-class learning, open set recognition, and out-of-distribution detection. Despite having similar and shared concepts, out-of-distribution, open-set, and anomaly detection have been investigated independently. Accordingly, these research avenues have not cross-pollinated, creating research barriers. While some surveys intend to provide an overview of these approaches, they seem to only focus on a specific domain without examining the relationship between different domains. This survey aims to provide a cross-domain and comprehensive review of numerous eminent works in respective areas while identifying their commonalities. Researchers can benefit from the overview of research advances in different fields and develop future methodology synergistically. Furthermore, to the best of our knowledge, while there are surveys in anomaly detection or one-class learning, there is no comprehensive or up-to-date survey on out-of-distribution detection, which our survey covers extensively. Finally, having a unified cross-domain perspective, we discuss and shed light on future lines of research, intending to bring these fields closer together.

show abstract

ATOM: Robustifying Out-of-Distribution Detection Using Outlier Mining

Cited by 58 publications

References 26 publications

CIDER: Exploiting Hyperspherical Embeddings for Out-of-Distribution Detection

CIDER: Exploiting Hyperspherical Embeddings for Out-of-Distribution Detection

Concept-based Explanations for Out-Of-Distribution Detectors

A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges

Contact Info

Product

Resources

About