H2ST: Hierarchical Two-Sample Tests for Continual Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2503.14832v1
• Date: Wed, 19 Mar 2025 02:24:43 GMT
• Title: H2ST: Hierarchical Two-Sample Tests for Continual Out-of-Distribution Detection
• Authors: Yuhang Liu, Wenjie Zhao, Yunhui Guo,
• Abstract summary: Task Incremental Learning (TIL) is a specialized form of Continual Learning (CL) in which a model incrementally learns from non-stationary data streams.<n>In an open-world setting, incoming samples may originate from out-of-distribution sources.<n>We propose a novel continual OOD detection method called the Hierarchical Two-sample Tests (H2ST)
• Score: 10.949658724247387
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Task Incremental Learning (TIL) is a specialized form of Continual Learning (CL) in which a model incrementally learns from non-stationary data streams. Existing TIL methodologies operate under the closed-world assumption, presuming that incoming data remains in-distribution (ID). However, in an open-world setting, incoming samples may originate from out-of-distribution (OOD) sources, with their task identities inherently unknown. Continually detecting OOD samples presents several challenges for current OOD detection methods: reliance on model outputs leads to excessive dependence on model performance, selecting suitable thresholds is difficult, hindering real-world deployment, and binary ID/OOD classification fails to provide task-level identification. To address these issues, we propose a novel continual OOD detection method called the Hierarchical Two-sample Tests (H2ST). H2ST eliminates the need for threshold selection through hypothesis testing and utilizes feature maps to better exploit model capabilities without excessive dependence on model performance. The proposed hierarchical architecture enables task-level detection with superior performance and lower overhead compared to non-hierarchical classifier two-sample tests. Extensive experiments and analysis validate the effectiveness of H2ST in open-world TIL scenarios and its superiority to the existing methods. Code is available at \href{https://github.com/YuhangLiuu/H2ST}{https://github.com/YuhangLiuu/H2ST}.

Related papers

• STOOD-X methodology: using statistical nonparametric test for OOD Detection Large-Scale datasets enhanced with explainability [9.658282892513386]
  Out-of-Distribution (OOD) detection is a critical task in machine learning, particularly in safety-sensitive applications where model failures can have serious consequences. We propose STOOD-X, a two-stage methodology that combines a Statistical nonparametric Test for OOD Detection with eXplainability enhancements. In the first stage, STOOD-X uses feature-space distances and a Wilcoxon-Mann-Whitney test to identify OOD samples without assuming a specific feature distribution. In the second stage, it generates user-friendly, concept-based visual explanations that reveal the features driving each decision, aligning with the BLUE
  arXiv  Detail & Related papers  (2025-04-03T15:26:03Z)
• Multi-label out-of-distribution detection via evidential learning [8.256216638460455]
  We propose a CNN architecture that uses a Beta Evidential Neural Network to compute both the likelihood and the predictive uncertainty of the samples. Based on these results, we propose two new uncertainty-based scores for OOD data detection: (i) OOD - score Max, based on the maximum evidence; and (ii) OOD - Sum, which considers the evidence from all outputs.
  arXiv  Detail & Related papers  (2025-02-25T14:08:35Z)
• Out-of-Distribution Detection using Synthetic Data Generation [21.612592503592143]
  In- and out-of-distribution (OOD) inputs are crucial for reliable deployment of classification systems.<n>We present a method that harnesses the generative capabilities of Large Language Models (LLMs) to create high-quality synthetic OOD proxies.
  arXiv  Detail & Related papers  (2025-02-05T16:22:09Z)
• Going Beyond Conventional OOD Detection [0.0]
  Out-of-distribution (OOD) detection is critical to ensure the safe deployment of deep learning models in critical applications.<n>We present a unified Approach to Spurimatious, fine-grained, and Conventional OOD Detection (ASCOOD)<n>Our approach effectively mitigates the impact of spurious correlations and encourages capturing fine-grained attributes.
  arXiv  Detail & Related papers  (2024-11-16T13:04:52Z)
• Representation Norm Amplification for Out-of-Distribution Detection in Long-Tail Learning [10.696635172502141]
  We introduce our method, called textitRepresentation Norm Amplification (RNA), which solves the problem of detecting out-of-distribution samples. Experiments show that RNA achieves superior performance in both OOD detection and classification compared to the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-20T09:27:07Z)
• Out-of-Distribution Detection with a Single Unconditional Diffusion Model [54.15132801131365]
  Out-of-distribution (OOD) detection is a critical task in machine learning that seeks to identify abnormal samples. Traditionally, unsupervised methods utilize a deep generative model for OOD detection. This paper explores whether a single model can perform OOD detection across diverse tasks.
  arXiv  Detail & Related papers  (2024-05-20T08:54:03Z)
• EAT: Towards Long-Tailed Out-of-Distribution Detection [55.380390767978554]
  This paper addresses the challenging task of long-tailed OOD detection. The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes. We propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes, and (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data.
  arXiv  Detail & Related papers  (2023-12-14T13:47:13Z)
• On Pitfalls of Test-Time Adaptation [82.8392232222119]
  Test-Time Adaptation (TTA) has emerged as a promising approach for tackling the robustness challenge under distribution shifts. We present TTAB, a test-time adaptation benchmark that encompasses ten state-of-the-art algorithms, a diverse array of distribution shifts, and two evaluation protocols.
  arXiv  Detail & Related papers  (2023-06-06T09:35:29Z)
• Learning Mixtures of Linear Dynamical Systems [94.49754087817931]
  We develop a two-stage meta-algorithm to efficiently recover each ground-truth LDS model up to error $tildeO(sqrtd/T)$. We validate our theoretical studies with numerical experiments, confirming the efficacy of the proposed algorithm.
  arXiv  Detail & Related papers  (2022-01-26T22:26:01Z)
• Semantically Coherent Out-of-Distribution Detection [26.224146828317277]
  Current out-of-distribution (OOD) detection benchmarks are commonly built by defining one dataset as in-distribution (ID) and all others as OOD. We re-design the benchmarks and propose the semantically coherent out-of-distribution detection (SC-OOD) Our approach achieves state-of-the-art performance on SC-OOD benchmarks.
  arXiv  Detail & Related papers  (2021-08-26T17:53:32Z)
• Learn what you can't learn: Regularized Ensembles for Transductive Out-of-distribution Detection [76.39067237772286]
  We show that current out-of-distribution (OOD) detection algorithms for neural networks produce unsatisfactory results in a variety of OOD detection scenarios. This paper studies how such "hard" OOD scenarios can benefit from adjusting the detection method after observing a batch of the test data. We propose a novel method that uses an artificial labeling scheme for the test data and regularization to obtain ensembles of models that produce contradictory predictions only on the OOD samples in a test batch.
  arXiv  Detail & Related papers  (2020-12-10T16:55:13Z)
• Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders [51.691585766702744]
  We propose a variant of Adversarial Autoencoder which uses a mirrored Wasserstein loss in the discriminator to enforce better semantic-level reconstruction. We put forward an alternative measure of anomaly score to replace the reconstruction-based metric. Our method outperforms the current state-of-the-art methods for anomaly detection on several OOD detection benchmarks.
  arXiv  Detail & Related papers  (2020-03-24T08:26:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.