Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks

• URL: http://arxiv.org/abs/2408.16757v2
• Date: Fri, 30 Aug 2024 02:26:01 GMT
• Title: Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks
• Authors: Hongjun Wang, Sagar Vaze, Kai Han,
• Abstract summary: We aim to provide a consolidated view of the two largest sub-fields within the community: out-of-distribution (OOD) detection and open-set recognition (OSR) We perform rigorous cross-evaluation between state-of-the-art methods in the OOD detection and OSR settings and identify a strong correlation between the performances of methods for them. We propose a new, large-scale benchmark setting which we suggest better disentangles the problem tackled by OOD detection and OSR.
• Score: 17.520137576423593
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Detecting test-time distribution shift has emerged as a key capability for safely deployed machine learning models, with the question being tackled under various guises in recent years. In this paper, we aim to provide a consolidated view of the two largest sub-fields within the community: out-of-distribution (OOD) detection and open-set recognition (OSR). In particular, we aim to provide rigorous empirical analysis of different methods across settings and provide actionable takeaways for practitioners and researchers. Concretely, we make the following contributions: (i) We perform rigorous cross-evaluation between state-of-the-art methods in the OOD detection and OSR settings and identify a strong correlation between the performances of methods for them; (ii) We propose a new, large-scale benchmark setting which we suggest better disentangles the problem tackled by OOD detection and OSR, re-evaluating state-of-the-art OOD detection and OSR methods in this setting; (iii) We surprisingly find that the best performing method on standard benchmarks (Outlier Exposure) struggles when tested at scale, while scoring rules which are sensitive to the deep feature magnitude consistently show promise; and (iv) We conduct empirical analysis to explain these phenomena and highlight directions for future research. Code: https://github.com/Visual-AI/Dissect-OOD-OSR

Related papers

• Margin-bounded Confidence Scores for Out-of-Distribution Detection [2.373572816573706]
  We propose a novel method called Margin bounded Confidence Scores (MaCS) to address the nontrivial OOD detection problem. MaCS enlarges the disparity between ID and OOD scores, which in turn makes the decision boundary more compact. Experiments on various benchmark datasets for image classification tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-09-22T05:40:25Z)
• Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark [73.58840254552656]
  Unsupervised graph-level anomaly detection (GLAD) and unsupervised graph-level out-of-distribution (OOD) detection have received significant attention in recent years. We present a Unified Benchmark for unsupervised Graph-level OOD and anomaly Detection (our method) Our benchmark encompasses 35 datasets spanning four practical anomaly and OOD detection scenarios. We conduct multi-dimensional analyses to explore the effectiveness, generalizability, robustness, and efficiency of existing methods.
  arXiv  Detail & Related papers  (2024-06-21T04:07:43Z)
• Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection [3.7384109981836158]
  We study the problem of out-of-distribution (OOD) detection in reinforcement learning (RL) We propose a clarification of terminology for OOD detection in RL, which aligns it with the literature from other machine learning domains. We present new benchmark scenarios for OOD detection, which introduce anomalies with temporal autocorrelation into different components of the agent-environment loop. We find that DEXTER can reliably identify anomalies across benchmark scenarios, exhibiting superior performance compared to both state-of-the-art OOD detectors and high-dimensional changepoint detectors adopted from statistics.
  arXiv  Detail & Related papers  (2024-04-10T15:39:49Z)
• Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection [9.656342063882555]
  We study five types of distribution shifts and evaluate the performance of recent OOD detection methods on each of them. Our findings reveal that while these methods excel in detecting unknown classes, their performance is inconsistent when encountering other types of distribution shifts. We present an ensemble approach that offers a more consistent and comprehensive solution for broad OOD detection.
  arXiv  Detail & Related papers  (2023-08-22T14:52:44Z)
• Beyond AUROC & co. for evaluating out-of-distribution detection performance [50.88341818412508]
  Given their relevance for safe(r) AI, it is important to examine whether the basis for comparing OOD detection methods is consistent with practical needs. We propose a new metric - Area Under the Threshold Curve (AUTC), which explicitly penalizes poor separation between ID and OOD samples.
  arXiv  Detail & Related papers  (2023-06-26T12:51:32Z)
• Plugin estimators for selective classification with out-of-distribution detection [67.28226919253214]
  Real-world classifiers can benefit from abstaining from predicting on samples where they have low confidence. These settings have been the subject of extensive but disjoint study in the selective classification (SC) and out-of-distribution (OOD) detection literature. Recent work on selective classification with OOD detection has argued for the unified study of these problems. We propose new plugin estimators for SCOD that are theoretically grounded, effective, and generalise existing approaches.
  arXiv  Detail & Related papers  (2023-01-29T07:45:17Z)
• OpenOOD: Benchmarking Generalized Out-of-Distribution Detection [60.13300701826931]
  Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications. The field currently lacks a unified, strictly formulated, and comprehensive benchmark. We build a unified, well-structured called OpenOOD, which implements over 30 methods developed in relevant fields.
  arXiv  Detail & Related papers  (2022-10-13T17:59:57Z)
• Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation [76.2621758731288]
  We tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA) We show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.
  arXiv  Detail & Related papers  (2021-08-03T17:09:56Z)
• Robust Out-of-distribution Detection for Neural Networks [51.19164318924997]
  We show that existing detection mechanisms can be extremely brittle when evaluating on in-distribution and OOD inputs. We propose an effective algorithm called ALOE, which performs robust training by exposing the model to both adversarially crafted inlier and outlier examples.
  arXiv  Detail & Related papers  (2020-03-21T17:46:28Z)

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.