When and How Does In-Distribution Label Help Out-of-Distribution Detection?

• URL: http://arxiv.org/abs/2405.18635v1
• Date: Tue, 28 May 2024 22:34:53 GMT
• Title: When and How Does In-Distribution Label Help Out-of-Distribution Detection?
• Authors: Xuefeng Du, Yiyou Sun, Yixuan Li,
• Abstract summary: This paper offers a formal understanding to theoretically delineate the impact of ID labels on OOD detection. We employ a graph-theoretic approach, rigorously analyzing the separability of ID data from OOD data in a closed-form manner. We present empirical results on both simulated and real datasets, validating theoretical guarantees and reinforcing our insights.
• Score: 38.874518492468965
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detecting data points deviating from the training distribution is pivotal for ensuring reliable machine learning. Extensive research has been dedicated to the challenge, spanning classical anomaly detection techniques to contemporary out-of-distribution (OOD) detection approaches. While OOD detection commonly relies on supervised learning from a labeled in-distribution (ID) dataset, anomaly detection may treat the entire ID data as a single class and disregard ID labels. This fundamental distinction raises a significant question that has yet to be rigorously explored: when and how does ID label help OOD detection? This paper bridges this gap by offering a formal understanding to theoretically delineate the impact of ID labels on OOD detection. We employ a graph-theoretic approach, rigorously analyzing the separability of ID data from OOD data in a closed-form manner. Key to our approach is the characterization of data representations through spectral decomposition on the graph. Leveraging these representations, we establish a provable error bound that compares the OOD detection performance with and without ID labels, unveiling conditions for achieving enhanced OOD detection. Lastly, we present empirical results on both simulated and real datasets, validating theoretical guarantees and reinforcing our insights. Code is publicly available at https://github.com/deeplearning-wisc/id_label.

Related papers

• Semantic or Covariate? A Study on the Intractable Case of Out-of-Distribution Detection [70.57120710151105]
  We provide a more precise definition of the Semantic Space for the ID distribution. We also define the "Tractable OOD" setting which ensures the distinguishability of OOD and ID distributions.
  arXiv  Detail & Related papers  (2024-11-18T03:09:39Z)
• 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. We present a unified Approach to Spurimatious, fine-grained, and Conventional OOD Detection (ASCOOD) Our approach effectively mitigates the impact of spurious correlations and encourages capturing fine-grained attributes.
  arXiv  Detail & Related papers  (2024-11-16T13:04:52Z)
• What If the Input is Expanded in OOD Detection? [77.37433624869857]
  Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes. Various scoring functions are proposed to distinguish it from in-distribution (ID) data. We introduce a novel perspective, i.e., employing different common corruptions on the input space.
  arXiv  Detail & Related papers  (2024-10-24T06:47:28Z)
• How Does Unlabeled Data Provably Help Out-of-Distribution Detection? [63.41681272937562]
  Unlabeled in-the-wild data is non-trivial due to the heterogeneity of both in-distribution (ID) and out-of-distribution (OOD) data. This paper introduces a new learning framework SAL (Separate And Learn) that offers both strong theoretical guarantees and empirical effectiveness.
  arXiv  Detail & Related papers  (2024-02-05T20:36:33Z)
• 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)
• GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection [67.90365841083951]
  We develop a new graph contrastive learning framework GOOD-D for detecting OOD graphs without using any ground-truth labels. GOOD-D is able to capture the latent ID patterns and accurately detect OOD graphs based on the semantic inconsistency in different granularities. As a pioneering work in unsupervised graph-level OOD detection, we build a comprehensive benchmark to compare our proposed approach with different state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-11-08T12:41:58Z)
• Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data [7.221206118679026]
  We show that existing post-hoc methods perform quite differently compared to when evaluated only on OOD detection. We propose a novel method for SCOD, Softmax Information Retaining Combination (SIRC), that augments softmax-based confidence scores with feature-agnostic information. Experiments on a wide variety of ImageNet-scale datasets and convolutional neural network architectures show that SIRC is able to consistently match or outperform the baseline for SCOD.
  arXiv  Detail & Related papers  (2022-07-15T14:39:57Z)
• Supervision Adaptation Balancing In-distribution Generalization and Out-of-distribution Detection [36.66825830101456]
  In-distribution (ID) and out-of-distribution (OOD) samples can lead to textitdistributional vulnerability in deep neural networks. We introduce a novel textitsupervision adaptation approach to generate adaptive supervision information for OOD samples, making them more compatible with ID samples.
  arXiv  Detail & Related papers  (2022-06-19T11:16:44Z)

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.