Dimensionality-induced information loss of outliers in deep neural networks

• URL: http://arxiv.org/abs/2410.21656v1
• Date: Tue, 29 Oct 2024 01:52:46 GMT
• Title: Dimensionality-induced information loss of outliers in deep neural networks
• Authors: Kazuki Uematsu, Kosuke Haruki, Taiji Suzuki, Mitsuhiro Kimura, Takahiro Takimoto, Hideyuki Nakagawa,
• Abstract summary: Out-of-distribution (OOD) detection is a critical issue for systems using a deep neural network (DNN) We experimentally clarify this issue by investigating the layer dependence of feature representations from multiple perspectives. We propose a dimensionality-aware OOD detection method based on alignment of features and weights.
• Score: 29.15751143793406
• License:
• Abstract: Out-of-distribution (OOD) detection is a critical issue for the stable and reliable operation of systems using a deep neural network (DNN). Although many OOD detection methods have been proposed, it remains unclear how the differences between in-distribution (ID) and OOD samples are generated by each processing step inside DNNs. We experimentally clarify this issue by investigating the layer dependence of feature representations from multiple perspectives. We find that intrinsic low dimensionalization of DNNs is essential for understanding how OOD samples become more distinct from ID samples as features propagate to deeper layers. Based on these observations, we provide a simple picture that consistently explains various properties of OOD samples. Specifically, low-dimensional weights eliminate most information from OOD samples, resulting in misclassifications due to excessive attention to dataset bias. In addition, we demonstrate the utility of dimensionality by proposing a dimensionality-aware OOD detection method based on alignment of features and weights, which consistently achieves high performance for various datasets with lower computational cost.

Related papers

• Can OOD Object Detectors Learn from Foundation Models? [56.03404530594071]
  Out-of-distribution (OOD) object detection is a challenging task due to the absence of open-set OOD data. Inspired by recent advancements in text-to-image generative models, we study the potential of generative models trained on large-scale open-set data to synthesize OOD samples. We introduce SyncOOD, a simple data curation method that capitalizes on the capabilities of large foundation models.
  arXiv  Detail & Related papers  (2024-09-08T17:28:22Z)
• Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox [70.57120710151105]
  Most existing out-of-distribution (OOD) detection benchmarks classify samples with novel labels as the OOD data. Some marginal OOD samples actually have close semantic contents to the in-distribution (ID) sample, which makes determining the OOD sample a Sorites Paradox. We construct a benchmark named Incremental Shift OOD (IS-OOD) to address the issue.
  arXiv  Detail & Related papers  (2024-06-14T09:27:56Z)
• Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection [21.357620914949624]
  In the open world, detecting out-of-distribution (OOD) data, whose labels are disjoint with those of in-distribution (ID) samples, is important for reliable deep neural networks (DNNs) We propose a simple but effective loss called OrthLoss, which binds the features of OOD data in a subspace to the principal subspace of ID features formed by NC. Our detection achieves SOTA performance on CIFAR benchmarks without any additional data augmentation or sampling.
  arXiv  Detail & Related papers  (2024-05-28T04:24:38Z)
• LINe: Out-of-Distribution Detection by Leveraging Important Neurons [15.797257361788812]
  We introduce a new aspect for analyzing the difference in model outputs between in-distribution data and OOD data. We propose a novel method, Leveraging Important Neurons (LINe), for post-hoc Out of distribution detection.
  arXiv  Detail & Related papers  (2023-03-24T13:49:05Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection [7.221206118679026]
  The ability to detect Out-of-Distribution (OOD) data is important in safety-critical applications of deep learning. An existing intuition in the literature is that the diversity of Deep Ensemble predictions indicates distributional shift. We show experimentally that this intuition is not valid on ImageNet-scale OOD detection.
  arXiv  Detail & Related papers  (2022-07-15T15:02:38Z)
• Do Deep Neural Networks Always Perform Better When Eating More Data? [82.6459747000664]
  We design experiments from Identically Independent Distribution(IID) and Out of Distribution(OOD) Under IID condition, the amount of information determines the effectivity of each sample, the contribution of samples and difference between classes determine the amount of class information. Under OOD condition, the cross-domain degree of samples determine the contributions, and the bias-fitting caused by irrelevant elements is a significant factor of cross-domain.
  arXiv  Detail & Related papers  (2022-05-30T15:40:33Z)
• Igeood: An Information Geometry Approach to Out-of-Distribution Detection [35.04325145919005]
  We introduce Igeood, an effective method for detecting out-of-distribution (OOD) samples. Igeood applies to any pre-trained neural network, works under various degrees of access to the machine learning model. We show that Igeood outperforms competing state-of-the-art methods on a variety of network architectures and datasets.
  arXiv  Detail & Related papers  (2022-03-15T11:26:35Z)
• 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)
• Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Features [7.219077740523682]
  This paper presents a principled approach for detecting out-of-distribution (OOD) samples in deep neural networks (DNN) Modeling probability distributions on deep features has recently emerged as an effective, yet computationally cheap method to detect OOD samples in DNN. We apply linear statistical dimensionality reduction techniques and nonlinear manifold-learning techniques on the high-dimensional features in order to capture the true subspace spanned by the features.
  arXiv  Detail & Related papers  (2020-12-08T07:07:11Z)
• NADS: Neural Architecture Distribution Search for Uncertainty Awareness [79.18710225716791]
  Machine learning (ML) systems often encounter Out-of-Distribution (OoD) errors when dealing with testing data coming from a distribution different from training data. Existing OoD detection approaches are prone to errors and even sometimes assign higher likelihoods to OoD samples. We propose Neural Architecture Distribution Search (NADS) to identify common building blocks among all uncertainty-aware architectures.
  arXiv  Detail & Related papers  (2020-06-11T17:39:07Z)

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.