Understanding the Feature Norm for Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2310.05316v1
• Date: Mon, 9 Oct 2023 00:17:20 GMT
• Title: Understanding the Feature Norm for Out-of-Distribution Detection
• Abstract summary: A neural network trained on a classification dataset often exhibits a higher vector norm of hidden layer features for in-distribution (ID) samples. We propose a novel negative-aware norm (NAN) that can capture both the activation and deactivation tendencies of hidden layer neurons.
• Score: 16.40441221109391
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A neural network trained on a classification dataset often exhibits a higher vector norm of hidden layer features for in-distribution (ID) samples, while producing relatively lower norm values on unseen instances from out-of-distribution (OOD). Despite this intriguing phenomenon being utilized in many applications, the underlying cause has not been thoroughly investigated. In this study, we demystify this very phenomenon by scrutinizing the discriminative structures concealed in the intermediate layers of a neural network. Our analysis leads to the following discoveries: (1) The feature norm is a confidence value of a classifier hidden in the network layer, specifically its maximum logit. Hence, the feature norm distinguishes OOD from ID in the same manner that a classifier confidence does. (2) The feature norm is class-agnostic, thus it can detect OOD samples across diverse discriminative models. (3) The conventional feature norm fails to capture the deactivation tendency of hidden layer neurons, which may lead to misidentification of ID samples as OOD instances. To resolve this drawback, we propose a novel negative-aware norm (NAN) that can capture both the activation and deactivation tendencies of hidden layer neurons. We conduct extensive experiments on NAN, demonstrating its efficacy and compatibility with existing OOD detectors, as well as its capability in label-free environments.

Related papers

• Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models [40.6282934670186]
  We argue that anomaly knowledge is intrinsically embedded within pre-trained models but remains latent and under-activated.<n>We propose latent anomaly knowledge excavation (LAKE), a training-free framework that identifies and elicits these critical neuronal signals.<n>Our work advocates for a paradigm shift: redefining anomaly detection as the targeted activation of latent pre-trained knowledge.
  arXiv  Detail & Related papers  (2026-04-09T04:54:25Z)
• GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection [61.96025941146103]
  GOOD is a novel framework that guides sampling trajectories towards OOD regions using off-the-shelf in-distribution (ID) classifiers.<n> GOOD incorporates dual-level guidance: Image-level guidance based on the gradient of log partition to reduce input likelihood, drives samples toward low-density regions in pixel space.<n>We introduce a unified OOD score that adaptively combines image and feature discrepancies, enhancing detection robustness.
  arXiv  Detail & Related papers  (2025-10-20T03:58:46Z)
• Advancing Out-of-Distribution Detection via Local Neuroplasticity [60.53625435889467]
  This paper presents a novel OOD detection method that leverages the unique local neuroplasticity property of Kolmogorov-Arnold Networks (KANs) Our method compares the activation patterns of a trained KAN against its untrained counterpart to detect OOD samples. We validate our approach on benchmarks from image and medical domains, demonstrating superior performance and robustness compared to state-of-the-art techniques.
  arXiv  Detail & Related papers  (2025-02-20T11:13:41Z)
• 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)
• The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection [75.65876949930258]
  Out-of-distribution (OOD) detection is essential for model trustworthiness. We show that the superior OOD detection performance of state-of-the-art methods is achieved by secretly sacrificing the OOD generalization ability.
  arXiv  Detail & Related papers  (2024-10-12T07:02:04Z)
• Your Classifier Can Be Secretly a Likelihood-Based OOD Detector [17.420727709895736]
  We propose Intrinsic Likelihood (INK), which offers rigorous likelihood interpretation to modern discriminative-based classifiers. INK establishes a new state-of-the-art in a variety of OOD detection setups, including both far-OOD and near-OOD.
  arXiv  Detail & Related papers  (2024-08-09T04:00:53Z)
• Distilling the Unknown to Unveil Certainty [66.29929319664167]
  Out-of-distribution (OOD) detection is essential in identifying test samples that deviate from the in-distribution (ID) data upon which a standard network is trained. This paper introduces OOD knowledge distillation, a pioneering learning framework applicable whether or not training ID data is available.
  arXiv  Detail & Related papers  (2023-11-14T08:05:02Z)
• Detecting Out-of-Distribution Through the Lens of Neural Collapse [7.04686607977352]
  Out-of-distribution (OOD) detection is essential for safe deployment. Existing detectors exhibit generalization discrepancies and cost concerns. We propose a highly versatile and efficient OOD detector inspired by the trend of Neural Collapse.
  arXiv  Detail & Related papers  (2023-11-02T05:18:28Z)
• T2FNorm: Extremely Simple Scaled Train-time Feature Normalization for OOD Detection [16.03174062601543]
  We introduce T2FNorm, a novel approach to transforming features to hyperspherical space during training, while employing non-transformed space for OOD-scoring purposes. This method yields a surprising enhancement in OOD detection capabilities without compromising model accuracy in in-distribution(ID)
  arXiv  Detail & Related papers  (2023-05-28T18:56:54Z)
• 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)
• A Novel Explainable Out-of-Distribution Detection Approach for Spiking Neural Networks [6.100274095771616]
  This work presents a novel OoD detector that can identify whether test examples input to a Spiking Neural Network belong to the distribution of the data over which it was trained. We characterize the internal activations of the hidden layers of the network in the form of spike count patterns. A local explanation method is devised to produce attribution maps revealing which parts of the input instance push most towards the detection of an example as an OoD sample.
  arXiv  Detail & Related papers  (2022-09-30T11:16:35Z)
• Provably Robust Detection of Out-of-distribution Data (almost) for free [124.14121487542613]
  Deep neural networks are known to produce highly overconfident predictions on out-of-distribution (OOD) data. In this paper we propose a novel method where from first principles we combine a certifiable OOD detector with a standard classifier into an OOD aware classifier. In this way we achieve the best of two worlds: certifiably adversarially robust OOD detection, even for OOD samples close to the in-distribution, without loss in prediction accuracy and close to state-of-the-art OOD detection performance for non-manipulated OOD data.
  arXiv  Detail & Related papers  (2021-06-08T11:40:49Z)
• 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)
• Understanding Classifier Mistakes with Generative Models [88.20470690631372]
  Deep neural networks are effective on supervised learning tasks, but have been shown to be brittle. In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize. Our approach is agnostic to class labels from the training set which makes it applicable to models trained in a semi-supervised way.
  arXiv  Detail & Related papers  (2020-10-05T22:13:21Z)

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.