Detecting Out-of-Distribution Through the Lens of Neural Collapse

• URL: http://arxiv.org/abs/2311.01479v6
• Date: Mon, 14 Oct 2024 04:26:21 GMT
• Title: Detecting Out-of-Distribution Through the Lens of Neural Collapse
• Authors: Litian Liu, Yao Qin,
• Abstract summary: 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.
• Score: 7.04686607977352
• License:
• Abstract: Out-of-distribution (OOD) detection is essential for safe deployment; however, existing detectors exhibit generalization discrepancies and cost concerns. To address this, we propose a highly versatile and efficient OOD detector inspired by the trend of Neural Collapse on practical models, without requiring complete collapse. By analyzing this trend, we discover that features of in-distribution (ID) samples cluster closer to the weight vectors compared to features of OOD samples. Additionally, we reveal that ID features tend to expand in space to structure a simplex Equiangular Tight Framework, which explains the prevalent observation that ID features reside further from the origin than OOD features. Taking both insights from Neural Collapse into consideration, our OOD detector utilizes feature proximity to weight vectors and further complements this perspective by using feature norms to filter OOD samples. Extensive experiments on off-the-shelf models demonstrate the efficiency and effectiveness of our OOD detector across diverse classification tasks and model architectures, mitigating generalization discrepancies and improving overall performance.

Related papers

• Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexity [2.206582444513284]
  We propose an expected OOD risk metric to evaluate classifiers confidence on both training and OOD samples. We show that the OOD risk depicts an infinite peak, when the number of parameters is equal to the number of samples.
  arXiv  Detail & Related papers  (2024-11-04T15:39:12Z)
• Dimensionality-induced information loss of outliers in deep neural networks [29.15751143793406]
  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.
  arXiv  Detail & Related papers  (2024-10-29T01:52:46Z)
• 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)
• WeiPer: OOD Detection using Weight Perturbations of Class Projections [11.130659240045544]
  We introduce perturbations of the class projections in the final fully connected layer which creates a richer representation of the input. We achieve state-of-the-art OOD detection results across multiple benchmarks of the OpenOOD framework.
  arXiv  Detail & Related papers  (2024-05-27T13:38:28Z)
• Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Models [71.39421638547164]
  We propose to detect OOD molecules by adopting an auxiliary diffusion model-based framework, which compares similarities between input molecules and reconstructed graphs. Due to the generative bias towards reconstructing ID training samples, the similarity scores of OOD molecules will be much lower to facilitate detection. Our research pioneers an approach of Prototypical Graph Reconstruction for Molecular OOD Detection, dubbed as PGR-MOOD and hinges on three innovations.
  arXiv  Detail & Related papers  (2024-04-24T03:25:53Z)
• Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection [67.68030805755679]
  Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class. In this paper, we propose to apply world knowledge to enhance OOD detection performance through selective generation from LLMs.
  arXiv  Detail & Related papers  (2023-10-12T04:14:28Z)
• NECO: NEural Collapse Based Out-of-distribution detection [2.4958897155282282]
  We introduce NECO, a novel post-hoc method for OOD detection. Our experiments demonstrate that NECO achieves both small and large-scale OOD detection tasks. We provide a theoretical explanation for the effectiveness of our method in OOD detection.
  arXiv  Detail & Related papers  (2023-10-10T17:53:36Z)
• AUTO: Adaptive Outlier Optimization for Online Test-Time OOD Detection [81.49353397201887]
  Out-of-distribution (OOD) detection is crucial to deploying machine learning models in open-world applications. We introduce a novel paradigm called test-time OOD detection, which utilizes unlabeled online data directly at test time to improve OOD detection performance. We propose adaptive outlier optimization (AUTO), which consists of an in-out-aware filter, an ID memory bank, and a semantically-consistent objective.
  arXiv  Detail & Related papers  (2023-03-22T02:28:54Z)
• Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need [52.88953913542445]
  We find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly. We take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD)
  arXiv  Detail & Related papers  (2023-02-06T08:24:41Z)
• 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.