AnomalyHop: An SSL-based Image Anomaly Localization Method

• URL: http://arxiv.org/abs/2105.03797v1
• Date: Sat, 8 May 2021 23:17:27 GMT
• Title: AnomalyHop: An SSL-based Image Anomaly Localization Method
• Authors: Kaitai Zhang, Bin Wang, Wei Wang, Fahad Sohrab, Moncef Gabbouj and C.-C. Jay Kuo
• Abstract summary: AnomalyHop is an image anomaly localization method based on the successive subspace learning (SSL) framework. AnomalyHop is mathematically transparent, easy to train, and fast in its inference speed. Its area under the ROC curve (ROC-AUC) performance on the MVTec AD dataset is 95.9%, which is among the best of several benchmarking methods.
• Score: 47.56319291471639
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An image anomaly localization method based on the successive subspace learning (SSL) framework, called AnomalyHop, is proposed in this work. AnomalyHop consists of three modules: 1) feature extraction via successive subspace learning (SSL), 2) normality feature distributions modeling via Gaussian models, and 3) anomaly map generation and fusion. Comparing with state-of-the-art image anomaly localization methods based on deep neural networks (DNNs), AnomalyHop is mathematically transparent, easy to train, and fast in its inference speed. Besides, its area under the ROC curve (ROC-AUC) performance on the MVTec AD dataset is 95.9%, which is among the best of several benchmarking methods. Our codes are publicly available at Github.

Related papers

• Towards Realistic Example-based Modeling via 3D Gaussian Stitching [31.710954782769377]
  We present an example-based modeling method that combines multiple Gaussian fields in a point-based representation using sample-guided synthesis. Specifically, as for composition, we create a GUI to segment and transform multiple fields in real time, easily obtaining a semantically meaningful composition of models. For texture blending, due to the discrete and irregular nature of 3DGS, straightforwardly applying gradient propagation as SeamlssNeRF is not supported.
  arXiv  Detail & Related papers  (2024-08-28T11:13:27Z)
• GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [51.96353586773191]
  We introduce textbfGS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping system. Our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets.
  arXiv  Detail & Related papers  (2023-11-20T12:08:23Z)
• LeapfrogLayers: A Trainable Framework for Effective Topological Sampling [0.7366405857677227]
  We introduce Leapfrogs, an invertible neural network architecture that can be trained to efficiently sample the topology of a 2D $U(1)$ lattice gauge theory. We show an improvement in the integrated autocorrelation time of the topological charge when compared with traditional HMC, and propose methods for scaling our model to larger lattice volumes.
  arXiv  Detail & Related papers  (2021-12-02T19:48:16Z)
• Spatial-spectral Hyperspectral Image Classification via Multiple Random Anchor Graphs Ensemble Learning [88.60285937702304]
  This paper proposes a novel spatial-spectral HSI classification method via multiple random anchor graphs ensemble learning (RAGE) Firstly, the local binary pattern is adopted to extract the more descriptive features on each selected band, which preserves local structures and subtle changes of a region. Secondly, the adaptive neighbors assignment is introduced in the construction of anchor graph, to reduce the computational complexity.
  arXiv  Detail & Related papers  (2021-03-25T09:31:41Z)
• PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation [87.50205728818601]
  We propose a PriorGuided Local (PGL) self-supervised model that learns the region-wise local consistency in the latent feature space. Our PGL model learns the distinctive representations of local regions, and hence is able to retain structural information.
  arXiv  Detail & Related papers  (2020-11-25T11:03:11Z)
• Multiscale Score Matching for Out-of-Distribution Detection [19.61640396236456]
  We present a new methodology for detecting out-of-distribution (OOD) images by utilizing norms of the score estimates at multiple noise scales. Our methodology is completely unsupervised and follows a straight forward training scheme.
  arXiv  Detail & Related papers  (2020-10-25T15:10:31Z)
• Stein Variational Inference for Discrete Distributions [70.19352762933259]
  We propose a simple yet general framework that transforms discrete distributions to equivalent piecewise continuous distributions. Our method outperforms traditional algorithms such as Gibbs sampling and discontinuous Hamiltonian Monte Carlo. We demonstrate that our method provides a promising tool for learning ensembles of binarized neural network (BNN) In addition, such transform can be straightforwardly employed in gradient-free kernelized Stein discrepancy to perform goodness-of-fit (GOF) test on discrete distributions.
  arXiv  Detail & Related papers  (2020-03-01T22:45:41Z)
• AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning [112.95742995816367]
  We propose a new few-shot fewshot learning setting termed FSFSL. Under FSFSL, both the source and target classes have limited training samples. We also propose a graph convolutional network (GCN)-based label denoising (LDN) method to remove irrelevant images.
  arXiv  Detail & Related papers  (2020-02-28T10:34:36Z)
• PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification [30.49387075658641]
  We propose an improved PixelHop method and call it PixelHop++. In PixelHop++, one can control the learning model size of fine-granularity,offering a flexible tradeoff between the model size and the classification performance.
  arXiv  Detail & Related papers  (2020-02-08T11:08:54Z)

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.