Test Time Training for Industrial Anomaly Segmentation

• URL: http://arxiv.org/abs/2404.03743v1
• Date: Thu, 4 Apr 2024 18:31:24 GMT
• Title: Test Time Training for Industrial Anomaly Segmentation
• Authors: Alex Costanzino, Pierluigi Zama Ramirez, Mirko Del Moro, Agostino Aiezzo, Giuseppe Lisanti, Samuele Salti, Luigi Di Stefano,
• Abstract summary: Anomaly Detection and Ranging (AD&S) is crucial for industrial quality control. This paper proposes a test time training strategy to improve the segmentation performance. We demonstrate the effectiveness of our approach over baselines through extensive experimentation and evaluation on MVTec AD and MVTec 3D-AD.
• Score: 15.973768095014906
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Anomaly Detection and Segmentation (AD&S) is crucial for industrial quality control. While existing methods excel in generating anomaly scores for each pixel, practical applications require producing a binary segmentation to identify anomalies. Due to the absence of labeled anomalies in many real scenarios, standard practices binarize these maps based on some statistics derived from a validation set containing only nominal samples, resulting in poor segmentation performance. This paper addresses this problem by proposing a test time training strategy to improve the segmentation performance. Indeed, at test time, we can extract rich features directly from anomalous samples to train a classifier that can discriminate defects effectively. Our general approach can work downstream to any AD&S method that provides an anomaly score map as output, even in multimodal settings. We demonstrate the effectiveness of our approach over baselines through extensive experimentation and evaluation on MVTec AD and MVTec 3D-AD.

Related papers

• Are Anomaly Scores Telling the Whole Story? A Benchmark for Multilevel Anomaly Detection [46.244213695024]
  Anomaly detection (AD) is a machine learning task that identifies anomalies by learning patterns from normal training data. Existing models primarily operate in a binary setting, and the anomaly scores they produce are usually based on the deviation of data points from normal data. We propose a novel setting, Multilevel AD (MAD), in which the anomaly score represents the severity of anomalies in real-world applications. Second, we introduce a novel benchmark, MAD-Bench, that evaluates models not only on their ability to detect anomalies, but also on how effectively their anomaly scores reflect severity.
  arXiv  Detail & Related papers  (2024-11-21T14:18:37Z)
• ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection [10.241033980055695]
  This paper presents a two-stage training strategy, called textbfToCoAD. In the first stage, a discriminative network is trained by using synthetic anomalies in a self-supervised learning manner. This network is then utilized in the second stage to provide a negative feature guide, aiding in the training of the feature extractor through bootstrap contrastive learning.
  arXiv  Detail & Related papers  (2024-07-01T14:19:36Z)
• Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark [101.23684938489413]
  Anomaly detection (AD) is often focused on detecting anomalies for industrial quality inspection and medical lesion examination. This work first constructs a large-scale and general-purpose COCO-AD dataset by extending COCO to the AD field. Inspired by the metrics in the segmentation field, we propose several more practical threshold-dependent AD-specific metrics.
  arXiv  Detail & Related papers  (2024-04-16T17:38:26Z)
• Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [59.41026558455904]
  We focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets. We propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.
  arXiv  Detail & Related papers  (2024-01-06T07:30:41Z)
• How Low Can You Go? Surfacing Prototypical In-Distribution Samples for Unsupervised Anomaly Detection [48.30283806131551]
  We show that UAD with extremely few training samples can already match -- and in some cases even surpass -- the performance of training with the whole training dataset. We propose an unsupervised method to reliably identify prototypical samples to further boost UAD performance.
  arXiv  Detail & Related papers  (2023-12-06T15:30:47Z)
• On Pitfalls of Test-Time Adaptation [82.8392232222119]
  Test-Time Adaptation (TTA) has emerged as a promising approach for tackling the robustness challenge under distribution shifts. We present TTAB, a test-time adaptation benchmark that encompasses ten state-of-the-art algorithms, a diverse array of distribution shifts, and two evaluation protocols.
  arXiv  Detail & Related papers  (2023-06-06T09:35:29Z)
• On Modality Bias Recognition and Reduction [70.69194431713825]
  We study the modality bias problem in the context of multi-modal classification. We propose a plug-and-play loss function method, whereby the feature space for each label is adaptively learned. Our method yields remarkable performance improvements compared with the baselines.
  arXiv  Detail & Related papers  (2022-02-25T13:47:09Z)
• Self-Trained One-class Classification for Unsupervised Anomaly Detection [56.35424872736276]
  Anomaly detection (AD) has various applications across domains, from manufacturing to healthcare. In this work, we focus on unsupervised AD problems whose entire training data are unlabeled and may contain both normal and anomalous samples. To tackle this problem, we build a robust one-class classification framework via data refinement. We show that our method outperforms state-of-the-art one-class classification method by 6.3 AUC and 12.5 average precision.
  arXiv  Detail & Related papers  (2021-06-11T01:36:08Z)
• Regularization with Latent Space Virtual Adversarial Training [4.874780144224057]
  Virtual Adversarial Training (VAT) has shown impressive results among recently developed regularization methods. We propose LVAT, which injects perturbation in the latent space instead of the input space. LVAT can generate adversarial samples flexibly, resulting in more adverse effects and thus more effective regularization.
  arXiv  Detail & Related papers  (2020-11-26T08:51:38Z)

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.