Continual Novelty Detection

• URL: http://arxiv.org/abs/2106.12964v1
• Date: Thu, 24 Jun 2021 12:30:41 GMT
• Title: Continual Novelty Detection
• Authors: Rahaf Aljundi, Daniel Olmeda Reino, Nikolay Chumerin, Richard E. Turner
• Abstract summary: We show that Continual Learning affects the behaviour of novelty detection algorithms, while novelty detection can pinpoint insights in the behaviour of a continual learner. We believe that the coupling of the two problems is a promising direction to bring vision models into practice.
• Score: 37.43667292607965
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Novelty Detection methods identify samples that are not representative of a model's training set thereby flagging misleading predictions and bringing a greater flexibility and transparency at deployment time. However, research in this area has only considered Novelty Detection in the offline setting. Recently, there has been a growing realization in the computer vision community that applications demand a more flexible framework - Continual Learning - where new batches of data representing new domains, new classes or new tasks become available at different points in time. In this setting, Novelty Detection becomes more important, interesting and challenging. This work identifies the crucial link between the two problems and investigates the Novelty Detection problem under the Continual Learning setting. We formulate the Continual Novelty Detection problem and present a benchmark, where we compare several Novelty Detection methods under different Continual Learning settings. We show that Continual Learning affects the behaviour of novelty detection algorithms, while novelty detection can pinpoint insights in the behaviour of a continual learner. We further propose baselines and discuss possible research directions. We believe that the coupling of the two problems is a promising direction to bring vision models into practice.

Related papers

• Unsupervised Novelty Detection Methods Benchmarking with Wavelet Decomposition [0.22369578015657962]
  unsupervised machine learning algorithms for novelty detection are compared. A new dataset is gathered from an actuator vibrating at specific frequencies to benchmark the algorithms and evaluate the framework. Our findings offer valuable insights into the adaptability and robustness of unsupervised learning techniques for real-world novelty detection applications.
  arXiv  Detail & Related papers  (2024-09-11T09:31:28Z)
• Assaying on the Robustness of Zero-Shot Machine-Generated Text Detectors [57.7003399760813]
  We explore advanced Large Language Models (LLMs) and their specialized variants, contributing to this field in several ways. We uncover a significant correlation between topics and detection performance. These investigations shed light on the adaptability and robustness of these detection methods across diverse topics.
  arXiv  Detail & Related papers  (2023-12-20T10:53:53Z)
• A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning [58.107474025048866]
  Forgetting refers to the loss or deterioration of previously acquired knowledge. Forgetting is a prevalent phenomenon observed in various other research domains within deep learning.
  arXiv  Detail & Related papers  (2023-07-16T16:27:58Z)
• Continual Learning for Pose-Agnostic Object Recognition in 3D Point Clouds [5.521693536291449]
  This work focuses on pose-agnostic continual learning tasks, where the object's pose changes dynamically and unpredictably. We propose a novel continual learning model that effectively distillates previous tasks' geometric equivariance information. The experiments show that our method overcomes the challenge of pose-agnostic scenarios in several mainstream point cloud datasets.
  arXiv  Detail & Related papers  (2022-09-11T11:31:39Z)
• Continual Object Detection: A review of definitions, strategies, and challenges [0.0]
  The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. We believe that research in continual object detection deserves even more attention due to its vast range of applications in robotics and autonomous vehicles.
  arXiv  Detail & Related papers  (2022-05-30T21:57:48Z)
• On Generalizing Beyond Domains in Cross-Domain Continual Learning [91.56748415975683]
  Deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Our proposed approach learns new tasks under domain shift with accuracy boosts up to 10% on challenging datasets such as DomainNet and OfficeHome.
  arXiv  Detail & Related papers  (2022-03-08T09:57:48Z)
• What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks? [59.51457877578138]
  We study contrastive learning on the wearable-based activity recognition task. This paper presents an open-source PyTorch library textttCL-HAR, which can serve as a practical tool for researchers.
  arXiv  Detail & Related papers  (2022-02-12T06:10:15Z)
• Towards Generalized and Incremental Few-Shot Object Detection [9.033533653482529]
  A novel Incremental Few-Shot Object Detection (iFSOD) method is proposed to enable the effective continual learning from few-shot samples. Specifically, a Double-Branch Framework (DBF) is proposed to decouple the feature representation of base and novel (few-shot) class. We conduct experiments on both Pascal VOC and MS-COCO, which demonstrate that our method can effectively solve the problem of incremental few-shot detection.
  arXiv  Detail & Related papers  (2021-09-23T12:38:09Z)
• ARCADe: A Rapid Continual Anomaly Detector [25.34227775187408]
  We address a novel learning problem of continual anomaly detection (CAD) We propose ARCADe, an approach to train neural networks to be robust against the major challenges of this new learning problem. The results of our experiments on three datasets show that ARCADe substantially outperforms baselines from the continual learning and anomaly detection literature.
  arXiv  Detail & Related papers  (2020-08-10T11:59:32Z)
• Deep Learning for Anomaly Detection: A Review [150.9270911031327]
  This paper surveys the research of deep anomaly detection with a comprehensive taxonomy, covering advancements in three high-level categories and 11 fine-grained categories of the methods. We review their key intuitions, objective functions, underlying assumptions, advantages and disadvantages, and discuss how they address the aforementioned challenges.
  arXiv  Detail & Related papers  (2020-07-06T02:21:16Z)

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.