Synthetic Non-stationary Data Streams for Recognition of the Unknown

• URL: http://arxiv.org/abs/2505.13745v1
• Date: Mon, 19 May 2025 21:44:32 GMT
• Title: Synthetic Non-stationary Data Streams for Recognition of the Unknown
• Authors: Joanna Komorniczak,
• Abstract summary: This article presents a strategy for synthetic data stream generation in which concept drifts and the emergence of new classes occur.<n>It shows how unsupervised drift detectors address the task of detecting novelty and concept drifts.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The problem of data non-stationarity is commonly addressed in data stream processing. In a dynamic environment, methods should continuously be ready to analyze time-varying data -- hence, they should enable incremental training and respond to concept drifts. An equally important variability typical for non-stationary data stream environments is the emergence of new, previously unknown classes. Often, methods focus on one of these two phenomena -- detection of concept drifts or detection of novel classes -- while both difficulties can be observed in data streams. Additionally, concerning previously unknown observations, the topic of open set of classes has become particularly important in recent years, where the goal of methods is to efficiently classify within known classes and recognize objects outside the model competence. This article presents a strategy for synthetic data stream generation in which both concept drifts and the emergence of new classes representing unknown objects occur. The presented research shows how unsupervised drift detectors address the task of detecting novelty and concept drifts and demonstrates how the generated data streams can be utilized in the open set recognition task.

Related papers

• A Dataset for Semantic Segmentation in the Presence of Unknowns [49.795683850385956]
  Existing datasets allow evaluation of only knowns or unknowns - but not both.<n>We propose a novel anomaly segmentation dataset, ISSU, that features a diverse set of anomaly inputs from cluttered real-world environments.<n>The dataset is twice larger than existing anomaly segmentation datasets.
  arXiv  Detail & Related papers  (2025-03-28T10:31:01Z)
• Decoupling the Class Label and the Target Concept in Machine Unlearning [81.69857244976123]
  Machine unlearning aims to adjust a trained model to approximate a retrained one that excludes a portion of training data. Previous studies showed that class-wise unlearning is successful in forgetting the knowledge of a target class. We propose a general framework, namely, TARget-aware Forgetting (TARF)
  arXiv  Detail & Related papers  (2024-06-12T14:53:30Z)
• Activate and Reject: Towards Safe Domain Generalization under Category Shift [71.95548187205736]
  We study a practical problem of Domain Generalization under Category Shift (DGCS) It aims to simultaneously detect unknown-class samples and classify known-class samples in the target domains. Compared to prior DG works, we face two new challenges: 1) how to learn the concept of unknown'' during training with only source known-class samples, and 2) how to adapt the source-trained model to unseen environments.
  arXiv  Detail & Related papers  (2023-10-07T07:53:12Z)
• Learning from Data Streams: An Overview and Update [1.5076964620370268]
  We reformulate the fundamental definitions and settings of supervised data-stream learning. We take a fresh look at what constitutes a supervised data-stream learning task. Our main emphasis is that learning from data streams does not impose a single-pass or online-learning approach.
  arXiv  Detail & Related papers  (2022-12-30T14:01:41Z)
• Open World DETR: Transformer based Open World Object Detection [60.64535309016623]
  We propose a two-stage training approach named Open World DETR for open world object detection based on Deformable DETR. We fine-tune the class-specific components of the model with a multi-view self-labeling strategy and a consistency constraint. Our proposed method outperforms other state-of-the-art open world object detection methods by a large margin.
  arXiv  Detail & Related papers  (2022-12-06T13:39:30Z)
• Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection [71.18882803642526]
  Deep learning approaches have shown remarkable performance in the 3D object detection task. They suffer from a catastrophic performance drop when incrementally learning new classes without revisiting the old data. This "catastrophic forgetting" phenomenon impedes the deployment of 3D object detection approaches in real-world scenarios. We present the first solution - SDCoT, a novel static-dynamic co-teaching method.
  arXiv  Detail & Related papers  (2021-12-14T09:03:41Z)
• Anomaly-Aware Semantic Segmentation by Leveraging Synthetic-Unknown Data [19.80173687261055]
  Anomaly awareness is essential for safety-critical applications such as autonomous driving. We propose a novel Synthetic-Unknown Data Generation to tackle the anomaly-aware semantic segmentation task. We reach the state-of-the-art performance on two anomaly segmentation datasets.
  arXiv  Detail & Related papers  (2021-11-29T06:24:50Z)
• Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection [56.22467011292147]
  Several incremental learning methods are proposed to mitigate catastrophic forgetting for object detection. Despite the effectiveness, these methods require co-occurrence of the unlabeled base classes in the training data of the novel classes. We propose the use of unlabeled in-the-wild data to bridge the non-occurrence caused by the missing base classes during the training of additional novel classes.
  arXiv  Detail & Related papers  (2021-10-28T10:57:25Z)
• Detecting Concept Drift With Neural Network Model Uncertainty [0.0]
  Uncertainty Drift Detection (UDD) is able to detect drifts without access to true labels. In contrast to input data-based drift detection, our approach considers the effects of the current input data on the properties of the prediction model. We show that UDD outperforms other state-of-the-art strategies on two synthetic as well as ten real-world data sets for both regression and classification tasks.
  arXiv  Detail & Related papers  (2021-07-05T08:56:36Z)
• STUDD: A Student-Teacher Method for Unsupervised Concept Drift Detection [10.326887191803275]
  We propose a novel approach to concept drift detection based on a student-teacher learning paradigm. At run-time, our approach is to use the teacher for predicting new instances and monitoring the mimicking loss of the student for concept drift detection. In a set of experiments using 19 data streams, we show that the proposed approach can detect concept drift and present a competitive behaviour.
  arXiv  Detail & Related papers  (2021-03-01T10:51:09Z)
• Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams [42.525141660788]
  We introduce a system to enable learning and prediction at any point in time. In contrast to the major body of work in continual learning, data streams are processed in an online fashion. We obtain state-of-the-art performance by a significant margin on eight benchmarks, including three highly imbalanced data streams.
  arXiv  Detail & Related papers  (2020-09-02T09:39:26Z)

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.