paper-with-me

홈 › Papers

Multi-View Class Incremental Learning

2023-06-16 · Depeng Li, Tianqi Wang, Junwei Chen, Kenji Kawaguchi, Cheng Lian, Zhigang Zeng

Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance. To make MVL methods more practical in an open-ended environment, this paper investigates a novel paradigm called multi-view class incremental learning (MVCIL), where a single model incrementally classifies new classes from a continual stream of views, requiring no access to earlier views of data. However, MVCIL is challenged by the catastrophic forgetting of old information and the interference with learning new concepts. To address this, we first develop a randomization-based representation learning technique serving for feature extraction to guarantee their separate view-optimal working states, during which multiple views belonging to a class are presented sequentially; Then, we integrate them one by one in the orthogonality fusion subspace spanned by the extracted features; Finally, we introduce selective weight consolidation for learning-without-forgetting decision-making while encountering new classes. Extensive experiments on synthetic and real-world datasets validate the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2306.09675

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learningClass Incremental LearningDecision MakingIncremental LearningMULTI-VIEW LEARNINGRepresentation Learning

Similar Papers 제목 키워드 기반

Incremental Minimax Optimization based Fuzzy Clustering for Large Multi-view Data

2016-08-25 · Yangtao Wang, Lihui Chen, Xiao-Li Li

Incremental clustering approaches have been proposed for handling large data when given data set is too large to be stored. The key idea of these approaches is to find representatives to represent each cluster in each da…

Clustering

E2PL: Effective and Efficient Prompt Learning for Incomplete Multi-view Multi-Label Class Incremental Learning

2026-01-23 · Jiajun Chen, Yue Wu, Kai Huang, Wen Xi 외 arxiv

Multi-view multi-label classification (MvMLC) is indispensable for modern web applications aggregating information from diverse sources. However, real-world web-scale settings are rife with missing views and continuously…

Multi-Label ClassificationClass Incremental LearningContrastive Learning

Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection

2026-07-16 · Peisheng Qian, Jie Xu, Xulei Yang, Na Zhao arxiv

Incremental 3D object detection requires a detector to learn novel object classes while remembering previously learned ones over sequentially arriving data. Previous methods, primarily based on pseudo-labeling, perform r…

3D Object Detection

Few-shot Class-incremental Learning for Classification and Object Detection: A Survey

2023-08-13 · Jinghua Zhang, Li Liu, Olli Silvén, Matti Pietikäinen 외

Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML), as it necessitates the Incremental Learning (IL) of new classes from sparsely labeled training samples without forgetting …

class-incremental learningClass Incremental LearningClass-Incremental Object DetectionFew-Shot Class-Incremental Learning+5

Multi-View Correlation Distillation for Incremental Object Detection

2021-07-05 · Dongbao Yang, Yu Zhou, Weiping Wang

In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy of old data, sometimes it is impractica…

Objectobject-detectionObject Detection