Results 41 to 50 of about 842,651 (374)
Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning [PDF]
Computer Vision and Pattern RecognitionClass-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often results in the ...
Da-Wei Zhou +3 more
semanticscholar +1 more source
Class Incremental Online Streaming Learning
CoRR, 2021 A wide variety of methods have been developed to enable lifelong learning in conventional deep neural networks. However, to succeed, these methods require a `batch' of samples to be available and visited multiple times during training. While this works well in a static setting, these methods continue to suffer in a more realistic situation where data ...
Soumya Banerjee +4 more
openaire +2 more sources
Adaptive Class Incremental Learning-Based IoT Intrusion Detection System [PDF]
Jisuanji gongcheng, 2023 The conventional intrusion detection system for the Internet of Things(IoT) typically fails to detect new types of attacks in real time.Therefore, a new intrusion detection method for the IoT that is based on Stacked Sparse Autoencoders(SSAE) and Self ...
LIU Qiang, ZHANG Ying, ZHOU Weixiang, JIANG Xiantao, ZHOU Weina, ZHOU Mouguo
doaj +1 more source
Maintaining Discrimination and Fairness in Class Incremental Learning [PDF]
Computer Vision and Pattern Recognition, 2019 Deep neural networks (DNNs) have been applied in class incremental learning, which aims to solve common real-world problems of learning new classes continually. One drawback of standard DNNs is that they are prone to catastrophic forgetting.
Bowen Zhao +4 more
semanticscholar +1 more source
Self-Supervised Class Incremental Learning
CoRR, 2021 Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new. In this paper, we explore the performance of Self-Supervised representation
Zixuan Ni, Siliang Tang, Yueting Zhuang
openaire +2 more sources
Class Incremental Learning Method Integrating Balance Weight and Self-supervision [PDF]
Jisuanji kexue yu tansuoIn view of the catastrophic forgetting phenomenon of knowledge in class incremental learning in image classification, the existing class incremental learning methods focus on the correction of the unbalanced offset of the model classification layer ...
GONG Jiayi, XU Xinlei, XIAO Ting, WANG Zhe
doaj +1 more source
Hellinger Distance Trees for Imbalanced Streams [PDF]
, 2014 Classifiers trained on data sets possessing an imbalanced class distribution are known to exhibit poor generalisation performance. This is known as the imbalanced learning problem.
Brooke, J. M. +3 more
core +2 more sources
Boosting Deep Open World Recognition by Clustering [PDF]
, 2020 While convolutional neural networks have brought significant advances in robot vision, their ability is often limited to closed world scenarios, where the number of semantic concepts to be recognized is determined by the available training set.
Bulò, Samuel Rota +5 more
core +3 more sources
Incremental Sparse Bayesian Ordinal Regression [PDF]
, 2018 Ordinal Regression (OR) aims to model the ordering information between different data categories, which is a crucial topic in multi-label learning. An important class of approaches to OR models the problem as a linear combination of basis functions that ...
de Rijke, Maarten, Li, Chang
core +3 more sources
A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning [PDF]
International Conference on Learning Representations, 2022 Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement.
Da-Wei Zhou +3 more
semanticscholar +1 more source