Fault Diagnosis in Chemical Processes Based on Class-Incremental FDA and PCA
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Access"
DOI: 10.1109/access.2019.2896056
Abstract: A class-incremental scheme of fisher discriminant analysis is proposed to improve the performance ofprocess fault diagnosis. Fisher discriminant analysis seeks directions which are efficient for discrimination and has excellent fault detection and diagnostic performance for… read more here.
Keywords: fisher discriminant; discriminant analysis; class incremental; fault ... See more keywords
Passive Sensing for Class-Incremental Human Activity Recognition
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Geoscience and Remote Sensing Letters"
DOI: 10.1109/lgrs.2023.3278091
Abstract: Passive sensing technology enables Wi-Fi-based human activity recognition (HAR), which has been widely noted in recent years. This letter presents a novel Wi-Fi-based class-incremental HAR system that allows for the gradual addition of new activity… read more here.
Keywords: human activity; passive sensing; activity; activity recognition ... See more keywords
Curiosity-Driven Class-Incremental Learning via Adaptive Sample Selection
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Circuits and Systems for Video Technology"
DOI: 10.1109/tcsvt.2022.3196092
Abstract: Modern artificial intelligence systems require class-incremental learning while suffering from catastrophic forgetting in many real-world applications. Due to the missing knowledge of past data, performance substantially degrades. Recent methods often used knowledge distillation and bias… read more here.
Keywords: sample; curiosity driven; incremental learning; catastrophic forgetting ... See more keywords
Anchor Assisted Experience Replay for Online Class-Incremental Learning
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Circuits and Systems for Video Technology"
DOI: 10.1109/tcsvt.2022.3219605
Abstract: Online class-incremental learning (OCIL) studies the problem of mitigating the phenomenon of catastrophic forgetting while learning new classes from a continuously non-stationary data stream. Existing approaches mainly constrain the updating of parameters to prevent the… read more here.
Keywords: anchor; incremental learning; online class; drift ... See more keywords
Class-Incremental Learning Network for Small Objects Enhancing of Semantic Segmentation in Aerial Imagery
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Geoscience and Remote Sensing"
DOI: 10.1109/tgrs.2021.3124303
Abstract: Due to the differences in the feature distribution between classes, when the model learns in a continuous data stream, it will encounter catastrophic forgetting. The incremental learning methods have shown great potential to solve this… read more here.
Keywords: network small; incremental learning; segmentation; small objects ... See more keywords
Class-Incremental Semantic Segmentation of Aerial Images via Pixel-Level Feature Generation and Task-Wise Distillation
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Geoscience and Remote Sensing"
DOI: 10.1109/tgrs.2022.3231351
Abstract: Deep neural networks achieve significant progress in semantic segmentation but still suffer from the catastrophic forgetting problem, i.e., networks will forget old classes as they learn new ones. In this article, we propose an effective… read more here.
Keywords: pixel level; task; segmentation; module ... See more keywords
Few-Shot Class-Incremental SAR Target Recognition Based on Hierarchical Embedding and Incremental Evolutionary Network
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Geoscience and Remote Sensing"
DOI: 10.1109/tgrs.2023.3248040
Abstract: It is difficult to realize effective synthetic aperture radar (SAR) automatic target recognition (ATR) in open scenarios because the ATR model cannot continuously learn from new classes with limited training samples. When adding new classes… read more here.
Keywords: incremental sar; class incremental; hierarchical embedding; sar ... See more keywords
Mine-Distill-Prototypes for Complete Few-Shot Class-Incremental Learning in Image Classification
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Geoscience and Remote Sensing"
DOI: 10.1109/tgrs.2023.3248601
Abstract: Recently, few-shot learning (FSL) has received increasing attention because of difficulties in sample collection in some application scenarios, such as maritime surveillance using synthetic aperture radar (SAR) or infrared images. In real situations of such… read more here.
Keywords: complete shot; distill; class; incremental learning ... See more keywords
Memorizing Complementation Network for Few-Shot Class-Incremental Learning
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2023.3236160
Abstract: Few-shot Class-Incremental Learning (FSCIL) aims at learning new concepts continually with only a few samples, which is prone to suffer the catastrophic forgetting and overfitting problems. The inaccessibility of old classes and the scarcity of… read more here.
Keywords: shot class; memorizing complementation; incremental learning; class incremental ... See more keywords
Few-Shot Class-Incremental Learning via Compact and Separable Features for Fine-Grained Vehicle Recognition
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Intelligent Transportation Systems"
DOI: 10.1109/tits.2022.3174662
Abstract: Most of the existing deep learning-based fine-grained vehicle recognition methods collect a large-scale training set in advance and train a model based on the closed-world assumption. However, in the real world, new classes of vehicles… read more here.
Keywords: compact separable; grained vehicle; class; incremental learning ... See more keywords
Self-Training for Class-Incremental Semantic Segmentation
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3155746
Abstract: In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned knowledge. To address this… read more here.
Keywords: incremental semantic; self training; class incremental; semantic segmentation ... See more keywords