14.2.6.1 Continunal Learning, Incremental Learning

Chapter Contents (Back)
Continual Learning. Active Learning. Incremental Learning. Online learning. Forgetting is one issue.
See also Intrepretation, Explaination, Understanding of Convolutional Neural Networks.
See also Forgetting, Learning without Forgetting, Convolutional Neural Networks.

Hong, Y.[Yi], Kwong, S.[Sam], Chang, Y.C.[Yu-Chou], Ren, Q.S.[Qing-Sheng],
Unsupervised feature selection using clustering ensembles and population based incremental learning algorithm,
PR(41), No. 9, September 2008, pp. 2742-2756.
Elsevier DOI 0806
Clustering ensembles; Dimensionality unbiased; Population based incremental learning algorithm; Unsupervised feature selection BibRef

Lughofer, E.[Edwin],
Extensions of vector quantization for incremental clustering,
PR(41), No. 3, March 2008, pp. 995-1011.
Elsevier DOI 0711
Vector quantization; Clustering; Incremental learning; New winning cluster selection strategy; Removing cluster satellites; Split-and-merge strategy; Image classification framework; Fault detection; Evolving fuzzy models BibRef

Jia, P.[Peng], Yin, J.S.[Jun-Song], Huang, X.S.[Xin-Sheng], Hu, D.[Dewen],
Incremental Laplacian eigenmaps by preserving adjacent information between data points,
PRL(30), No. 16, 1 December 2009, pp. 1457-1463.
Elsevier DOI 0911
Laplacian eigenmaps; Incremental learning; Locally linear construction; Nonlinear dimensionality reduction BibRef

Li, H.S.[Hou-Sen], Jiang, H.[Hao], Barrio, R.[Roberto], Liao, X.K.[Xiang-Ke], Cheng, L.Z.[Li-Zhi], Su, F.[Fang],
Incremental manifold learning by spectral embedding methods,
PRL(32), No. 10, 15 July 2011, pp. 1447-1455.
Elsevier DOI 1106
Manifold learning; Incremental learning; Dimensionality reduction; Spectral embedding methods; Hessian eigenmaps BibRef

Lu, G.F.[Gui-Fu], Jian, Z.[Zou], Wang, Y.[Yong],
Incremental learning from chunk data for IDR/QR,
IVC(36), No. 1, 2015, pp. 1-8.
Elsevier DOI 1504
Feature extraction incremental dimension reduction. BibRef

Le, T.B.[Thanh-Binh], Kim, S.W.[Sang-Woon],
On incrementally using a small portion of strong unlabeled data for semi-supervised learning algorithms,
PRL(41), No. 1, 2014, pp. 53-64.
Elsevier DOI 1403
Semi-supervised learning BibRef

Zhang, Z., Li, Y., Zhang, Z., Jin, C., Gao, M.,
Adaptive Matrix Sketching and Clustering for Semisupervised Incremental Learning,
SPLetters(25), No. 7, July 2018, pp. 1069-1073.
IEEE DOI 1807
learning (artificial intelligence), matrix algebra, pattern classification, adaptive matrix sketching, semisupervised classification BibRef

Li, Y.C.[Yan-Chao], Wang, Y.L.[Yong-Li], Liu, Q.[Qi], Bi, C.[Cheng], Jiang, X.H.[Xiao-Hui], Sun, S.R.[Shu-Rong],
Incremental semi-supervised learning on streaming data,
PR(88), 2019, pp. 383-396.
Elsevier DOI 1901
Semi-supervised learning, Dynamic feature learning, Streaming data, Classification BibRef

Besedin, A.[Andrey], Blanchart, P.[Pierre], Crucianu, M.[Michel], Ferecatu, M.[Marin],
Deep online classification using pseudo-generative models,
CVIU(201), 2020, pp. 103048.
Elsevier DOI 2011
Avoid issues of forgetting. Deep learning, Online learning, Pseudo-generative models, Stream learning BibRef

Peng, C.[Can], Zhao, K.[Kun], Lovell, B.C.[Brian C.],
Faster ILOD: Incremental learning for object detectors based on faster RCNN,
PRL(140), 2020, pp. 109-115.
Elsevier DOI 2012
Deep learning, Object detection, Incremental learning BibRef

Wang, G.X.[Guang-Xing], Ren, P.[Peng],
Hyperspectral Image Classification with Feature-Oriented Adversarial Active Learning,
RS(12), No. 23, 2020, pp. xx-yy.
DOI Link 2012
BibRef

Xiang, S.C.[Sun-Cheng], Fu, Y.Z.[Yu-Zhuo], Liu, T.[Ting],
Progressive learning with style transfer for distant domain adaptation,
IET-IPR(14), No. 14, December 2020, pp. 3527-3535.
DOI Link 2012
BibRef

Berger, K.[Katja], Caicedo, J.P.R.[Juan Pablo Rivera], Martino, L.[Luca], Wocher, M.[Matthias], Hank, T.[Tobias], Verrelst, J.[Jochem],
A Survey of Active Learning for Quantifying Vegetation Traits from Terrestrial Earth Observation Data,
RS(13), No. 2, 2021, pp. xx-yy.
DOI Link 2101
Survey, Active Learning. BibRef

Li, J.[Jia], Song, Y.F.[Ya-Fei], Zhu, J.F.[Jian-Feng], Cheng, L.L.[Le-Le], Su, Y.[Ying], Ye, L.[Lin], Yuan, P.C.[Peng-Cheng], Han, S.M.[Shu-Min],
Learning From Large-Scale Noisy Web Data With Ubiquitous Reweighting for Image Classification,
PAMI(43), No. 5, May 2021, pp. 1808-1814.
IEEE DOI 2104
Noise measurement, Deep learning, Task analysis, Training, Annotations, Solid modeling, Visualization, Image classification, deep learning BibRef

Gweon, H.[Hyukjun], Yu, H.[Hao],
A nearest neighbor-based active learning method and its application to time series classification,
PRL(146), 2021, pp. 230-236.
Elsevier DOI 2105
Active learning, Batch mode, Time series classification, Nearest neighbor BibRef

Wang, Y.[Yi], Ding, Y.[Yi], He, X.J.[Xiang-Jian], Fan, X.[Xin], Lin, C.[Chi], Li, F.Q.[Feng-Qi], Wang, T.Z.[Tian-Zhu], Luo, Z.X.[Zhong-Xuan], Luo, J.B.[Jie-Bo],
Novelty Detection and Online Learning for Chunk Data Streams,
PAMI(43), No. 7, July 2021, pp. 2400-2412.
IEEE DOI 2106
Kernel, Data models, Linear systems, Fans, Hilbert space, Streaming media, Feature extraction, Data stream, online learning BibRef

Fonseca, J.[Joao], Douzas, G.[Georgios], Bacao, F.[Fernando],
Increasing the Effectiveness of Active Learning: Introducing Artificial Data Generation in Active Learning for Land Use/Land Cover Classification,
RS(13), No. 13, 2021, pp. xx-yy.
DOI Link 2107
BibRef

Celik, B.[Bilge], Vanschoren, J.[Joaquin],
Adaptation Strategies for Automated Machine Learning on Evolving Data,
PAMI(43), No. 9, September 2021, pp. 3067-3078.
IEEE DOI 2108
Pipelines, Adaptation models, Machine learning, Optimization, Data models, Task analysis, Bayes methods, AutoML, data streams, adaptation strategies BibRef

Zheng, X.[Xiawu], Zhang, Y.[Yang], Hong, S.[Sirui], Li, H.X.[Hui-Xia], Tang, L.[Lang], Xiong, Y.[Youcheng], Zhou, J.[Jin], Wang, Y.[Yan], Sun, X.S.[Xiao-Shuai], Zhu, P.F.[Peng-Fei], Wu, C.[Chenglin], Ji, R.R.[Rong-Rong],
Evolving Fully Automated Machine Learning via Life-Long Knowledge Anchors,
PAMI(43), No. 9, September 2021, pp. 3091-3107.
IEEE DOI 2108
Pipelines, Task analysis, Optimization, Data models, Computational modeling, Training, Search problems, evolutionary algorithm BibRef

Wang, K.[Kai], van de Weijer, J.[Joost], Herranz, L.[Luis],
ACAE-REMIND for online continual learning with compressed feature replay,
PRL(150), 2021, pp. 122-129.
Elsevier DOI 2109
online continual learning, autoencoders, vector quantization BibRef

Agarwal, M.[Mridul], Aggarwal, V.[Vaneet],
Blind decision making: Reinforcement learning with delayed observations,
PRL(150), 2021, pp. 176-182.
Elsevier DOI 2109
BibRef

Grigoletto, R.[Riccardo], Maiettini, E.[Elisa], Natale, L.[Lorenzo],
Score to Learn: A Comparative Analysis of Scoring Functions for Active Learning in Robotics,
CVS21(55-67).
Springer DOI 2109
BibRef

Dong, J.H.[Jia-Hua], Cong, Y.[Yang], Sun, G.[Gan], Zhang, T.[Tao],
Lifelong robotic visual-tactile perception learning,
PR(121), 2022, pp. 108176.
Elsevier DOI 2109
Lifelong machine learning, Robotics, Visual-tactile perception, Cross-modality learning, Multi-task learning BibRef


Yan, Z.[Zike], Wang, X.[Xin], Zha, H.B.[Hong-Bin],
Online Learning of a Probabilistic and Adaptive Scene Representation,
CVPR21(13106-13116)
IEEE DOI 2111
Geometry, Adaptation models, Computational modeling, Mixture models, Probability density function, Data models BibRef

Pang, B.[Bo], Peng, G.[Gao], Li, Y.Z.[Yi-Zhuo], Lu, C.[Cewu],
PGT: A Progressive Method for Training Models on Long Videos,
CVPR21(11374-11384)
IEEE DOI 2111
Training, Convolutional codes, Computational modeling, Video sequences, Semantics, Markov processes BibRef

Wang, X.D.[Xu-Dong], Lian, L.[Long], Yu, S.X.[Stella X.],
Unsupervised Visual Attention and Invariance for Reinforcement Learning,
CVPR21(6673-6683)
IEEE DOI 2111
Training, Visualization, Annotations, Reinforcement learning, Manuals, Benchmark testing BibRef

Singh, P.[Pravendra], Mazumder, P.[Pratik], Rai, P.[Piyush], Namboodiri, V.P.[Vinay P.],
Rectification-based Knowledge Retention for Continual Learning,
CVPR21(15277-15286)
IEEE DOI 2111
Learning systems, Training, Deep learning, Adaptation models, Pattern recognition, Task analysis BibRef

Shi, Y.J.[Yu-Jun], Yuan, L.[Li], Chen, Y.P.[Yun-Peng], Feng, J.[Jiashi],
Continual Learning via Bit-Level Information Preserving,
CVPR21(16669-16678)
IEEE DOI 2111
Quantization (signal), Costs, Neural networks, Memory management, Reinforcement learning, Distance measurement, Pattern recognition BibRef

Verma, V.K.[Vinay Kumar], Liang, K.J.[Kevin J], Mehta, N.[Nikhil], Rai, P.[Piyush], Carin, L.[Lawrence],
Efficient Feature Transformations for Discriminative and Generative Continual Learning,
CVPR21(13860-13870)
IEEE DOI 2111
Learning systems, Computational modeling, Scalability, Neural networks, Transforms, Predictive models BibRef

Tang, S.X.[Shi-Xiang], Chen, D.P.[Da-Peng], Zhu, J.[Jinguo], Yu, S.J.[Shi-Jie], Ouyang, W.L.[Wan-Li],
Layerwise Optimization by Gradient Decomposition for Continual Learning,
CVPR21(9629-9638)
IEEE DOI 2111
Knowledge engineering, Deep learning, Computational modeling, Benchmark testing, Pattern recognition, Task analysis BibRef

Wang, S.P.[Shi-Peng], Li, X.R.[Xiao-Rong], Sun, J.[Jian], Xu, Z.B.[Zong-Ben],
Training Networks in Null Space of Feature Covariance for Continual Learning,
CVPR21(184-193)
IEEE DOI 2111
Training, Null space, Benchmark testing, Approximation algorithms, Stability analysis, Pattern recognition BibRef

Volpi, R.[Riccardo], Larlus, D.[Diane], Rogez, G.[Grégory],
Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning,
CVPR21(4441-4451)
IEEE DOI 2111
Visualization, Adaptation models, Image segmentation, Computational modeling, Semantics, Pattern recognition BibRef

Bang, J.[Jihwan], Kim, H.[Heesu], Yoo, Y.J.[Young-Joon], Ha, J.W.[Jung-Woo], Choi, J.H.[Jong-Hyun],
Rainbow Memory: Continual Learning with a Memory of Diverse Samples,
CVPR21(8214-8223)
IEEE DOI 2111
Training, Uncertainty, Codes, Memory management, Learning (artificial intelligence), Sampling methods BibRef

Simon, C.[Christian], Koniusz, P.[Piotr], Harandi, M.[Mehrtash],
On Learning the Geodesic Path for Incremental Learning,
CVPR21(1591-1600)
IEEE DOI 2111
Manifolds, Knowledge engineering, Neural networks, Linear programming, Pattern recognition, Task analysis BibRef

Wu, Z.Y.[Zi-Yang], Baek, C.[Christina], You, C.[Chong], Ma, Y.[Yi],
Incremental Learning via Rate Reduction,
CVPR21(1125-1133)
IEEE DOI 2111
Deep learning, Training, Backpropagation, Computational modeling, Computer architecture, Data models BibRef

Cheraghian, A.[Ali], Rahman, S.[Shafin], Fang, P.F.[Peng-Fei], Roy, S.K.[Soumava Kumar], Petersson, L.[Lars], Harandi, M.[Mehrtash],
Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning,
CVPR21(2534-2543)
IEEE DOI 2111
Training, Visualization, Semantics, Training data, Power capacitors, Pattern recognition BibRef

Liu, Y.Y.[Yao-Yao], Schiele, B.[Bernt], Sun, Q.[Qianru],
Adaptive Aggregation Networks for Class-Incremental Learning,
CVPR21(2544-2553)
IEEE DOI 2111
Adaptation models, Adaptive systems, Computer architecture, Network architecture, Benchmark testing, Stability analysis BibRef

Yan, S.P.[Shi-Peng], Xie, J.W.[Jiang-Wei], He, X.M.[Xu-Ming],
DER: Dynamically Expandable Representation for Class Incremental Learning,
CVPR21(3013-3022)
IEEE DOI 2111
Visualization, Adaptation models, Benchmark testing, Feature extraction, Pattern recognition, Complexity theory BibRef

Hu, X.[Xinting], Tang, K.[Kaihua], Miao, C.Y.[Chun-Yan], Hua, X.S.[Xian-Sheng], Zhang, H.[Hanwang],
Distilling Causal Effect of Data in Class-Incremental Learning,
CVPR21(3956-3965)
IEEE DOI 2111
Training, Costs, Streaming media, Benchmark testing, Pattern recognition, Reliability BibRef

Wang, L.Y.[Li-Yuan], Yang, K.[Kuo], Li, C.X.[Chong-Xuan], Hong, L.Q.[Lan-Qing], Li, Z.G.[Zhen-Guo], Zhu, J.[Jun],
ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning,
CVPR21(5379-5388)
IEEE DOI 2111
Deep learning, Systematics, Semisupervised learning, Benchmark testing, Generators BibRef

Zhu, F.[Fei], Zhang, X.Y.[Xu-Yao], Wang, C.[Chuang], Yin, F.[Fei], Liu, C.L.[Cheng-Lin],
Prototype Augmentation and Self-Supervision for Incremental Learning,
CVPR21(5867-5876)
IEEE DOI 2111
Training, Learning systems, Deep learning, Data privacy, Computational modeling, Prototypes BibRef

Zhu, K.[Kai], Cao, Y.[Yang], Zhai, W.[Wei], Cheng, J.[Jie], Zha, Z.J.[Zheng-Jun],
Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning,
CVPR21(6797-6806)
IEEE DOI 2111
Adaptation models, Computational modeling, Prototypes, Benchmark testing, Power capacitors, Pattern recognition BibRef

Abdelsalam, M.[Mohamed], Faramarzi, M.[Mojtaba], Sodhani, S.[Shagun], Chandar, S.[Sarath],
IIRC: Incremental Implicitly-Refined Classification,
CVPR21(11033-11042)
IEEE DOI 2111
Analytical models, Computational modeling, Benchmark testing, Prediction algorithms, Pattern recognition, Classification algorithms BibRef

Zhang, C.[Chi], Song, N.[Nan], Lin, G.[Guosheng], Zheng, Y.[Yun], Pan, P.[Pan], Xu, Y.[Yinghui],
Few-Shot Incremental Learning with Continually Evolved Classifiers,
CVPR21(12450-12459)
IEEE DOI 2111
Adaptation models, Machine learning algorithms, Training data, Benchmark testing, Power capacitors, Pattern recognition BibRef

Shukla, M.[Megh], Ahmed, S.[Shuaib],
A Mathematical Analysis of Learning Loss for Active Learning in Regression,
TCV21(3315-3323)
IEEE DOI 2109
Training, Industries, Fault diagnosis, Computational modeling, Pose estimation, Refining, Mathematical analysis BibRef

Rakesh, V.[Vineeth], Jain, S.[Swayambhoo],
Efficacy of Bayesian Neural Networks in Active Learning,
LLID21(2601-2609)
IEEE DOI 2109
Uncertainty, Monte Carlo methods, Neural networks, Estimation, Machine learning, Data models BibRef

Masana, M.[Marc], Tuytelaars, T.[Tinne], van de Weijer, J.[Joost],
Ternary Feature Masks: zero-forgetting for task-incremental learning,
CLVision21(3565-3574)
IEEE DOI 2109
Scalability, Encoding, Pattern recognition, Computational efficiency, Task analysis BibRef

van de Ven, G.M.[Gido M.], Li, Z.[Zhe], Tolias, A.S.[Andreas S.],
Class-Incremental Learning with Generative Classifiers,
CLVision21(3606-3615)
IEEE DOI 2109
Training, Learning systems, Deep learning, Monte Carlo methods, Benchmark testing BibRef

Sun, W.J.[Wen-Ju], Zhang, J.[Jing], Wang, D.Y.[Dan-Yu], Geng, Y.A.[Yangli-Ao], Li, Q.Y.[Qing-Yong],
ILCOC: An Incremental Learning Framework based on Contrastive One-class Classifiers,
CLVision21(3575-3583)
IEEE DOI 2109
Degradation, Heuristic algorithms, Computational modeling, Pattern recognition, Classification algorithms BibRef

Jiang, J.[Jian], Cetin, E.[Edoardo], Celiktutan, O.[Oya],
IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay,
CLVision21(3528-3537)
IEEE DOI 2109
Training, Image coding, Memory management, Machine learning, Pattern recognition BibRef

Mittal, S.[Sudhanshu], Galesso, S.[Silvio], Brox, T.[Thomas],
Essentials for Class Incremental Learning,
CLVision21(3508-3517)
IEEE DOI 2109
Learning systems, Art, Neural networks, Training data, Boosting BibRef

Choi, Y.[Yoojin], El-Khamy, M.[Mostafa], Lee, J.[Jungwon],
Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay,
CLVision21(3538-3547)
IEEE DOI 2109
Data privacy, Training data, Data models, Pattern recognition, Knowledge transfer BibRef

Douillard, A.[Arthur], Valle, E.[Eduardo], Ollion, C.[Charles], Robert, T.[Thomas], Cord, M.[Matthieu],
Insights from the Future for Continual Learning,
CLVision21(3477-3486)
IEEE DOI 2109
Training, Computational modeling, Training data, Pattern recognition, Task analysis BibRef

Hayes, T.L.[Tyler L.], Kanan, C.[Christopher],
Selective Replay Enhances Learning in Online Continual Analogical Reasoning,
CLVision21(3497-3507)
IEEE DOI 2109
Measurement, Protocols, Neural networks, Reinforcement learning, Streaming media, Cognition, Pattern recognition BibRef

Kuo, N.I.H.[Nicholas I-Hsien], Harandi, M.[Mehrtash], Fourrier, N.[Nicolas], Walder, C.[Christian], Ferraro, G.[Gabriela], Suominen, H.[Hanna],
Plastic and Stable Gated Classifiers for Continual Learning,
CLVision21(3548-3553)
IEEE DOI 2109
Training, Knowledge engineering, Neural networks, Logic gates, Feature extraction, Robustness BibRef

Mai, Z.[Zheda], Li, R.[Ruiwen], Kim, H.W.[Hyun-Woo], Sanner, S.[Scott],
Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning,
CLVision21(3584-3594)
IEEE DOI 2109
Training, Performance gain, Pattern recognition BibRef

Lomonaco, V.[Vincenzo], Pellegrini, L.[Lorenzo], Cossu, A.[Andrea], Carta, A.[Antonio], Graffieti, G.[Gabriele], Hayes, T.L.[Tyler L.], de Lange, M.[Matthias], Masana, M.[Marc], Pomponi, J.[Jary], van de Ven, G.M.[Gido M.], Mundt, M.[Martin], She, Q.[Qi], Cooper, K.[Keiland], Forest, J.[Jeremy], Belouadah, E.[Eden], Calderara, S.[Simone], Parisi, G.I.[German I.], Cuzzolin, F.[Fabio], Tolias, A.S.[Andreas S.], Scardapane, S.[Simone], Antiga, L.[Luca], Ahmad, S.[Subutai], Popescu, A.[Adrian], Kanan, C.[Christopher], van de Weijer, J.[Joost], Tuytelaars, T.[Tinne], Bacciu, D.[Davide], Maltoni, D.[Davide],
Avalanche: an End-to-End Library for Continual Learning,
CLVision21(3595-3605)
IEEE DOI 2109
Training, Deep learning, Machine learning algorithms, Collaboration, Libraries BibRef

Mirzadeh, S.I.[Seyed Iman], Ghasemzadeh, H.[Hassan],
CL-Gym: Full-Featured PyTorch Library for Continual Learning,
OmniCV21(3616-3622)
IEEE DOI 2109
Philosophical considerations, Computer architecture, Learning (artificial intelligence), Libraries BibRef

Korycki, L.[Lukasz], Krawczyk, B.[Bartosz],
Class-Incremental Experience Replay for Continual Learning under Concept Drift,
OmniCV21(3644-3653)
IEEE DOI 2109
Computer architecture, Machine learning, Data mining, Task analysis BibRef

Bagi, A.M.[Alexandra M.], Schild, K.I.[Kim I.], Khan, O.S.[Omar Shahbaz], Zahálka, J.[Jan], Jónsson, B.Þ.[Björn Þór],
XQM: Interactive Learning on Mobile Phones,
MMMod21(II:281-293).
Springer DOI 2106
BibRef

Shi, F.F.[Fei-Fei], Wang, P.[Peng], Shi, Z.C.[Zhong-Chao], Rui, Y.[Yong],
Selecting Useful Knowledge from Previous Tasks for Future Learning in a Single Network,
ICPR21(9727-9732)
IEEE DOI 2105
Knowledge engineering, Learning systems, Network architecture, Iterative methods, Task analysis BibRef

Jarboui, F.[Firas], Perchet, V.[Vianney],
Trajectory representation learning for Multi-Task NMRDP planning,
ICPR21(6786-6793)
IEEE DOI 2105
Non Markovian Reward Decision Processes. Bridges, Reinforcement learning, Markov processes, Trajectory, Planning, Task analysis BibRef

Lechat, A.[Alexis], Herbin, S.[Stéphane], Jurie, F.[Frédéric],
Semi-Supervised Class Incremental Learning,
ICPR21(10383-10389)
IEEE DOI 2105
Training, Protocols, Image reconstruction BibRef

Chang, X.Y.[Xin-Yuan], Tao, X.Y.[Xiao-Yu], Hong, X.P.[Xiao-Peng], Wei, X.[Xing], Ke, W.[Wei], Gong, Y.H.[Yi-Hong],
Class-Incremental Learning with Topological Schemas of Memory Spaces,
ICPR21(9719-9726)
IEEE DOI 2105
Multiprotocol label switching, Manifolds, Knowledge engineering, Adaptation models, Network topology, Neural networks, Topological Schemas Model BibRef

Pernici, F.[Federico], Bruni, M.[Matteo], Baecchi, C.[Claudio], Turchini, F.[Francesco], del Bimbo, A.[Alberto],
Class-incremental Learning with Pre-allocated Fixed Classifiers,
ICPR21(6259-6266)
IEEE DOI 2105
Training, Knowledge engineering, Neural networks, Standards, Faces BibRef

Buzzega, P.[Pietro], Boschini, M.[Matteo], Porrello, A.[Angelo], Calderara, S.[Simone],
Rethinking Experience Replay: a Bag of Tricks for Continual Learning,
ICPR21(2180-2187)
IEEE DOI 2105
Degradation, Neural networks, Proposals, Erbium, Standards BibRef

Fidalgo-Merino, R.[Raúl], Gabrielli, L.[Lorenzo], Checchi, E.[Enrico],
Leveraging Sequential Pattern Information for Active Learning from Sequential Data,
ICPR21(6957-6964)
IEEE DOI 2105
Training, Machine learning algorithms, Annotations, Databases, Manuals, Machine learning, Data models BibRef

Agarwal, A.[Arvind], Mujumdar, S.[Shashank], Gupta, N.[Nitin], Mehta, S.[Sameep],
Budgeted Batch Mode Active Learning with Generalized Cost and Utility Functions,
ICPR21(7692-7698)
IEEE DOI 2105
Learning systems, Training data, Cost function, Data models, Labeling BibRef

Herde, M.[Marek], Kottke, D.[Daniel], Huseljic, D.[Denis], Sick, B.[Bernhard],
Multi-Annotator Probabilistic Active Learning,
ICPR21(10281-10288)
IEEE DOI 2105
Training, Deep learning, Annotations, Computational modeling, Employment, Manuals, Gaussian processes BibRef

Arnavaz, K.[Kasra], Feragen, A.[Aasa], Krause, O.[Oswin], Loog, M.[Marco],
Bayesian Active Learning for Maximal Information Gain on Model Parameters,
ICPR21(10524-10531)
IEEE DOI 2105
Machine learning, Data models, Bayes methods, Logistics BibRef

Li, M.[Minghan], Liu, X.[Xialei], van de Weijer, J.[Joost], Raducanu, B.[Bogdan],
Learning to Rank for Active Learning: A Listwise Approach,
ICPR21(5587-5594)
IEEE DOI 2105
Training, Measurement, Correlation, Prediction algorithms, Classification algorithms, Labeling BibRef

Siméoni, O.[Oriane], Budnik, M.[Mateusz], Avrithis, Y.[Yannis], Gravier, G.[Guillaume],
Rethinking deep active learning: Using unlabeled data at model training,
ICPR21(1220-1227)
IEEE DOI 2105
Training, Deep learning, Pipelines, Semisupervised learning, Data models, Image classification BibRef

Li, C.[Cheng], Rana, S.[Santu], Gill, A.[Andrew], Nguyen, D.[Dang], Gupta, S.I.[Sun-Il], Venkatesh, S.[Svetha],
Factor Screening using Bayesian Active Learning and Gaussian Process Meta-Modelling,
ICPR21(3288-3295)
IEEE DOI 2105
Gaussian processes, Length measurement, Entropy, Bayes methods, Kernel, Factor screening, Gaussian Process BibRef

Li, X.O.[Xia-Obin], Shan, L.[Lianlei], Li, M.[Minglong], Wang, W.Q.[Wei-Qiang],
Energy Minimum Regularization in Continual Learning,
ICPR21(6404-6409)
IEEE DOI 2105
Learning systems, Sensitivity, Animals, Solids, Minimization, Pattern recognition, Task analysis BibRef

Ho, C.H.[Chih-Hsing], Tsai, S.H.L.[Shang-Ho Lawrence],
RSAC: Regularized Subspace Approximation Classifier for Lightweight Continuous Learning,
ICPR21(6680-6687)
IEEE DOI 2105
Training, Memory management, Training data, Approximation algorithms, Classification algorithms, Streaming Learning BibRef

Lei, C.H.[Cheng-Hsun], Chen, Y.H.[Yi-Hsin], Peng, W.H.[Wen-Hsiao], Chiu, W.C.[Wei-Chen],
Class-Incremental Learning with Rectified Feature-Graph Preservation,
ACCV20(VI:358-374).
Springer DOI 2103
Learn new classes as they arrive. BibRef

Chan, D.M.[David M.], Vijayanarasimhan, S.[Sudheendra], Ross, D.A.[David A.], Canny, J.F.[John F.],
Active Learning for Video Description with Cluster-regularized Ensemble Ranking,
ACCV20(V:443-459).
Springer DOI 2103
BibRef

Wang, S.[Shuo], Li, Y.X.[Yue-Xiang], Ma, K.[Kai], Ma, R.[Ruhui], Guan, H.B.[Hai-Bing], Zheng, Y.F.[Ye-Feng],
Dual Adversarial Network for Deep Active Learning,
ECCV20(XXIV:680-696).
Springer DOI 2012
BibRef

Lin, Z.[Zudi], Wei, D.[Donglai], Jang, W.D.[Won-Dong], Zhou, S.[Siyan], Chen, X.[Xupeng], Wang, X.[Xueying], Schalek, R.[Richard], Berger, D.[Daniel], Matejek, B.[Brian], Kamentsky, L.[Lee], Peleg, A.[Adi], Haehn, D.[Daniel], Jones, T.[Thouis], Parag, T.[Toufiq], Lichtman, J.[Jeff], Pfister, H.[Hanspeter],
Two Stream Active Query Suggestion for Active Learning in Connectomics,
ECCV20(XVIII:103-120).
Springer DOI 2012
BibRef

Ebrahimi, S.[Sayna], Meier, F.[Franziska], Calandra, R.[Roberto], Darrell, T.J.[Trevor J.], Rohrbach, M.[Marcus],
Adversarial Continual Learning,
ECCV20(XI:386-402).
Springer DOI 2011
BibRef

Kim, C.D.[Chris Dongjoo], Jeong, J.[Jinseo], Kim, G.[Gunhee],
Imbalanced Continual Learning with Partitioning Reservoir Sampling,
ECCV20(XIII:411-428).
Springer DOI 2011
BibRef

Kim, E.S., Kim, J.U., Lee, S., Moon, S.K., Ro, Y.M.,
Class Incremental Learning With Task-Selection,
ICIP20(1846-1850)
IEEE DOI 2011
Task analysis, Learning systems, Image reconstruction, Feature extraction, Training, Testing, Data models, Deep learning, autoencoder BibRef

Yao, X., Sun, L.,
Continual Local Training For Better Initialization Of Federated Models,
ICIP20(1736-1740)
IEEE DOI 2011
Training, Data models, Servers, Task analysis, Computational modeling, Distributed databases, Optimization, Generalization BibRef

Gao, M.F.[Ming-Fei], Zhang, Z.Z.[Zi-Zhao], Yu, G.[Guo], Arik, S.Ö.[Sercan Ö.], Davis, L.S.[Larry S.], Pfister, T.[Tomas],
Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost,
ECCV20(X:510-526).
Springer DOI 2011
BibRef

Chaplot, D.S.[Devendra Singh], Jiang, H.[Helen], Gupta, S.[Saurabh], Gupta, A.[Abhinav],
Semantic Curiosity for Active Visual Learning,
ECCV20(VI:309-326).
Springer DOI 2011
BibRef

Fini, E.[Enrico], Lathuilière, S.[Stéphane], Sangineto, E.[Enver], Nabi, M.[Moin], Ricci, E.[Elisa],
Online Continual Learning Under Extreme Memory Constraints,
ECCV20(XXVIII:720-735).
Springer DOI 2011
BibRef

Agarwal, S.[Sharat], Arora, H.[Himanshu], Anand, S.[Saket], Arora, C.[Chetan],
Contextual Diversity for Active Learning,
ECCV20(XVI: 137-153).
Springer DOI 2010
BibRef

Iscen, A.[Ahmet], Zhang, J.[Jeffrey], Lazebnik, S.[Svetlana], Schmid, C.[Cordelia],
Memory-efficient Incremental Learning Through Feature Adaptation,
ECCV20(XVI: 699-715).
Springer DOI 2010
BibRef

Yu, L., Twardowski, B., Liu, X., Herranz, L., Wang, K., Cheng, Y., Jui, S., van de Weijer, J.,
Semantic Drift Compensation for Class-Incremental Learning,
CVPR20(6980-6989)
IEEE DOI 2008
Task analysis, Training, Prototypes, Semantics, Measurement, Neurons, Computer vision BibRef

Zhao, B., Xiao, X., Gan, G., Zhang, B., Xia, S.,
Maintaining Discrimination and Fairness in Class Incremental Learning,
CVPR20(13205-13214)
IEEE DOI 2008
Training, Task analysis, Data models, Error analysis, Neural networks, Standards BibRef

Rajasegaran, J., Khan, S., Hayat, M., Khan, F.S., Shah, M.,
iTAML: An Incremental Task-Agnostic Meta-learning Approach,
CVPR20(13585-13594)
IEEE DOI 2008
Task analysis, Adaptation models, Training, Stability analysis, Interference, Predictive models, Heuristic algorithms BibRef

He, J., Mao, R., Shao, Z., Zhu, F.,
Incremental Learning in Online Scenario,
CVPR20(13923-13932)
IEEE DOI 2008
Data models, Machine learning, Training, Task analysis, Feature extraction, Predictive models, Learning systems BibRef

Mi, F., Kong, L., Lin, T., Yu, K., Faltings, B.,
Generalized Class Incremental Learning,
CLVision20(970-974)
IEEE DOI 2008
Erbium, Training, Data models, Computational modeling, Probabilistic logic, Machine learning, Task analysis BibRef

Ayub, A., Wagner, A.R.,
Cognitively-Inspired Model for Incremental Learning Using a Few Examples,
CLVision20(897-906)
IEEE DOI 2008
Feature extraction, Task analysis, Training, Machine learning, Training data, Data models, Hippocampus BibRef

Hayes, T.L., Kanan, C.,
Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis,
CLVision20(887-896)
IEEE DOI 2008
Streaming media, Covariance matrices, Training, Computational modeling, Neural networks, Task analysis, Linear discriminant analysis BibRef

Dhar, P.[Prithviraj], Singh, R.V.[Rajat Vikram], Peng, K.C.[Kuan-Chuan], Wu, Z.[Ziyan], Chellappa, R.[Rama],
Learning Without Memorizing,
CVPR19(5133-5141).
IEEE DOI 2002
Incremental learning, but can't store the whole past. BibRef

Hou, S.H.[Sai-Hui], Pan, X.Y.[Xin-Yu], Loy, C.C.[Chen Change], Wang, Z.L.[Zi-Lei], Lin, D.H.[Da-Hua],
Learning a Unified Classifier Incrementally via Rebalancing,
CVPR19(831-839).
IEEE DOI 2002
BibRef

Belouadah, E.[Eden], Popescu, A.[Adrian],
DeeSIL: Deep-Shallow Incremental Learning,
TASKCV18(II:151-157).
Springer DOI 1905
BibRef

Castro, F.M.[Francisco M.], Marín-Jiménez, M.J.[Manuel J.], Guil, N.[Nicolás], Schmid, C.[Cordelia], Alahari, K.[Karteek],
End-to-End Incremental Learning,
ECCV18(XII: 241-257).
Springer DOI 1810
BibRef

Prabhu, A.[Ameya], Torr, P.H.S.[Philip H. S.], Dokania, P.K.[Puneet K.],
GDUMB: A Simple Approach that Questions Our Progress in Continual Learning,
ECCV20(II:524-540).
Springer DOI 2011
BibRef

Chaudhry, A.[Arslan], Dokania, P.K.[Puneet K.], Ajanthan, T.[Thalaiyasingam], Torr, P.H.S.[Philip H. S.],
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence,
ECCV18(XI: 556-572).
Springer DOI 1810
BibRef

Lomonaco, V., Maltoni, D., Pellegrini, L.,
Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches,
CLVision20(989-998)
IEEE DOI 2008
Training, Robots, Videos, Object recognition, Benchmark testing, Computer architecture, Computational modeling BibRef

Silver, D.L., Mahfuz, S.,
Generating Accurate Pseudo Examples for Continual Learning,
CLVision20(1035-1042)
IEEE DOI 2008
Task analysis, Training, Probability distribution, Knowledge engineering, Input variables, Neural networks BibRef

Parshotam, K., Kilickaya, M.,
Continual Learning of Object Instances,
CLVision20(907-914)
IEEE DOI 2008
Automobiles, Task analysis, Measurement, Training, Data models, Visualization, Companies BibRef

Liu, X., Wu, C., Menta, M., Herranz, L., Raducanu, B., Bagdanov, A.D., Jui, S., van de Weijer, J.,
Generative Feature Replay For Class-Incremental Learning,
CLVision20(915-924)
IEEE DOI 2008
Task analysis, Feature extraction, Image generation, Correlation, Training, Generators BibRef

Mirzadeh, S.I., Farajtabar, M., Ghasemzadeh, H.,
Dropout as an Implicit Gating Mechanism For Continual Learning,
CLVision20(945-951)
IEEE DOI 2008
Task analysis, Neurons, Stability analysis, Training, Standards, Logic gates, Knowledge engineering BibRef

Liu, Y., Su, Y., Liu, A., Schiele, B., Sun, Q.,
Mnemonics Training: Multi-Class Incremental Learning Without Forgetting,
CVPR20(12242-12251)
IEEE DOI 2008
Training, Optimization, Data models, Computational modeling, Generative adversarial networks, Training data BibRef

Zhang, J.[Jie], Zhang, J.T.[Jun-Ting], Ghosh, S.[Shalini], Li, D.[Dawei], Zhu, J.W.[Jing-Wen], Zhang, H.M.[He-Ming], Wang, Y.L.[Ya-Lin],
Regularize, Expand and Compress: NonExpansive Continual Learning,
WACV20(843-851)
IEEE DOI 2006
Task analysis, Computational modeling, Computer architecture, Network architecture, Neural networks, Knowledge engineering, Correlation BibRef

Belouadah, E.[Eden], Popescu, A.[Adrian],
ScaIL: Classifier Weights Scaling for Class Incremental Learning,
WACV20(1255-1264)
IEEE DOI 2006
BibRef
Earlier:
IL2M: Class Incremental Learning With Dual Memory,
ICCV19(583-592)
IEEE DOI 2004
Tuning, Adaptation models, Training, Feature extraction, Machine learning, Memory management, Task analysis. computational complexity, image classification, inference mechanisms, learning (artificial intelligence), Computer architecture BibRef

Ostapenko, O.[Oleksiy], Puscas, M.[Mihai], Klein, T.[Tassilo], Jahnichen, P.[Patrick], Nabi, M.[Moin],
Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning,
CVPR19(11313-11321).
IEEE DOI 2002
BibRef

Stojanov, S.[Stefan], Mishra, S.[Samarth], Thai, N.A.[Ngoc Anh], Dhanda, N.[Nikhil], Humayun, A.[Ahmad], Yu, C.[Chen], Smith, L.B.[Linda B.], Rehg, J.M.[James M.],
Incremental Object Learning From Contiguous Views,
CVPR19(8769-8778).
IEEE DOI 2002
BibRef

Murata, K.[Kengo], Toyota, T.[Tetsuya], Ohara, K.[Kouzou],
What is Happening Inside a Continual Learning Model?: A Representation-Based Evaluation of Representational Forgetting,
CLVision20(952-956)
IEEE DOI 2008
Task analysis, Erbium, Measurement, Learning systems, Standards, Neural networks, Data models BibRef

Abati, D., Tomczak, J., Blankevoort, T., Calderara, S., Cucchiara, R., Bejnordi, B.E.,
Conditional Channel Gated Networks for Task-Aware Continual Learning,
CVPR20(3930-3939)
IEEE DOI 2008
Task analysis, Logic gates, Training, Computational modeling, Neural networks, Machine learning, Computer architecture BibRef

Lee, J., Hong, H.G., Joo, D., Kim, J.,
Continual Learning With Extended Kronecker-Factored Approximate Curvature,
CVPR20(8998-9007)
IEEE DOI 2008
Task analysis, Neural networks, Mathematical model, Learning systems, Optimization, Network architecture, Training BibRef

Kim, J., Kim, J., Kwak, N.,
StackNet: Stacking feature maps for Continual learning,
CLVision20(975-982)
IEEE DOI 2008
Task analysis, Indexes, Training, Data models, Biological neural networks, Stacking, Machine learning BibRef

Du, X., Li, Z., Seo, J., Liu, F., Cao, Y.,
Noise-based Selection of Robust Inherited Model for Accurate Continual Learning,
CLVision20(983-988)
IEEE DOI 2008
Pattern recognition BibRef

Lomonaco, V., Desai, K., Culurciello, E., Maltoni, D.,
Continual Reinforcement Learning in 3D Non-stationary Environments,
CLVision20(999-1008)
IEEE DOI 2008
Task analysis, Learning (artificial intelligence), Benchmark testing, Color, Training, Complexity theory BibRef

Aljundi, R.[Rahaf], Kelchtermans, K.[Klaas], Tuytelaars, T.[Tinne],
Task-Free Continual Learning,
CVPR19(11246-11255).
IEEE DOI 2002
BibRef

Park, D.M.[Dong-Min], Hong, S.[Seokil], Han, B.H.[Bo-Hyung], Lee, K.M.[Kyoung Mu],
Continual Learning by Asymmetric Loss Approximation With Single-Side Overestimation,
ICCV19(3334-3343)
IEEE DOI 2004
function approximation, learning (artificial intelligence), neural nets, asymmetric loss approximation, Scalability BibRef

El Khatib, A.[Alaa], Karray, F.[Fakhri],
Strategies for Improving Single-Head Continual Learning Performance,
ICIAR19(I:452-460).
Springer DOI 1909
Forgetting. Problem is also not all data is available at once. BibRef

Hayes, T.L., Kemker, R., Cahill, N.D., Kanan, C.,
New Metrics and Experimental Paradigms for Continual Learning,
DeepLearnRV18(2112-21123)
IEEE DOI 1812
Robots, Measurement, Training, Task analysis, Computational modeling, Neural networks, Data models BibRef

Zhai, M.Y.[Meng-Yao], Chen, L.[Lei], Mori, G.[Greg],
Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation,
CVPR21(2246-2255)
IEEE DOI 2111
Deep learning, Costs, Heuristic algorithms, Memory management, Filtering algorithms, Information filters, Generators BibRef

Zhai, M.Y.[Meng-Yao], Chen, L.[Lei], He, J.W.[Jia-Wei], Nawhal, M.[Megha], Tung, F.[Frederick], Mori, G.[Greg],
Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation,
ECCV20(XXI:397-413).
Springer DOI 2011
BibRef
Earlier: A1, A2, A5, A3, A4, A6:
Lifelong GAN: Continual Learning for Conditional Image Generation,
ICCV19(2759-2768)
IEEE DOI 2004
image processing, learning (artificial intelligence), neural nets, continual learning, deep neural networks, Training data BibRef

Lopes, N.[Noel], Ribeiro, B.[Bernardete],
Trading off Distance Metrics vs Accuracy in Incremental Learning Algorithms,
CIARP16(530-538).
Springer DOI 1703
BibRef
Earlier:
On the Impact of Distance Metrics in Instance-Based Learning Algorithms,
IbPRIA15(48-56).
Springer DOI 1506
BibRef

Ditzler, G.[Gregory], Polikar, R.[Robi], Chawla, N.V.[Nitesh V.],
An Incremental Learning Algorithm for Non-stationary Environments and Class Imbalance,
ICPR10(2997-3000).
IEEE DOI 1008
BibRef

Almaksour, A.[Abdullah], Anquetil, E.[Eric], Quiniou, S.[Solen], Cheriet, M.[Mohamed],
Evolving Fuzzy Classifiers: Application to Incremental Learning of Handwritten Gesture Recognition Systems,
ICPR10(4056-4059).
IEEE DOI 1008
BibRef

Sudo, K.[Kyoko], Osawa, T.[Tatsuya], Tanaka, H.[Hidenori], Koike, H.[Hideki], Arakawa, K.[Kenichi],
Online anomal movement detection based on unsupervised incremental learning,
ICPR08(1-4).
IEEE DOI 0812
BibRef

Zhang, R.[Rong], Rudnicky, A.I.[Alexander I.],
A New Data Selection Principle for Semi-Supervised Incremental Learning,
ICPR06(II: 780-783).
IEEE DOI 0609
BibRef

Prehn, H.[Herward], Sommer, G.[Gerald],
An Adaptive Classification Algorithm Using Robust Incremental Clustering,
ICPR06(I: 896-899).
IEEE DOI 0609
BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Subspace Clustering, Subspace Learning .


Last update:Nov 30, 2021 at 22:19:38