计算机视觉中的终身学习综述

doi:10.11772/j.issn.1001-9081.2022050766

《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (6): 1785-1795.DOI: 10.11772/j.issn.1001-9081.2022050766

所属专题：人工智能；综述

计算机视觉中的终身学习综述

陈一驰¹^,², 陈斌²^,³^,⁴()

^1.中国科学院成都计算机应用研究所, 成都 610041
^2.中国科学院大学计算机科学与技术学院, 北京 100049
^3.哈尔滨工业大学(深圳) 国际人工智能研究院, 广东深圳 518055
^4.哈尔滨工业大学重庆研究院, 重庆 401151

收稿日期:2022-05-27 修回日期:2022-09-27 接受日期:2022-10-13 发布日期:2023-06-08 出版日期:2023-06-10
通讯作者: 陈斌
作者简介:陈一驰（1997—），男，湖南岳阳人，博士研究生，主要研究方向：计算机视觉、终身学习
陈斌（1970—），男，四川广汉人，研究员，博士，主要研究方向：机器视觉、模式识别、增量学习、工业质检Email：chenbin2020@hit.edu.cn。

Review of lifelong learning in computer vision

Yichi CHEN¹^,², Bin CHEN²^,³^,⁴()

^1.Chengdu Institute of Computer Application，Chinese Academy of Sciences，Chengdu Sichuan 610041，China
^2.School of Computer Science and Technology，University of Chinese Academy of Sciences，Beijing 100049，China
^3.International Institute for Artificial Intelligence，Harbin Institute of Technology （Shenzhen），Shenzhen Guangdong 518055，China
^4.Chongqing Research Institute，Harbin Institute of Technology，Chongqing 401151，China

Received:2022-05-27 Revised:2022-09-27 Accepted:2022-10-13 Online:2023-06-08 Published:2023-06-10
Contact: Bin CHEN
About author:CHEN Yichi， born in 1997， Ph. D. candidate. His research interests include computer vision， lifelong learning.
Supported by:
2022 Key Program of Research and Development of State Administration of Science, Technology and Industry for National Defence(D020401)

摘要/Abstract

摘要：

终身学习（LLL）作为一种新兴方法打破了传统机器学习的局限性，并赋予了模型能够像人类一样在学习过程中不断积累、优化并转移知识的能力。近年来，随着深度学习的广泛应用，越来越多的研究致力于解决深度神经网络中出现的灾难性遗忘问题和摆脱稳定性-可塑性困境，并将LLL方法应用于各种各样的实际场景中，以推进人工智能由弱向强的发展。针对计算机视觉领域，首先，在图像分类任务中将LLL方法归纳为四大类型：基于数据驱动的方法、基于优化过程的方法、基于网络结构的方法和基于知识组合的方法；然后，介绍了LLL方法在其他视觉任务中的典型应用和相关评估指标；最后，针对现阶段LLL方法的不足之处进行讨论并提出了LLL方法未来发展的方向。

关键词: 深度学习, 终身学习, 计算机视觉, 灾难性遗忘, 稳定性-可塑性困境

Abstract:

LifeLong learning （LLL）， as an emerging method， breaks the limitations of traditional machine learning and gives the models the ability to accumulate， optimize and transfer knowledge in the learning process like human beings. In recent years， with the wide application of deep learning， more and more studies attempt to solve catastrophic forgetting problem in deep neural networks and get rid of the stability-plasticity dilemma， as well as apply LLL methods to a wide varieties of real-world scenarios to promote the development of artificial intelligence from weak to strong. Aiming at the field of computer vision， firstly， LLL methods were classified into four types in image classification tasks： data-driven methods， optimization process based methods， network structure based methods and knowledge combination based methods. Then， typical applications of LLL methods in other visual tasks and related evaluation indicators were introduced. Finally， the deficiencies of LLL methods at current stage were discussed， and the future development directions of LLL methods were proposed.

Key words: deep learning, LifeLong Learning (LLL), computer vision, catastrophic forgetting, stability-plasticity dilemma

中图分类号:

TP391.4

陈一驰, 陈斌. 计算机视觉中的终身学习综述[J]. 计算机应用, 2023, 43(6): 1785-1795.

Yichi CHEN, Bin CHEN. Review of lifelong learning in computer vision[J]. Journal of Computer Applications, 2023, 43(6): 1785-1795.

图/表 7

图 1 LLL系统示意图

Fig. 1 Schematic diagram of LLL system

表1 终身学习方法的分类

Tab. 1 Classification of lifelong learning methods

主要方法	子方法
基于数据驱动的终身学习	存储任务子集
基于数据驱动的终身学习	生成任务数据
基于优化过程的终身学习	损失函数设计
	梯度更新
	学习率更新
基于网络结构的终身学习	静态结构
基于网络结构的终身学习	动态结构
基于知识组合的终身学习	以上方法的组合

图2 EWC方法优化示意图

Fig. 2 Schematic diagram of optimization of EWC method

图 3 LwF方法优化示意图

Fig. 3 Schematic diagram of optimization of LwF method

图 4 PNN架构示意图

Fig. 4 Schematic diagram of PNN architecture

图 5 目标检测中的终身学习

Fig. 5 Lifelong learning in object detection

图6 语义分割中的终身学习

Fig. 6 Lifelong learning in semantic segmentation

参考文献 103

1	CHEN Z Y， LIU B. Lifelong Machine Learning， SLAIML ［M］. 2nd ed. Cham： Springer， 2018： 1-207. 10.2200/s00832ed1v01y201802aim037
2	GOODFELLOW I J， MIRZA M， XIAO D， et al. An empirical investigation of catastrophic forgetting in gradient-based neural networks ［EB/OL］. （2015-03-04）［2022-09-23］..
3	GAMA J， ŽLIOBAITĖ I， BIFET A， et al. A survey on concept drift adaptation ［J］. ACM Computing Surveys， 2014， 46（4）： No.44. 10.1145/2523813
4	MERMILLOD M， BUGAISKA A， BONIN P. The stability-plasticity dilemma： investigating the continuum from catastrophic forgetting to age-limited learning effects［J］. Frontiers in Psychology， 2013， 4： No.504. 10.3389/fpsyg.2013.00504
5	PARISI G I， KEMKER R， PART J L， et al. Continual lifelong learning with neural networks： a review［J］. Neural Networks， 2019， 113： 54-71. 10.1016/j.neunet.2019.01.012
6	QU H X， RAHMANI H， XU L， et al. Recent advances of continual learning in computer vision： an overview ［EB/OL］. （2021-09-24）［2022-09-26］..
7	DE LANGE M， ALJUNDI R， MASANA M， et al. A continual learning survey： defying forgetting in classification tasks ［J］. IEEE Transactions on Pattern Analysis Machine Intelligence， 2022， 44（7）： 3366-3385.
8	MASANA M， LIU X L， TWARDOWSKI B， et al. Class-incremental learning： survey and performance evaluation on image classification ［J］. IEEE Transactions on Pattern Analysis Machine Intelligence， 2023， 45（5）： 5513-5533.
9	REBUFFI S A， KOLESNIKOV A， SPERL G， et al. iCaRL： incremental classifier and representation learning ［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 5533-5542. 10.1109/cvpr.2017.587
10	CHAUDHRY A， ROHRBACH M， ELHOSEINY M， et al. On tiny episodic memories in continual learning ［EB/OL］. （2019-06-04）［2022-09-23］..
11	BUZZEGA P， BOSCHINI M， PORRELLO A， et al. Rethinking experience replay： a bag of tricks for continual learning［C］// Proceedings of the 25th International Conference on Pattern Recognition. Piscataway： IEEE， 2021： 2180-2187. 10.1109/icpr48806.2021.9412614
12	ALJUNDI R， CACCIA L， BELILOVSKY E， et al. Online continual learning with maximally interfered retrieval［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2019： 11872-11883. 10.1109/cvpr.2019.01151
13	BELOUADAH E， POPESCU A. IL2M： class incremental learning with dual memory［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 583-592. 10.1109/iccv.2019.00067
14	CHAUDHRY A， GORDO A， DOKANIA P， et al. Using hindsight to anchor past knowledge in continual learning［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2021： 6993-7001. 10.1609/aaai.v35i8.16861
15	ISCEN A， ZHANG J， LAZEBNIK S， et al. Memory-efficient incremental learning through feature adaptation ［C］// Proceedings of the 2020 European Conference on Computer Vision， LNCS 12361. Cham： Springer， 2020： 699-715.
16	ZHU F， ZHANG X Y， WANG C， et al. Prototype augmentation and self-supervision for incremental learning ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 5867-5876. 10.1109/cvpr46437.2021.00581
17	HE C， WANG R P， CHEN X L. A tale of two CILs： the connections between class incremental learning and class imbalanced learning， and beyond ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2021： 3554-3564. 10.1109/cvprw53098.2021.00395
18	KORYCKI Ł， KRAWCZYK B. Class-incremental experience replay for continual learning under concept drift ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2021： 3644-3653. 10.1109/cvprw53098.2021.00404
19	MAI Z D， LI R W， KIM H， et al. Supervised contrastive replay： revisiting the nearest class mean classifier in online class-incremental continual learning ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2021： 3584-3594. 10.1109/cvprw53098.2021.00398
20	SHIN H， LEE J K， KIM J， et al. Continual learning with deep generative replay［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017： 2994-3003.
21	ATKINSON C， McCANE B， SZYMANSKI L， et al. Pseudo-recursal： solving the catastrophic forgetting problem in deep neural networks［EB/OL］. （2018-05-07）［2022-09-23］.. 10.1016/j.neucom.2020.11.050
22	van de VEN G M， TOLIAS A S. Generative replay with feedback connections as a general strategy for continual learning［EB/OL］. （2019-04-17）［2022-09-23］..
23	CONG Y L， ZHAO M Y， LI J Q， et al. GAN memory with no forgetting ［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2020： 16481-16494.
24	PEREZ E， STRUB F， DE VRIES H， et al. FiLM： visual reasoning with a general conditioning layer ［C］// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2018： 3942-3951. 10.1609/aaai.v32i1.11671
25	ZHAO M Y， CONG Y L， CARIN L. On leveraging pretrained GANs for generation with limited data ［C］// Proceedings of the 37th International Conference on Machine Learning. New York： JMLR.org， 2020： 11340-11351.
26	RAMAPURAM J， GREGOROVA M， KALOUSIS A. Lifelong generative modeling ［J］. Neurocomputing， 2020， 404： 381-400. 10.1016/j.neucom.2020.02.115
27	YE F， BORS A G. Learning latent representations across multiple data domains using lifelong VAEGAN［C］// Proceedings of the 2020 European Conference on Computer Vision， LNCS 12365. Cham： Springer， 2020： 777-795.
28	LESORT T， CASELLES-DUPRÉ H， GARCIA-ORTIZ M， et al. Generative models from the perspective of continual learning ［C］// Proceedings of the 2019 International Joint Conference on Neural Networks. Piscataway： IEEE， 2019： 1-8. 10.1109/ijcnn.2019.8851986
29	GULRAJANI I， AHMED F， ARJOVSKY M， et al. Improved training of Wasserstein GANs［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017： 5769-5779.
30	KIRKPATRICK J， PASCANU R， RABINOWITZ N， et al. Overcoming catastrophic forgetting in neural networks［J］. Proceedings of the National Academy of Sciences of the United States of America， 2017， 114（13）： 3521-3526. 10.1073/pnas.1611835114
31	CHAUDHRY A， DOKANIA P K， AJANTHAN T， et al. Riemannian walk for incremental learning： understanding forgetting and intransigence［C］// Proceedings of the 2018 European Conference on Computer Vision， LNCS 11215. Cham： Springer， 2018： 556-572.
32	RITTER H， BOTEV A， BARBER D. Online structured Laplace approximations for overcoming catastrophic forgetting［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2018： 3742-3752.
33	ZENKE F， POOLE B， GANGULI S. Continual learning through synaptic intelligence ［C］// Proceedings of the 34th International Conference on Machine Learning. New York： JMLR.org， 2017： 3987-3995. 10.1007/978-1-4899-7687-1_171
34	ALJUNDI R， BABILONI F， ELHOSEINY M， et al. Memory aware synapses： learning what （not） to forget ［C］// Proceedings of the 2018 European Conference on Computer Vision. LNCS 11207. Cham： Springer， 2018： 144-161.
35	REN M Y， LIAO R J， FETAYA E， et al. Incremental few-shot learning with attention attractor networks［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2019： 5275-5285.
36	HU W P， QIN Q， WANG M Y， et al. Continual learning by using information of each class holistically ［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2021： 7797-7805. 10.1609/aaai.v35i9.16952
37	LI Z Z， HOIEM D. Learning without forgetting［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2018， 40（12）： 2935-2947. 10.1109/tpami.2017.2773081
38	RANNEN A， ALJUNDI R， BLASCHKO M B， et al. Encoder based lifelong learning［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2017： 1329-1337. 10.1109/iccv.2017.148
39	DHAR P， SINGH R V， PENG K C， et al. Learning without memorizing ［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 5133-5141. 10.1109/cvpr.2019.00528
40	DOUILLARD A， CORD M， OLLION C， et al. PODNet： pooled outputs distillation for small-tasks incremental learning［C］// Proceedings of the 2020 European Conference on Computer Vision， LNCS 12365. Cham： Springer， 2020： 86-102.
41	CHA H， LEE J， SHIN J. Co² L： contrastive continual learning［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 9496-9505. 10.1109/iccv48922.2021.00938
42	LOPEZ-PAZ D， RANZATO M. Gradient episodic memory for continual learning［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017： 6470-6479.
43	CHAUDHRY A， RANZATO M， ROHRBACH M， et al. Efficient lifelong learning with A-GEM ［EB/OL］. （2019-01-09）［2022-09-23］..
44	GUO Y H， LIU M R， YANG T B， et al. Improved schemes for episodic memory-based lifelong learning ［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2020： 1023-1035.
45	TANG S X， CHEN D P， ZHU J G， et al. Layerwise optimization by gradient decomposition for continual learning ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 9629-9638. 10.1109/cvpr46437.2021.00951
46	FARAJTABAR M， AZIZAN N， MOTT A， et al. Orthogonal gradient descent for continual learning［C］// Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics. New York： JMLR.org， 2020： 3762-3773. 10.1109/taai54685.2021.00034
47	SAHA G， GARG I， ROY K. Gradient projection memory for continual learning ［EB/OL］. （2021-03-17）［2022-09-23］..
48	EBRAHIMI S， ELHOSEINY M， DARRELL T， et al. Uncertainty-guided continual learning with Bayesian neural networks ［EB/OL］.（2020-02-20）［2022-09-23］..
49	FERNANDO C， BANARSE D， BLUNDELL C， et al. PathNet： evolution channels gradient descent in super neural networks ［EB/OL］.（2017-01-30）［2022-09-23］..
50	RAJASEGARAN J， HAYAT M， KHAN S， et al. Random path selection for incremental learning ［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2019： 12669-12679. 10.1109/cvpr42600.2020.01360
51	MALLYA A， LAZEBNIK S. PackNet： adding multiple tasks to a single network by iterative pruning ［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 7765-7773. 10.1109/cvpr.2018.00810
52	SERRA J， SURIS D， MIRON M， et al. Overcoming catastrophic forgetting with hard attention to the task ［C］// Proceedings of the 35th International Conference on Machine Learning. New York： JMLR.org， 2018： 4548-4557.
53	MALLYA A， DAVIS D， LAZEBNIK S. Piggyback： adapting a single network to multiple tasks by learning to mask weights ［C］// Proceedings of the 2018 European Conference on Computer Vision， LNCS 11208. Cham： Springer， 2018： 72-88.
54	HURTADO J， RAYMOND-SAEZ A， SOTO A. Optimizing reusable knowledge for continual learning via metalearning ［C/OL］// Proceedings of the 35th Conference on Neural Information Processing Systems ［2022-09-23］.. 10.48550/arXiv.2106.05390
55	ABATI D， TOMCZAK J， BLANKEVOORT T， et al. Conditional channel gated networks for task-aware continual learning［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 3930-3939. 10.1109/cvpr42600.2020.00399
56	MAZUMDER P， SINGH P， RAI P. Few-shot lifelong learning［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2021： 2337-2345. 10.1609/aaai.v35i3.16334
57	RUSU A A， RABINOWITZ N C， DESJARDINS G， et al. Progressive neural networks［EB/OL］. （2022-10-22）［2022-11-23］. .
58	ALJUNDI R， CHAKRAVARTY P， TUYTELAARS T. Expert gate： lifelong learning with a network of experts ［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 7120-7129. 10.1109/cvpr.2017.753
59	YOON J， YANG E， LEE J， et al. Lifelong learning with dynamically expandable networks ［EB/OL］. （2018-06-11）［2022-09-23］..
60	XU J， ZHU Z X. Reinforced continual learning ［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2018： 907-916. 10.7551/mitpress/11474.003.0014
61	LI X L， ZHOU Y B， WU T F， et al. Learn to grow： a continual structure learning framework for overcoming catastrophic forgetting［C］// Proceedings of the 36th International Conference on Machine Learning. New York： JMLR.org， 2019： 3925-3934.
62	LEE S， STOKES J， EATON E. Learning shared knowledge for deep lifelong learning using deconvolutional networks［C］// Proceedings of the 28th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2019： 2837-2844. 10.24963/ijcai.2019/393
63	YOON J， KIM S， YANG E， et al. Scalable and order-robust continual learning with additive parameter decomposition［EB/OL］. （2020-02-15）［2022-09-23］..
64	SINGH P， VERMA V K， MAZUMDER P， et al. Calibrating CNNs for lifelong learning［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2020： 15579-15590.
65	KUO N I H， HARANDI M， FOURRIER N， et al. Plastic and stable gated classifiers for continual learning ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2021： 3548-3553. 10.1109/cvprw53098.2021.00394
66	NGUYEN C V， LI Y Z， BUI T D， et al. Variational continual learning ［EB/OL］. （2018-05-20）［2022-09-23］..
67	CASTRO F M， MARÍN-JIMÉNEZ M J， GUIL N， et al. End-to-end incremental learning ［C］// Proceedings of the 2018 European Conference on Computer Vision， LNCS 11216. Cham： Springer， 2018： 241-257.
68	HOU S H， PAN X Y， LOY C C， et al. Lifelong learning via progressive distillation and retrospection ［C］// Proceedings of the 2018 European Conference on Computer Vision， LNCS 11207. Cham： Springer， 2018： 452-467.
69	李国锋. 深度神经网络模型持续学习能力的研究［D］. 成都：电子科技大学， 2021：24-53.
	LI G F. The research on continual learning ability of deep neural network model［D］. Chengdu： University of Electronic Science and Technology of China， 2021：24-53.
70	WU Y， CHEN Y P， WANG L J， et al. Incremental classifier learning with generative adversarial networks ［EB/OL］. （2018-02-02）［2022-09-23］..
71	HE C， WANG R P， SHAN S G， et al. Exemplar-supported generative reproduction for class incremental learning［C］// Proceedings of the 2018 British Machine Vision Conference. Durham： BMVA Press， 2018： No.98.
72	ACHILLE A， ECCLES T， MATTHEY L， et al. Life-long disentangled representation learning with cross-domain latent homologies ［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2018： 9895-9905.
73	OSTAPENKO O， PUSCAS M， KLEIN T， et al. Learning to remember： a synaptic plasticity driven framework for continual learning ［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 11313-11321. 10.1109/cvpr.2019.01158
74	YANG Y， ZHOU D W， ZHAN D C， et al. Adaptive deep models for incremental learning： considering capacity scalability and sustainability［C］// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2019： 74-82. 10.1145/3292500.3330865
75	GUPTA G， YADAV K， PAULL L. La-MAML： look-ahead meta learning for continual learning［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2020： 11588-11598.
76	CHOI Y， EL-KHAMY M， LEE J. Dual-teacher class-incremental learning with data-free generative replay ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2021： 3538-3547. 10.1109/cvprw53098.2021.00393
77	SHMELKOV K， SCHMID C， ALAHARI K. Incremental learning of object detectors without catastrophic forgetting ［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2017： 3420-3429. 10.1109/iccv.2017.368
78	PÉREZ-RÚA J M， ZHU X T， HOSPEDALES T M， et al. Incremental few-shot object detection［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 13843-13852. 10.1109/cvpr42600.2020.01386
79	JOSEPH K J， KHAN S， KHAN F S， et al. Towards open world object detection［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 5826-5836. 10.1109/cvpr46437.2021.00577
80	ZHOU W， CHANG S Y， SOSA N， et al. Lifelong object detection［EB/OL］. （2020-09-02）［2022-09-23］..
81	LIU X L， YANG H， RAVICHANDRAN A， et al. Multi-task incremental learning for object detection ［EB/OL］. （2020-11-18）［2022-09-23］..
82	BAWEJA C， GLOCKER B， KAMNITSAS K. Towards continual learning in medical imaging ［EB/OL］. （2018-11-06）［2022-09-23］..
83	ÖZGÜN S， RICKMANN A M， ROY A G， et al. Importance driven continual learning for segmentation across domains［C］// Proceedings of the 2020 International Workshop on Machine Learning in Medical Imaging， LNCS 12436. Cham： Springer， 2020： 423-433.
84	MICHIELI U， ZANUTTIGH P. Incremental learning techniques for semantic segmentation［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops. Piscataway： IEEE， 2019： 3205-3212. 10.1109/iccvw.2019.00400
85	LI Z Y， ZHONG C H， WANG R X， et al. Continual learning of new diseases with dual distillation and ensemble strategy［C］// Proceedings of the 2020 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS 12261. Cham： Springer， 2020： 169-178.
86	CERMELLI F， MANCINI M， ROTA BULÒ S R， et al. Modeling the background for incremental learning in semantic segmentation［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 9230-9239. 10.1109/cvpr42600.2020.00925
87	DOUILLARD A， CHEN Y F， DAPOGNY A， et al. PLOP： learning without forgetting for continual semantic segmentation［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 4039-4049. 10.1109/cvpr46437.2021.00403
88	MARACANI A， MICHIELI U， TOLDO M， et al. RECALL： replay-based continual learning in semantic segmentation［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 7006-7015. 10.1109/iccv48922.2021.00694
89	MICHIELI U， ZANUTTIGH P. Continual semantic segmentation via repulsion-attraction of sparse and disentangled latent representations［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 1114-1124. 10.1109/cvpr46437.2021.00117
90	SEFF A， BEATSON A， SUO D， et al. Continual learning in generative adversarial nets［EB/OL］. （2017-05-23）［2022-09-23］..
91	WU C S， HERRANZ L， LIU X L， et al. Memory replay GANs： learning to generate new categories without forgetting［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2018： 5966-5976.
92	RIOS A， ITTI L. Closed-loop memory GAN for continual learning［C］// Proceedings of the 28th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2019： 3332-3338. 10.24963/ijcai.2019/462
93	ZHAI M Y， CHEN L， TUNG F， et al. Lifelong GAN： continual learning for conditional image generation ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 2759-2768. 10.1109/iccv.2019.00285
94	ZHAI M Y， CHEN L， HE J W， et al. Piggyback GAN： efficient lifelong learning for image conditioned generation［C］// Proceedings of the 2020 European Conference on Computer Vision， LNCS 12366. Cham： Springer， 2020： 397-413.
95	ZHAI M Y， CHEN L， MORI G. Hyper-LifelongGAN： scalable lifelong learning for image conditioned generation［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 2246-2255. 10.1109/cvpr46437.2021.00228
96	ZHOU M， XIAO J， CHANG Y F， et al. Image de-raining via continual learning［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 4905-4914. 10.1109/cvpr46437.2021.00487
97	ZHU L， SHE Q， ZHANG B， et al. Learning the superpixel in a non-iterative and lifelong manner［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 1225-1234. 10.1109/cvpr46437.2021.00128
98	PU N， CHEN W， LIU Y， et al. Lifelong person re-identification via adaptive knowledge accumulation ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 7897-7906. 10.1109/cvpr46437.2021.00781
99	FAN L， XIONG P X， WEI W， et al. FLAR： a unified prototype framework for few-sample lifelong active recognition［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 15374-15383. 10.1109/iccv48922.2021.01511
100	LI T J， KE Q H， RAHMANI H， et al. Else-Net： elastic semantic network for continual action recognition from skeleton data［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 13414-13423. 10.1109/iccv48922.2021.01318
101	ROSTAMI M， SPINOULAS L， HUSSEIN M， et al. Detection and continual learning of novel face presentation attacks［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 14831-14840. 10.1109/iccv48922.2021.01458
102	WANG S Z， LASKAR Z， MELEKHOV I， et al. Continual learning for image-based camera localization ［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 3232-3242. 10.1109/iccv48922.2021.00324
103	DÍAZ-RODRÍGUEZ N， LOMONACO V， FILLIAT D， et al. Don’t forget， there is more than forgetting： new metrics for Continual Learning［EB/OL］. （2018-10-31）［2022-09-23］..

[1]	秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974.
[2]	王熙源, 张战成, 徐少康, 张宝成, 罗晓清, 胡伏原. 面向手术导航3D/2D配准的无监督跨域迁移网络[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2911-2918.
[3]	潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877.
[4]	黄云川, 江永全, 黄骏涛, 杨燕. 基于元图同构网络的分子毒性预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2964-2969.
[5]	李顺勇, 李师毅, 胥瑞, 赵兴旺. 基于自注意力融合的不完整多视图聚类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2696-2703.
[6]	付帅, 郭小英, 白茹意, 闫涛, 陈斌. 改进的CloFormer模型与有序回归相结合的年龄评估方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2372-2380.
[7]	刘禹含, 吉根林, 张红苹. 基于骨架图与混合注意力的视频行人异常检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2551-2557.
[8]	顾焰杰, 张英俊, 刘晓倩, 周围, 孙威. 基于时空多图融合的交通流量预测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2618-2625.
[9]	石乾宏, 杨燕, 江永全, 欧阳小草, 范武波, 陈强, 姜涛, 李媛. 面向空气质量预测的多粒度突变拟合网络[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2643-2650.
[10]	赵亦群, 张志禹, 董雪. 基于密集残差物理信息神经网络的各向异性旅行时计算方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2310-2318.
[11]	徐松, 张文博, 王一帆. 基于时空信息的轻量视频显著性目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2192-2199.
[12]	孙逊, 冯睿锋, 陈彦如. 基于深度与实例分割融合的单目3D目标检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2208-2215.
[13]	吴筝, 程志友, 汪真天, 汪传建, 王胜, 许辉. 基于深度学习的患者麻醉复苏过程中的头部运动幅度分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2258-2263.
[14]	李欢欢, 黄添强, 丁雪梅, 罗海峰, 黄丽清. 基于多尺度时空图卷积网络的交通出行需求预测[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2065-2072.
[15]	张郅, 李欣, 叶乃夫, 胡凯茜. 基于暗知识保护的模型窃取防御技术DKP[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2080-2086.

计算机视觉中的终身学习综述

Review of lifelong learning in computer vision

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 103

相关文章 15

编辑推荐

Metrics