A Survey on Transfer Learning
The DOI matches its Crossref record; 89 of the 90 references it cites were found in a registry or an index.
Abstract
A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many real-world applications, this assumption may not hold. For example, we sometimes have a classification task in one domain of interest, but we only have sufficient training data in another domain of interest, where the latter data may be in a different feature space or follow a different data distribution. In such cases, knowledge transfer, if done successfully, would greatly improve the performance of learning by avoiding much expensive data-labeling efforts. In recent years, transfer learning has emerged as a new learning framework to address this problem. This survey focuses on categorizing and reviewing the current progress on transfer learning for classification, regression, and clustering problems. In this survey, we discuss the relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift. We also explore some potential future issues in transfer learning research.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“These are perturbed versions of test inputs which seem almost indistinguishable from the original test input to a human, but fool the trained model [70, 441].”
From Advances and Open Problems in Federated Learning (2021) · cites this paper as [70]
In the citing paper
“The rationale is to make the data distributions from different subjects more similar, and hence a classifier trained on the auxiliary data would have a better chance to perform well on the new subject.”
From Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach (2020) · cites this paper as [23]
In the citing paper
“Fortunately, transfer learning is concerned to overcome such weaknesses by applying the knowledge learned from one or multiple tasks to other related but novel ones [27].”
From Applications of machine learning to machine fault diagnosis: A review and roadmap (2020) · cites this paper as [27]
In the citing paper
“Transfer learning is able to get the above purpose, in which the knowledge from one or more diagnosis tasks can be reused to other related but different ones [27].”
From Applications of machine learning to machine fault diagnosis: A review and roadmap (2020) · cites this paper as [27]
In the citing paper
“TL has many advantages in the development of ML algorithms, such as shorter training times and the enhanced robustness of using models that have already passed initial tests.”
From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [127]
14 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Wu, Y. (1999) · Technometrics · doi:10.1080/00401706.1999.10485951 · Cited by 27,221
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636 · cited 1×
“Among these, a closely related learning technique to transfer learning is the multitask learning framework [21], which tries to learn multiple tasks simultaneously even when they are different.”
BackgroundTop 10 algorithms in data mining
Wu, X., Kumar, V., Ross Quinlan, J., Ghosh, J., Yang, Q., Motoda, H., McLachlan, G. J., Ng, A., Liu, B., Yu, P. S., et al. (2008) · Knowledge and Information Systems · doi:10.1007/s10115-007-0114-2 · Cited by 5,667 · cited 1×
“ATA mining and machine learning technologies have already achieved significant success in many knowledge engineering areas including classification, regression, and clustering (e.g., [1], [2]).”
BackgroundSelf-citationCombining labeled and unlabeled data with co-training
Blum, A., & Mitchell, T. (1998) · Proceedings of the eleventh annual conference on Computational learning theory · doi:10.1145/279943.279962 · Cited by 5,495
Domain Adaptation via Transfer Component Analysis
Pan, S. J., Tsang, I. W., Kwok, J. T., & Yang, Q. (2011) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2091281 · Cited by 4,753 · cited 2×
“Finally, on the WiFi localization data set, we show the comparison results reported in [67], where the baseline is a regularized least square regression model (RLSR), which is a standard regression model, and KPCA, which represents to apply RLSR on the new representations of the data learned by…”
MethodSelf-citationSemi-Supervised Learning Literature Survey
Zhu, X. (2005) · Minds at UW (University of Wisconsin) · Cited by 4,505
Text classification from labeled and unlabeled documents using EM
Nigam, K., Mccallum, A. K., Thrun, S., & Mitchell, T. (2000) · Machine Learning · doi:10.1023/a:1007692713085 · Cited by 2,736
Transductive Inference for Text Classification using Support Vector Machines
Joachims, T. (1999) · Cited by 2,723
Richardson, M., & Domingos, P. (2006) · Machine Learning · doi:10.1007/s10994-006-5833-1 · Cited by 2,676 · cited 1×
“MLNs [56] is a powerful formalism, which combines the compact expressiveness of first-order logic with flexibility of probability, for statistical relational learning.”
BackgroundEfficient sparse coding algorithms
Lee, H., Battle, A., Raina, R., & Ng, A. Y. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0105 · Cited by 2,394
Research works printed but not linked: 3
- 1998, Learning to Learn
- 10.5555/2981562.2981582 · doi:10.5555/2981562.2981582
- Joachims, Transductive Inference for Text Classification Using Support Vector Machines, 200
Cited by
Items 801–900 of 1,257
Perspective on integrating machine learning into computational chemistry and materials science
Westermayr, J., Gastegger, M., Schütt, K. T., & Maurer, R. J. (2021) · The Journal of Chemical Physics · doi:10.1063/5.0047760 · Cited by 203
Domain Adaptation via Prompt Learning
Ge, C., Huang, R., Xie, M., Lai, Z., Song, S., Li, S., & Huang, G. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3327962 · Cited by 199
Spatiotemporal Patterns in Large-Scale Traffic Speed Prediction
Asif, M. T., Dauwels, J., Goh, C. Y., Oran, A., Fathi, E., Xu, M., Dhanya, M. M., Mitrovic, N., & Jaillet, P. (2014) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2013.2290285 · Cited by 211
“Supervised learning methods, such as the SVR and ANNs, assume that the labeled training data and the test data come from the same distribution [22]–[24].”
MethodA Novel Weighted Adversarial Transfer Network for Partial Domain Fault Diagnosis of Machinery
Li, W., Chen, Z., & He, G. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2994621 · Cited by 209
“Domain adaptation (DA) as a subfield of TL refers to the case where the large amount of labeled source data are present, and there are only unlabeled data available in the target domain [23].”
BackgroundRecent advances in reinforcement learning in finance
Hambly, B., Xu, R., & Yang, H. (2023) · Mathematical Finance · doi:10.1111/mafi.12382 · Cited by 205
Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
Hsu, Y.-C., Liu, Y.-C., Ramasamy, A., & Kira, Z. (2018) · arXiv · doi:10.48550/arxiv.1810.12488 · Cited by 211
“The input distribution (domain) difference has been discussed extensively in the setting of transfer learning [15], primarily as a domain adaptation problem [16].”
BackgroundBuilding Ethics into Artificial Intelligence
Yu, H., Shen, Z., Miao, C., Leung, C., Lesser, V. R., & Yang, Q. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/779 · Cited by 210
“There may be opportunities for transfer learning [Pan and Yang, 2010] to be applied in this case to model different ethics due to diversities in culture and other aspects.”
BackgroundSelf-citationWeakly-Supervised Cross-Domain Dictionary Learning for Visual Recognition
Zhu, F., & Shao, L. (2014) · International Journal of Computer Vision · doi:10.1007/s11263-014-0703-y · Cited by 210
Convolutional-network models to predict wall-bounded turbulence from wall quantities
Guastoni, L., Güemes, A., Ianiro, A., Discetti, S., Schlatter, P., Azizpour, H., & Vinuesa, R. (2021) · Journal of Fluid Mechanics · doi:10.1017/jfm.2021.812 · Cited by 209
Cross-Domain Fault Diagnosis Using Knowledge Transfer Strategy: A Review
Zheng, H., Wang, R., Yang, Y., Yin, J., Li, Y., Li, Y., & Xu, M. (2019) · IEEE Access · doi:10.1109/access.2019.2939876 · Cited by 209
Object fusion tracking based on visible and infrared images: A comprehensive review
Zhang, X., Ye, P., Leung, H., Gong, K., & Xiao, G. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.05.002 · Cited by 208
Deep Convolutional Neural Network-Based Epileptic Electroencephalogram (EEG) Signal Classification
Gao, Y., Gao, B., Chen, Q., Liu, J., & Zhang, Y. (2020) · Frontiers in Neurology · doi:10.3389/fneur.2020.00375 · Cited by 209
“There are two ways to apply transfer learning for training classification networks (28): (1) Loading the pretrained weight, freezing the parameters before the fully connected layer, and only training the fully connected layer.”
MethodMachine Learning‐Enabled Smart Sensor Systems
Ha, N., Xu, K., Ren, G., Mitchell, A., & Ou, J. Z. (2020) · Advanced Intelligent Systems · doi:10.1002/aisy.202000063 · Cited by 207
Li, J., Huang, R., He, G., Liao, Y., Wang, Z., & Li, W. (2021) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2020.3025615 · Cited by 208
“In generally, the deep TL can be classified into four categories, i.e., instances-based deep TL, mapping-based deep TL, network-based deep TL, and adversarial-based deep transfer learning(ADTL)[15].”
BackgroundA Review on Evolutionary Multitask Optimization: Trends and Challenges
Wei, T., Wang, S., Zhong, J., Liu, D., & Zhang, J. (2022) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2021.3139437 · Cited by 205
A Unified Framework for Metric Transfer Learning
Xu, Y., Pan, S. J., Xiong, H., Wu, Q., Luo, R., Min, H., & Song, H. (2017) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2017.2669193 · Cited by 208
“Recently, various transfer learning techniques have been proposed for transferring knowledge in terms of instances, features, parameters or relational information among data objects across domains [1], [2].”
BackgroundSelf-citationDiscriminative Adversarial Domain Adaptation
Tang, H., & Jia, K. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.6054 · Cited by 194
Convolutional neural networks based efficient approach for classification of lung diseases
Demir, F., Sengur, A., & Bajaj, V. (2020) · Health Information Science and Systems · doi:10.1007/s13755-019-0091-3 · Cited by 204
Yang, Q., Shi, W., Chen, J., & Lin, W. (2020) · Automation in Construction · doi:10.1016/j.autcon.2020.103199 · Cited by 206
Self-citationVoice Pathology Detection and Classification Using Convolutional Neural Network Model
Mohammed, M. A., Abdulkareem, K. H., Mostafa, S. A., Khanapi Abd Ghani, M., Maashi, M. S., Garcia-Zapirain, B., Oleagordia, I., Alhakami, H., & AL-Dhief, F. T. (2020) · Applied Sciences · doi:10.3390/app10113723 · Cited by 208
Cui, Z., Kang, L., Li, L., Wang, L., & Wang, K. (2022) · Energy · doi:10.1016/j.energy.2022.124933 · Cited by 207
Vessels fuel consumption forecast and trim optimisation: A data analytics perspective
Coraddu, A., Oneto, L., Baldi, F., & Anguita, D. (2017) · Ocean Engineering · doi:10.1016/j.oceaneng.2016.11.058 · Cited by 207
Deep Learning the Electromagnetic Properties of Metamaterials—A Comprehensive Review
Khatib, O., Ren, S., Malof, J., & Padilla, W. J. (2021) · Advanced Functional Materials · doi:10.1002/adfm.202101748 · Cited by 207
Promises and Challenges of Big Data Computing in Health Sciences
Huang, T., Lan, L., Fang, X., An, P., Min, J., & Wang, F. (2015) · Big Data Research · doi:10.1016/j.bdr.2015.02.002 · Cited by 205
“Since 2000, Transfer Learning[80], Manifold Learning[81] etc.”
Ternary Adversarial Networks With Self-Supervision for Zero-Shot Cross-Modal Retrieval
Xu, X., Lu, H., Song, J., Yang, Y., Shen, H. T., & Li, X. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2928180 · Cited by 205
“2) Transfer Learning for Cross-Modal Retrieval: Transfer learning [46], which exploits general knowledge from available source-domain data as guidance to promote the model learning in the target domain, has been widely studied for more than a decade and applied in various scenarios, such as image…”
BackgroundZhang, K., Zhang, Y., & Cheng, H.-D. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.2990703 · Cited by 205
Deep learning based synthetic‐CT generation in radiotherapy and PET: A review
Spadea, M. F., Maspero, M., Zaffino, P., & Seco, J. (2021) · Medical Physics · doi:10.1002/mp.15150 · Cited by 201
Deep learning for air pollutant concentration prediction: A review
Zhang, B., Rong, Y., Yong, R., Qin, D., Li, M., Zou, G., & Pan, J. (2022) · Atmospheric Environment · doi:10.1016/j.atmosenv.2022.119347 · Cited by 203
Measuring Robustness to Natural Distribution Shifts in Image Classification
Taori, R., Dave, A., Shankar, V., Carlini, N., Recht, B., & Schmidt, L. (2020) · arXiv · doi:10.48550/arxiv.2007.00644 · Cited by 206
Stability Properties of Graph Neural Networks
Gama, F., Bruna, J., & Ribeiro, A. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.3026980 · Cited by 204
“ample, several works have studied, experimentally, the concept of transfer learning, which considers the ability to train a CNN on one dataset, and then sucessfully use it on another, similar dataset [10]. In the theoretical realm, [11] opted for controlling for one of the sources of uncertainty, by fixing the bank of…”
BackgroundOpen Set Domain Adaptation: Theoretical Bound and Algorithm
Fang, Z., Lu, J., Liu, F., Xuan, J., & Zhang, G. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3017213 · Cited by 204
A framework for breast cancer classification using Multi-DCNNs
Ragab, D. A., Attallah, O., Sharkas, M., Ren, J., & Marshall, S. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104245 · Cited by 204
Artificial Intelligence and Biosensors in Healthcare and Its Clinical Relevance: A Review
(2023) · doi:10.1109/access.2023.3285596 · Cited by 205
“They will continue to advance in miniaturization, scalability, low power consumption, low cost, high sensitivity, multifunction, safety, non-toxicity, and degradation [146].”
BackgroundJeong, G., & Kim, H. Y. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.09.036 · Cited by 204
Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
Ben‐Nun, T., & Hoefler, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.09941 · Cited by 203
“the result. The choice of initial weights can originate from random values, informed decisions (e.g., Xavier initialization[79]), or from pre-trained weights in a methodology called Transfer Learning[191]. In deep learning, recent works state that the optimization space is riddled with saddle points[143], and assume t…”
Deep Learning for Hand Gesture Recognition on Skeletal Data
Devineau, G., Moutarde, F., Xi, W., & Yang, J. (2018) · 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) · doi:10.1109/fg.2018.00025 · Cited by 203
“A common trick to quickly train CNNs on gesture datasets consists in doing Transfer Learning [34].”
BackgroundWhat, Where, and How to Transfer in SAR Target Recognition Based on Deep CNNs
Huang, Z., Pan, Z., & Lei, B. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2947634 · Cited by 203
“Transfer learning, usually aiming at transferring knowledge from a large dataset known as the source domain to a small dataset called as the target domain [20], is widely popularized in deep convolutional neural networks based approaches.”
BackgroundLearning from crowdsourced labeled data: a survey
Zhang, J., Wu, X., & Sheng, V. S. (2016) · Artificial Intelligence Review · doi:10.1007/s10462-016-9491-9 · Cited by 203
“For example, researchers have been aware of the potential value of recent widely studied transfer learning (Pan and Yang 2010; Oyen and Lane 2015) to crowdsourcing.”
BackgroundOn constrained spectral clustering and its applications
Wang, X., Qian, B., & Davidson, I. (2014) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-012-0291-9 · Cited by 203
“5.1 A Graph Cut Interpretation Unconstrained spectral clustering can be interpreted as finding the Ncut of an unlabeled graph.”
BackgroundInfluentialRethinking Federated Learning with Domain Shift: A Prototype View
Huang, W., Ye, M., Shi, Z., Li, H., & Du, B. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01565 · Cited by 182
DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection
Rieger, P., Nguyen, T. D., Miettinen, M., & Sadeghi, A.-R. (2022) · Proceedings 2022 Network and Distributed System Security Symposium · doi:10.14722/ndss.2022.23156 · Cited by 202
“Moreover, if the global model of the previous round was already poisoned, this separation allows the benign clients to untrain the backdoor and gain a clean model, analogously to the concept of transfer learning [29].”
BackgroundDeep Learning Object Detection Methods for Ecological Camera Trap Data
Schneider, S., Taylor, G. W., & Kremer, S. (2018) · 2018 15th Conference on Computer and Robot Vision (CRV) · doi:10.1109/crv.2018.00052 · Cited by 184
Deep learning in head & neck cancer outcome prediction
Diamant, A., Chatterjee, A., Vallières, M., Shenouda, G., & Seuntjens, J. (2019) · Scientific Reports · doi:10.1038/s41598-019-39206-1 · Cited by 200
Challenges and frontiers in abusive content detection
Vidgen, B., Harris, A., Nguyen, D., Tromble, R., Hale, S., & Margetts, H. (2019) · Proceedings of the Third Workshop on Abusive Language Online · doi:10.18653/v1/w19-3509 · Cited by 199
“However, a key challenge in transfer learning is that systems may develop ‘bad’ learning habits and as such newly created transfer-based models could be more simplistic and unfair (Pan & Fellow, 2009).”
BackgroundTowards a fully automated algorithm driven platform for biosystems design
HamediRad, M., Chao, R., Weisberg, S., Lian, J., Sinha, S., & Zhao, H. (2019) · Nature Communications · doi:10.1038/s41467-019-13189-z · Cited by 201
Evaluation in artificial intelligence: from task-oriented to ability-oriented measurement
Hernández-Orallo, J. (2017) · Artificial Intelligence Review · doi:10.1007/s10462-016-9505-7 · Cited by 202
“Transfer learning (Pan and Yang 2010), seen as “the improvement of learning in a new task through the transfer of knowledge from a related task that has already been learned” (Torrey and Shavlik 2009), is presented as a solution for this.”
BackgroundLi, Y., Martinis, S., & Wieland, M. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.04.014 · Cited by 199
Multi-Label Classification of Fundus Images With EfficientNet
Wang, J., Yang, L., Huo, Z., He, W., & Luo, J. (2020) · IEEE Access · doi:10.1109/access.2020.3040275 · Cited by 199
A comprehensive review of machine learning‐based methods in landslide susceptibility mapping
Liu, S., Wang, L., Zhang, W., He, Y., & Pijush, S. (2023) · Geological Journal · doi:10.1002/gj.4666 · Cited by 199
“Unlike conventional machine learning which is basically constructed by one dataset, the establishment of a transfer learning-based model needs two different datasets, which were defined as source domain dataset and target domain dataset (Pan & Yang, 2009).”
MethodPHOTOMETRIC SUPERNOVA CLASSIFICATION WITH MACHINE LEARNING
Lochner, M., McEwen, J. D., Peiris, H. V., Lahav, O., & Winter, M. K. (2016) · The Astrophysical Journal Supplement Series · doi:10.3847/0067-0049/225/2/31 · Cited by 200
“However, the effect of non-representativeness, also called the “domain adaptation problem” or “sample selection bias,” can be mitigated using modern techniques in transductive transfer learning (Pan & Yang 2010).”
MethodHybrid Heterogeneous Transfer Learning through Deep Learning
Zhou, J., Pan, S., Tsang, I., & Yan, Y. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8961 · Cited by 197
Self-citationArtificial intelligence for precision oncology: beyond patient stratification
Azuaje, F. (2019) · npj Precision Oncology · doi:10.1038/s41698-019-0078-1 · Cited by 200
“30 TrLe ’ s main assumption is that predictive features learned in an application domain X can in principle be applied to a different, but related, application domain Y .”
BackgroundApplications of Deep Learning for Dense Scenes Analysis in Agriculture: A Review
Zhang, Q., Liu, Y., Gong, C., Chen, Y., & Yu, H. (2020) · Sensors · doi:10.3390/s20051520 · Cited by 199
“Besides, in dense agricultural scenes, for background processing with high similarity to the object, using semantic segmentation to extract the region of interest can achieve good results [66,78].”
Detecting false data attacks using machine learning techniques in smart grid: A survey
Cui, L., Qu, Y., Gao, L., Xie, G., & Yu, S. (2020) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2020.102808 · Cited by 197
A Review of Data-Driven Machinery Fault Diagnosis Using Machine Learning Algorithms
Cen, J., Yang, Z., Liu, X., Xiong, J., & Chen, H. (2022) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-022-00498-9 · Cited by 198
Deep transfer learning of cancer drug responses by integrating bulk and single-cell RNA-seq data
Chen, J., Wang, X., Ma, A., Wang, Q.-E., Liu, B., Li, L., Xu, D., & Ma, Q. (2022) · Nature Communications · doi:10.1038/s41467-022-34277-7 · Cited by 196
Zhao, P., Hoi, S. C. H., Wang, J., & Li, B. (2014) · Artificial Intelligence · doi:10.1016/j.artint.2014.06.003 · Cited by 199
“Despite being explored actively in literature [27,26,2,12,20], most existing approaches on transfer learning often have been studied in an offline/batch learning fashion, which assumes training data in the new domain is given a priori.”
BackgroundInfluentialTang, F., Mao, B., Kawamoto, Y., & Kato, N. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3073009 · Cited by 199
A Survey of Domain Adaptation for Neural Machine Translation
Chu, C., & Wang, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.00258 · Cited by 182
Deep Transfer Learning-Based Downlink Channel Prediction for FDD Massive MIMO Systems
Yang, Y., Gao, F., Zhong, Z., Ai, B., & Alkhateeb, A. (2020) · IEEE Transactions on Communications · doi:10.1109/tcomm.2020.3019077 · Cited by 198
Ab Initio Machine Learning in Chemical Compound Space
Huang, B., & von Lilienfeld, O. A. (2021) · Chemical Reviews · doi:10.1021/acs.chemrev.0c01303 · Cited by 195
A literature review on one-class classification and its potential applications in big data
Seliya, N., Abdollah Zadeh, A., & Khoshgoftaar, T. M. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00514-x · Cited by 193
Tian, J., Chen, C., Shen, W., Sun, F., & Xiong, R. (2023) · Energy Storage Materials · doi:10.1016/j.ensm.2023.102883 · Cited by 195
Alzubaidi, L., Fadhel, M. A., Al-Shamma, O., Zhang, J., & Duan, Y. (2020) · Electronics · doi:10.3390/electronics9030427 · Cited by 197
Object-oriented mapping of urban trees using Random Forest classifiers
Puissant, A., Rougier, S., & Stumpf, A. (2014) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2013.07.002 · Cited by 197
Cao, Y., Jia, M., Ding, P., & Ding, Y. (2021) · Measurement · doi:10.1016/j.measurement.2021.109287 · Cited by 197
Ahmad, M., Abdullah, M., Moon, H., & Han, D. (2021) · IEEE Access · doi:10.1109/access.2021.3119655 · Cited by 197
“Apart from MobileNet_V3_Large, other models used in benchmarking were also trained with stepwise TL.”
BackgroundInfluentialKorkmaz, D., & Acikgoz, H. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.104959 · Cited by 194
Composite Backdoor Attack for Deep Neural Network by Mixing Existing Benign Features
Lin, J., Xu, L., Liu, Y., & Zhang, X. (2020) · Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3372297.3423362 · Cited by 196
“Hence an alternative is to retrain part of a pre-trained model [33, 52, 53].”
BackgroundTransferring a semantic representation for person re-identification and search
Shi, Z., Hospedales, T. M., & Xiang, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299046 · Cited by 192
“Addressing a change of domains with domain adaptation is well studied in computer vision [13, 47, 4] and beyond [42].”
BackgroundIoT and Interpretable Machine Learning Based Framework for Disease Prediction in Pearl Millet
Kundu, N., Rani, G., Dhaka, V. S., Gupta, K., Nayak, S. C., Verma, S., Ijaz, M. F., & Woźniak, M. (2021) · Sensors · doi:10.3390/s21165386 · Cited by 196
“Furthermore, the advancements in deep transfer learning bring down the requirement for the vast dataset [22].”
BackgroundMethodLi, X., Pang, T., Xiong, B., Liu, W., Liang, P., & Wang, T. (2017) · 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) · doi:10.1109/cisp-bmei.2017.8301998 · Cited by 195
“It is reasonable that when there exists explicit relationship between task domains, transfer learning may be able to help improve the target task [33].”
BackgroundMethodInfluentialTan, B., Song, Y., Zhong, E., & Yang, Q. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783295 · Cited by 184
“Transfer Learning solves the lack of class label problem in the target domain by “borrowing” supervised knowledge from related source domains [18].”
BackgroundSelf-citationTransfer Sparse Coding for Robust Image Representation
Long, M., Ding, G., Wang, J., Sun, J., Guo, Y., & Yu, P. S. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.59 · Cited by 189
CLAMI: Defect Prediction on Unlabeled Datasets (T)
Nam, J., & Kim, S. (2015) · 2015 30th IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase.2015.56 · Cited by 192
“In CPDP and UDP, the major task is to make the different distributions of datasets similar since prediction models work well when the datasets for training and testing a model have the same distributions [31], [32].”
BackgroundLooking beyond appearances: Synthetic training data for deep CNNs in re-identification
Barbosa, I. B., Cristani, M., Caputo, B., Rognhaugen, A., & Theoharis, T. (2018) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.12.002 · Cited by 195
“In this case, the trained classifiers should be adapted to the testing situation by attribute learning [38], domain adaptation [39] or transfer learning [40].”
BackgroundVehicleNet: Learning Robust Visual Representation for Vehicle Re-Identification
Zheng, Z., Ruan, T., Wei, Y., Yang, Y., & Mei, T. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3014488 · Cited by 192
“In several existing works, some researchers resort to transfer learning [11], which aims at transferring the useful knowledge from the labeled source domain to the unlabeled target domain and minimizing the discrepancy between the source domain and the target domain.”
BackgroundGeometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation
Zhao, S., Fu, H., Gong, M., & Tao, D. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01002 · Cited by 188
On the application of domain adaptation in structural health monitoring
Gardner, P., Liu, X., & Worden, K. (2020) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2019.106550 · Cited by 193
A General Knowledge Distillation Framework for Counterfactual Recommendation via Uniform Data
Liu, D., Cheng, P., Dong, Z., He, X., Pan, W., & Ming, Z. (2020) · Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3397271.3401083 · Cited by 186
“Moreover, they are also related to the types of knowledge (instance, feature and model) and strategies (adaptive, collective and integrative) in transfer learning [18, 19].”
BackgroundContrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Prediction
Ragab, M., Chen, Z., Wu, M., Foo, C. S., Kwoh, C. K., Yan, R., & Li, X. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3032690 · Cited by 195
Liu, J., Xiang, J., Jin, Y., Liu, R., Yan, J., & Wang, L. (2021) · Remote Sensing · doi:10.3390/rs13214387 · Cited by 193
Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation
Tsai, Y.-H. H., Yeh, Y.-R., & Wang, Y.-C. F. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.549 · Cited by 189
“To alleviate this concern, domain adaptation (DA) aims to utilize labeled data from a source domain, while only few (or no) labeled data can be observed in the target domain of interest [27].”
BackgroundUthoff, R. D., Song, B., Sunny, S., Patrick, S., Suresh, A., Kolur, T., Keerthi, G., Spires, O., Anbarani, A., Wilder-Smith, P., et al. (2018) · PLOS ONE · doi:10.1371/journal.pone.0207493 · Cited by 192
“For the CNN training, methods commonly used in network training were applied including transfer learning [69] and data augmentation [70–72].”
MethodReview on deep learning techniques for marine object recognition: Architectures and algorithms
Wang, N., Wang, Y., & Er, M. J. (2022) · Control Engineering Practice · doi:10.1016/j.conengprac.2020.104458 · Cited by 193
Deep Learning for Channel Estimation: Interpretation, Performance, and Comparison
Hu, Q., Gao, F., Zhang, H., Jin, S., & Li, G. Y. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3042074 · Cited by 191
Leaf image based plant disease identification using transfer learning and feature fusion
Fan, X., Luo, P., Mu, Y., Zhou, R., Tjahjadi, T., & Ren, Y. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.106892 · Cited by 191
Duan, L., Xu, D., & Chang, S.-F. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247819 · Cited by 193
“Domain adaptation ( a.k.a. , cross-domain learning or transfer learning) methods have been used for different applications [22].”
MethodHagerty, J. R., Stanley, R. J., Almubarak, H. A., Lama, N., Kasmi, R., Guo, P., Drugge, R. J., Rabinovitz, H. S., Oliviero, M., & Stoecker, W. V. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2891049 · Cited by 192
“learning [37] of a deep residual network or ResNet [38].”
BackgroundUsing YOLOv3 Algorithm with Pre- and Post-Processing for Apple Detection in Fruit-Harvesting Robot
Kuznetsova, A., Maleva, T., & Soloviev, V. (2020) · Agronomy · doi:10.3390/agronomy10071016 · Cited by 193
Distant Domain Transfer Learning
Tan, B., Zhang, Y., Pan, S. J., & Yang, Q. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10826 · Cited by 214
“In the worst case, it could lead to even worse performance than ‘non-transfer’ algorithms in the target domain, which is the ‘negative transfer’ phenomena (Rosenstein et al. 2005; Pan and Yang 2010).”
BackgroundSelf-citationFederated Adversarial Domain Adaptation
Peng, X., Huang, Z., Zhu, Y., & Saenko, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.02054 · Cited by 128
Ghasemi, A., Hashtarkhani, S., Schwartz, D. L., & Shaban‐Nejad, A. (2024) · Cancer Innovation · doi:10.1002/cai2.136 · Cited by 193
“Despite significant progress over the last years in terms of fine ‐ tuning [7] and optimizing [8 – 11] AI algorithms to tackle supervised and unsupervised tasks, a considerable number of these algorithms remain enigmatic, classified as Black ‐ box and are yet to be demystified.”
BackgroundDeep Transfer Learning for Person Re-identification
Geng, M., Wang, Y., Xiang, T., & Tian, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.05244 · Cited by 192
“tation is an extensively studied topic [17].”
Deep Aesthetic Quality Assessment With Semantic Information
Kao, Y., He, R., & Huang, K. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2651399 · Cited by 192
Yang, Z., Yabansu, Y. C., Jha, D., Liao, W.-K., Choudhary, A. N., Kalidindi, S. R., & Agrawal, A. (2019) · Acta Materialia · doi:10.1016/j.actamat.2018.12.045 · Cited by 192
“Thus, transfer learning [74] can provide a promising alternative.”
BackgroundMa, J., Cheng, J. C. P., Jiang, F., Chen, W., Wang, M., & Zhai, C. (2020) · Energy and Buildings · doi:10.1016/j.enbuild.2020.109941 · Cited by 190
Adaptive Context-Aware Multi-Modal Network for Depth Completion
Zhao, S., Gong, M., Fu, H., & Tao, D. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3079821 · Cited by 174
“[45] proposed to predict depth maps from stereo pair images by exploring unsupervised cues, while some recent works tried to utilize synthetic data [58, 59, 60, 61, 62] based on the domain adaptation technique [63].”
Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation
Ghafoorian, M., Mehrtash, A., Kapur, T., Karssemeijer, N., Marchiori, E., Pesteie, M., Guttmann, C. R. G., Leeuw, F.-E. D., Tempany, C. M., van Ginneken, B., et al. (2017) · Radboud Repository (Radboud University) · Cited by 192
Cao, Y., & Huang, X. (2021) · Remote Sensing of Environment · doi:10.1016/j.rse.2021.112590 · Cited by 191
Metadata
- Authors
- Pan, S. J., & Yang, Q.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- Venue
- IEEE Transactions on Knowledge and Data Engineering
- Published
- 2010-10
- Volume
- 22
- Issue
- 10
- Pages
- 1345-1359
- ISSN
- 1041-4347 (ISSN-L)
- OpenAlex
- W2165698076
- Semantic Scholar
- a25fbcbbae1e8f79c4360d26aa11a3abf1a11972
- Cited by
- 23,387
- References
- 90
- Citations by year
- 2026: 1673 · 2025: 2106 · 2024: 2284 · 2023: 2499 · 2022: 2654 · 2021: 3152 · 2020: 2705 · 2019: 2137 · 2018: 1346 · 2017: 776 · 2016: 516 · 2015: 429 · 2014: 369 · 2013: 293 · 2012: 211
- FWCI
- 160.24
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Knowledge and Data Engineering (publishedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- Funders
- Defense Advanced Research Projects Agency
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- transfer learning, domain adaptation, multi-task learning, sample selection bias, covariate shift, knowledge transfer, classification, regression analysis, clustering, distribution shift
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.