Deep Active Learning for Computer Vision: Past and Future
Open accessAbstract
As an important data selection schema, active learning emerges as the essential component when iterating an Artificial Intelligence (AI) model. It becomes even more critical given the dominance of deep neural network based models, which are composed of a large number of parameters and data hungry, in application. Despite its indispensable role for developing AI models, research on active learning is not as intensive as other research directions. In this paper, we present a review of active learning through deep active learning approaches from the following perspectives: (1) technical advancements in active learning, (2) applications of active learning in computer vision, (3) industrial systems leveraging or with potential to leverage active learning for data iteration, (4) current limitations and future research directions. We expect this paper to clarify the significance of active learning in a modern AI model manufacturing process and to bring additional research attention to active learning. By addressing data automation challenges and coping with automated machine learning systems, active learning will facilitate democratization of AI technologies by boosting model production at scale.
Integrity signals
Registry
Cites
Statistics
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?
Previous reviews are more oriented to other AI areas such as natural language processing, speech processing, and computer vision, without going deeper into OD, showing only a few related papers.
“Furthermore, previous reviews [8,10-13] are more oriented to other AI areas such as natural language processing, speech processing, and computer vision, but without going deeper into OD, showing only a few related papers.”
From Ten Years of Active Learning Techniques and Object Detection: A Systematic Review (2023) · cites this paper as [13]
The most recent review found was published in November 2022 and addresses applications of active learning in several computer vision tasks, including object detection, but with a superficial contribution.
“The most recent review found [13] was published in November 2022 and addresses the applications of AL in several computer vision tasks, including OD, but with a superficial contribution.”
From Ten Years of Active Learning Techniques and Object Detection: A Systematic Review (2023) · cites this paper as [13]
Five recent active learning reviews were identified in the preliminary search.
“Five recent AL reviews [8,10-13] were identified in that process”
From Ten Years of Active Learning Techniques and Object Detection: A Systematic Review (2023) · cites this paper as [13]
Cites
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347 · see citing works
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857 · see citing works
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512 · see citing works
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489 · see citing works
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. A., Guo, Z. D., Azar, M. G., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.07733 · Cited by 3,846 · see citing works
Progressive Neural Architecture Search
Liu, C., Zoph, B., Neumann, M., Shlens, J., Wei, H., Li, L.-J., Fei-Fei, L., Yuille, A., Huang, J., & Murphy, K. P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01246-5_2 · Cited by 1,946 · see citing works
Understanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514 · see citing works
BEiT: BERT Pre-Training of Image Transformers
Bao, H., Dong, L., Piao, S., & Wei, F. (2021) · arXiv · doi:10.48550/arxiv.2106.08254 · Cited by 1,392 · see citing works
Heterogeneous Uncertainty Sampling for Supervised Learning
Lewis, D. D., & Catlett, J. (1994) · Elsevier eBooks · doi:10.1016/b978-1-55860-335-6.50026-x · Cited by 1,174 · see citing works
A Survey of Deep Active Learning
Ren, P., Xiao, Y., Chang, X., Huang, P.-Y., Li, Z., Gupta, B. B., Chen, X., & Wang, X. (2022) · ACM Computing Surveys · doi:10.1145/3472291 · Cited by 1,169 · see citing works
Self-citationDeep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support
(2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67558-9 · Cited by 1,149 · see citing works
Active Learning for Convolutional Neural Networks: A Core-Set Approach
Sener, O., & Savarese, S. (2017) · arXiv · doi:10.48550/arxiv.1708.00489 · Cited by 922 · see citing works
Deep Bayesian Active Learning with Image Data
Gal, Y., Islam, R., & Ghahramani, Z. (2017) · arXiv · doi:10.48550/arxiv.1703.02910 · Cited by 900 · see citing works
Learning Loss for Active Learning
Yoo, D., & Kweon, I. S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00018 · Cited by 740 · see citing works
Employing EM and Pool-Based Active Learning for Text Classification
McCallum, A., & Nigam, K. (1998) · Cited by 689 · see citing works
Label Propagation for Deep Semi-Supervised Learning
Iscen, A., Tolias, G., Avrithis, Y., & Chum, O. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00521 · Cited by 686 · see citing works
Active learning using pre-clustering
Nguyen, H. T., & Smeulders, A. W. M. (2004) · doi:10.1145/1015330.1015349 · Cited by 671 · see citing works
Cost-Effective Active Learning for Deep Image Classification
Wang, K., Zhang, D., Li, Y., Zhang, R., & Lin, L. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2589879 · Cited by 669 · see citing works
The Power of Ensembles for Active Learning in Image Classification
Beluch, W. H., Genewein, T., Nurnberger, A., & Kohler, J. M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00976 · Cited by 655 · see citing works
Kampffmeyer, M., Salberg, A.-B., & Jenssen, R. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.90 · Cited by 618 · see citing works
Variational Adversarial Active Learning
Sinha, S., Ebrahimi, S., & Darrell, T. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00607 · Cited by 585 · see citing works
Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation
Yang, L., Zhang, Y., Chen, J., Zhang, S., & Chen, D. Z. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-66179-7_46 · Cited by 526 · see citing works
Self-citationBayesian Active Learning for Classification and Preference Learning
Houlsby, N., Huszár, F., Ghahramani, Z., & Lengyel, M. (2011) · arXiv · doi:10.48550/arxiv.1112.5745 · Cited by 507 · cited 5× · see citing works
“BatchBALD takes this issue into account and makes itself more likely to acquire a diverse cover.”
BackgroundInfluentialMultiple-Instance Active Learning
Settles, B., Craven, M. W., & Ray, S. (2007) · Cited by 458 · see citing works
Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization
Yang, Y., Ma, Z., Nie, F., Chang, X., & Hauptmann, A. G. (2014) · International Journal of Computer Vision · doi:10.1007/s11263-014-0781-x · Cited by 448 · see citing works
Deep Active Learning for Named Entity Recognition
Shen, Y., Yun, H., Lipton, Z. C., Kronrod, Y., & Anandkumar, A. (2017) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w17-2630 · Cited by 389 · see citing works
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower BoundsPreprint
Ash, J. T., Zhang, C., Krishnamurthy, A., Langford, J. C., & Agarwal, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.03671 · Cited by 366 · see citing works
Active Deep Learning for Classification of Hyperspectral Images
Liu, P., Zhang, H., & Eom, K. B. (2016) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2016.2598859 · Cited by 290 · see citing works
Batch Active Learning at ScalePreprint
Citovsky, G., DeSalvo, G., Gentile, C., Karydas, L., Rajagopalan, A., Rostamizadeh, A., & Kumar, S. (2021) · Neural Information Processing Systems · doi:10.48550/arxiv.2107.14263 · Cited by 226 · see citing works
Selecting Influential Examples: Active Learning with Expected Model Output Changes
Freytag, A., Rodner, E., & Denzler, J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10593-2_37 · Cited by 200 · see citing works
Task-Aware Variational Adversarial Active Learning
Kim, K., Park, D., Kim, K. I., & Chun, S. (2020) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr46437.2021.00807 · Cited by 187 · see citing works
Adversarial Active Learning for Deep Networks: a Margin Based ApproachPreprint
Ducoffe, M., & Precioso, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.09841 · Cited by 181 · see citing works
Consistency-Based Semi-supervised Active Learning: Towards Minimizing Labeling Cost
Gao, M., Zhang, Z., Yu, G., Arık, S. Ö., Davis, L. S., & Pfister, T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58607-2_30 · Cited by 180 · see citing works
Contextual Diversity for Active Learning
Agarwal, S., Arora, H., Anand, S., & Arora, C. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58517-4_9 · Cited by 176 · see citing works
Deng, C. D., Xue, Y., Liu, X., Li, C., & Tao, D. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2868851 · Cited by 168 · see citing works
Self-citationDeep Active Learning over the Long TailPreprint
Geifman, Y., & El-Yaniv, R. (2017) · arXiv.org · doi:10.48550/arxiv.1711.00941 · Cited by 166 · see citing works
Bayesian Generative Active Deep LearningPreprint
Tran, T., Do, T.-T., Reid, I., & Carneiro, G. (2019) · International Conference on Machine Learning · doi:10.48550/arxiv.1904.11643 · Cited by 160 · see citing works
Margin-Based Active Learning for Structured Output Spaces
Roth, D., & Small, K. (2006) · Lecture notes in computer science · doi:10.1007/11871842_40 · Cited by 156 · see citing works
Multiple Instance Active Learning for Object Detection
Yuan, T., Wan, F., Fu, M., Liu, J., Xu, S., Ji, X., & Ye, Q. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00529 · Cited by 155 · see citing works
Multi-class active learning for image classification
Joshi, A., Porikli, F., & Papanikolopoulos, N. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvprw.2009.5206627 · Cited by 148 · see citing works
Active Learning for Deep Detection Neural Networks
Aghdam, H. H., Gonzalez-Garcia, A., Lopez, A., & Weijer, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00377 · Cited by 148 · cited 1× · see citing works
“[81] compute pixel-level uncertainty scores by the divergence among predictions at different levels of decoder for each pixel and their neighborhoods.”
BackgroundA Comparative Survey of Deep Active LearningPreprint
Zhan, X.-Y., Wang, Q.-Z., Huang, K.-H., Xiong, H., Dou, D., & Chan, A. B. (2022) · arXiv.org · doi:10.48550/arxiv.2203.13450 · Cited by 146 · see citing works
A Convex Optimization Framework for Active Learning
Elhamifar, E., Sapiro, G., Yang, A. Y., & Sasrty, S. S. (2013) · IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.33 · Cited by 140 · see citing works
Active Learning for Deep Object Detection via Probabilistic Modeling
Choi, J., Elezi, I., Lee, H.-J., Farabet, C., & Alvarez, J. M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01010 · Cited by 135 · cited 1× · see citing works
“[84] learn a Gaussian Mixture Model (GMM) for the network outputs including both localization and classification.”
BackgroundReinforced active learning for image segmentationPreprint
Casanova, A., Pinheiro, P. H. O., Rostamzadeh, N., & Pal, C. (2020) · International Conference on Learning Representations · doi:10.48550/arxiv.2002.06583 · Cited by 134 · see citing works
Sequential Graph Convolutional Network for Active Learning
Caramalau, R., Bhattarai, B., & Kim, T. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00946 · Cited by 133 · see citing works
State-Relabeling Adversarial Active Learning
Zhang, B., Li, L., Yang, S., Wang, S., Zha, Z.-J., & Huang, Q. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00878 · Cited by 132 · see citing works
Generative Adversarial Active LearningPreprint
Zhu, J.-J., & Bento, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.07956 · Cited by 130 · see citing works
Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection
Wang, K., Yan, X., Zhang, D., Zhang, L., & Lin, L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00173 · Cited by 127 · see citing works
Active Instance Sampling via Matrix Partition
Guo, Y. (2010) · Cited by 124 · see citing works
Active Discriminative Text Representation Learning
Zhang, Y., Lease, M., & Wallace, B. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10962 · Cited by 120 · see citing works
Localization-Aware Active Learning for Object Detection
Kao, C.-C., Lee, T.-Y., Sen, P., & Liu, M.-Y. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-20876-9_32 · Cited by 118 · see citing works
Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-Identification
Liu, Z., Wang, J., Gong, S., Tao, D., & Lu, H. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00622 · Cited by 115 · see citing works
Active Deep Networks for Semi-Supervised Sentiment Classification
Zhou, S., Chen, Q., & Wang, X. (2010) · Cited by 110 · see citing works
Self-citationDiscriminative Active LearningPreprint
Gissin, D., & Shalev‐Shwartz, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.06347 · Cited by 108 · see citing works
Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint
Wu, J., Chen, J., & Huang, D. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00918 · Cited by 104 · see citing works
Video Annotation and Tracking with Active Learning
Vondrick, C., & Ramanan, D. (2011) · Cited by 104 · see citing works
MST: Masked Self-Supervised Transformer for Visual RepresentationPreprint
Li, Z., Chen, Z., Yang, F., Li, W., Zhu, Y., Zhao, C., Deng, R., Wu, L., Zhao, R., Tang, M., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.05656 · Cited by 99 · see citing works
Diverse mini-batch Active LearningPreprint
Zhdanov, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.05954 · Cited by 96 · see citing works
CAPTCHA Recognition with Active Deep Learning
Stark, F., Hazırbaş, C., Triebel, R., & Cremers, D. (2015) · Cited by 92 · see citing works
Hierarchical Subquery Evaluation for Active Learning on a Graph
Aodha, O. M., Campbell, N. D. F., Kautz, J., & Brostow, G. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.79 · Cited by 91 · see citing works
Context Aware Active Learning of Activity Recognition Models
Hasan, M., & Roy–Chowdhury, A. K. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.516 · Cited by 91 · see citing works
Yao, A., Gall, J., Leistner, C., & Gool, L. V. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6248060 · Cited by 88 · see citing works
Active learning based news veracity detection with feature weighting and deep-shallow fusion
Bhattacharjee, S. D., Talukder, A., & Balantrapu, B. V. (2017) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2017.8257971 · Cited by 87 · see citing works
Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector
Feng, D., Wei, X., Rosenbaum, L., Maki, A., & Dietmayer, K. (2019) · 2019 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2019.8814236 · Cited by 85 · see citing works
Revisiting Superpixels for Active Learning in Semantic Segmentation with Realistic Annotation Costs
Cai, L.-L., Xu, X., Liew, J., & Foo, C. S. (2021) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr46437.2021.01084 · Cited by 83 · see citing works
Folmsbee, J., Liu, X., Brandwein‐Weber, M., & Doyle, S. T. (2018) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2018.8363686 · Cited by 80 · see citing works
Self-citationCEREALS - Cost-Effective REgion-based Active Learning for Semantic SegmentationPreprint
Mackowiak, R., Lenz, P., Ghori, O., Diego, F., Lange, O., & Rother, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.09726 · Cited by 80 · see citing works
Deep Active Learning: Unified and Principled Method for Query and TrainingPreprint
Shui, C., Zhou, F., Gagné, C., & Wang, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.09162 · Cited by 80 · see citing works
Cost-Effective Active Learning for Melanoma Segmentation
Gorriz, M., Carlier, A., Faure, E., & Giró-i-Nieto, X. (2017) · RECERCAT (Consorci de Serveis Universitaris de Catalunya) · doi:10.48550/arxiv.1711.09168 · Cited by 79 · see citing works
Consistency-based Active Learning for Object Detection
Yu, W., Zhu, S., Yang, T., & Chen, C. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00440 · Cited by 78 · see citing works
Batch Active Learning Using Determinantal Point ProcessesPreprint
Biyik, E., Wang, K., Anari, N., & Sadigh, D. (2019) · arXiv.org · doi:10.48550/arxiv.1906.07975 · Cited by 75 · see citing works
Deep active learning for object detection
Roy, S. D., Unmesh, A., & Namboodiri, V. P. (2018) · Cited by 71 · see citing works
Active-Learning-Incorporated Deep Transfer Learning for Hyperspectral Image Classification
Lin, J., Zhao, L., Li, S., Ward, R. K., & Wang, Z. J. (2018) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2018.2874225 · Cited by 65 · see citing works
Reducing Label Effort: Self-Supervised meets Active Learning
Bengar, J. Z., van de Weijer, J., Twardowski, B., & Raducanu, B. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00188 · Cited by 64 · see citing works
Classification of ECG beats using deep belief network and active learning
Sayantan, G., Kien, P. T., & Kadambari, K. V. (2018) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-018-1815-2 · Cited by 62 · see citing works
ActiveLink: Deep Active Learning for Link Prediction in Knowledge Graphs
Ostapuk, N., Yang, J., & Cudré-Mauroux, P. (2019) · The Web Conference · doi:10.1145/3308558.3313620 · Cited by 54 · see citing works
Deep Similarity-Based Batch Mode Active Learning with Exploration-Exploitation
Yin, C., Qian, B., Cao, S., Li, X., Wei, J., Zheng, Q., & Davidson, I. A. K. (2017) · Proceedings · doi:10.1109/icdm.2017.67 · Cited by 52 · see citing works
Rethinking deep active learning: Using unlabeled data at model training
Siméoni, O., Budnik, M., Avrithis, Y., & Gravier, G. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412716 · Cited by 51 · see citing works
Multi-level Adaptive Active Learning for Scene Classification
Li, X., & Guo, Y. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10584-0_16 · Cited by 49 · see citing works
Active Learning for Deep Object Detection
Brust, C.-A., Käding, C., & Denzler, J. (2019) · Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications · doi:10.5220/0007248600002108 · Cited by 48 · see citing works
All you need are a few pixels: semantic segmentation with PixelPick
Shin, G., Xie, W., & Albanie, S. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00194 · Cited by 46 · see citing works
Bilgic, M., & Getoor, L. C. (2009) · Cited by 41 · see citing works
Pair-based Uncertainty and Diversity Promoting Early Active Learning for Person Re-identification
Liu, W., Chang, X., Chen, L., Phung, D., Zhang, X., Yang, Y., & Hauptmann, A. G. (2020) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3372121 · Cited by 41 · see citing works
Active and Continuous Exploration with Deep Neural Networks and Expected Model Output ChangesPreprint
Käding, C., Rodner, E., Freytag, A., & Denzler, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.06129 · Cited by 40 · see citing works
Deep Active Learning for In Situ Plankton Classification
Bochinski, E., Bacha, G., Eiselein, V., Walles, T. J. W., Nejstgaard, J. C., & Sikora, T. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-05792-3_1 · Cited by 40 · see citing works
Importance of Self-Consistency in Active Learning for Semantic Segmentation
Golestaneh, S. A., & Kitani, K. (2020) · British Machine Vision Conference (BMVC) · doi:10.5244/c.34.3 · Cited by 31 · see citing works
Contrastive Coding for Active Learning under Class Distribution Mismatch
Du, P., Zhao, S., Chen, H., Chai, S., Chen, H., & Li, C. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00880 · Cited by 31 · see citing works
An Adaptive Supervision Framework for Active Learning in Object Detection
Desai, S. V., Chandra, A. L., Guo, W., Ninomiya, S., & Balasubramanian, V. N. (2019) · arXiv · doi:10.48550/arxiv.1908.02454 · Cited by 29 · see citing works
Du, B., Qi, Q., Zheng, H., Huang, Y., & Ding, X. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01421-6_11 · Cited by 28 · see citing works
SIMILAR: Submodular Information Measures Based Active Learning In Realistic ScenariosPreprint
Kothawade, S. N., Beck, N., Killamsetty, K., & Iyer, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.00717 · Cited by 28 · see citing works
Deep Active Self-paced Learning for Accurate Pulmonary Nodule Segmentation
Wang, W., Lu, Y., Wu, B., Chen, T., Chen, D. Z., & Wu, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00934-2_80 · Cited by 25 · see citing works
Boosting Active Learning via Improving Test Performance
Wang, T., Li, X., Yang, P., Hu, G., Zeng, X., Huang, S., Xu, C., & Xu, M. (2022) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v36i8.20834 · Cited by 25 · see citing works
Ranking CGANs: Subjective Control over Semantic Image AttributesPreprint
Saquil, Y., Kim, K. I., & Hall, P. M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.04082 · Cited by 21 · see citing works
Highly Efficient Regression for Scalable Person Re-Identification
Wang, H., Gong, S., & Xiang, T. (2016) · British Machine Vision Conference (BMVC) · doi:10.5244/c.30.134 · Cited by 21 · see citing works
Deep Active Learning for Text Classification
An, B., Wu, W., & Han, H. (2018) · International Conference on Vision, Image and Signal Processing (ICVISP) · doi:10.1145/3271553.3271578 · Cited by 21 · see citing works
Amazon SageMaker Autopilot: a white box AutoML solution at scalePreprint
Das, P., Perrone, V., Ivkin, N. P., Bansal, T., Karnin, Z. S., Shen, H., Shcherbatyi, I., Elor, Y., Wu, W., Zolic, A., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.08483 · Cited by 19 · see citing works
Early Active Learning with Pairwise Constraint for Person Re-identification
Liu, W., Chang, X., Chen, L., & Yang, Y. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-71249-9_7 · Cited by 18 · see citing works
LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active LearningPreprint
Kim, Y.-Y., Song, K., Jang, J., & Moon, I. (2021) · arXiv (Cornell University) · Cited by 18 · see citing works
Towards Fine-grained Sampling for Active Learning in Object Detection
Vikas Desai, S., & Balasubramanian, V. N. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00470 · Cited by 14 · see citing works
On the Marginal Benefit of Active Learning: Does Self-Supervision Eat its Cake?
Chan, Y.-C., Li, M., & Oymak, S. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414665 · Cited by 11 · see citing works
ALBench: A Framework for Evaluating Active Learning in Object DetectionPreprint
Feng, Z.-P., Zhang, S.-L., Takezoe, R., Hu, W., Chandraker, M., Li, L.-J., Narayanan, V., & Wang, X. (2022) · arXiv.org · doi:10.48550/arxiv.2207.13339 · Cited by 9 · see citing works
Self-citationBAOD: Budget-Aware Object Detection
Pardo, A., Xu, M., Thabet, A., Arbeláez, P., & Ghanem, B. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00137 · Cited by 8 · see citing works
YMIR: A Rapid Data-centric Development Platform for Vision ApplicationsPreprint
Huang, P. X., Hu, W., Brendel, W., Chandraker, M., Li, L.-J., & Wang, X. (2021) · arXiv.org · doi:10.48550/arxiv.2111.10046 · Cited by 7 · see citing works
Self-citationActive learning with version spaces for object detectionPreprint
Roy, S. D., Namboodiri, V. P., & Biswas, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.07285 · Cited by 6 · see citing works
Deep Active Learning for Video-based Person Re-identificationPreprint
Wang, M., Lai, B., Jin, Z., Gong, X., Huang, J., & Hua, X. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.05785 · Cited by 4 · see citing works
Suzuki, K., Sunagawa, T., Sasaki, T., & Katoh, T. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636355 · Cited by 2 · see citing works
Towards Fewer Labels: Support Pair Active Learning for Person Re-identificationPreprint
Jin, D., & Li, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2204.10008 · Cited by 1 · see citing works
Unsupervised Clustering Active Learning for Person Re-identificationPreprint
Gao, W.-J., & Li, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.13308 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Ten deep learning techniques to address small data problems with remote sensing
Safonova, A. N., Ghazaryan, G., Stiller, S., Main-Knorn, M., Nendel, C., & Ryo, M. (2023) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2023.103569 · Cited by 202 · see citing works
A Survey on Deep Active Learning: Recent Advances and New Frontiers
Li, D., Wang, Z. R., Chen, Y., Jiang, R., Ding, W., & Okumura, M. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3396463 · Cited by 145 · see citing works
A comprehensive survey on deep active learning in medical image analysis
Wang, H., Jin, Q., Li, S., Liu, S., Wang, M., & Song, Z. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103201 · Cited by 139 · see citing works
Image steganalysis using active learning and hyperparameter optimization
Bohang, L., Li, N., Yang, J., Alfarraj, O., Albelhai, F., Tolba, A. K. R., Shaikh, Z. A., Alizadehsani, R., Pławiak, P., & Yee, P. L. (2025) · Scientific Reports · doi:10.1038/s41598-025-92082-w · Cited by 33 · see citing works
A multivocal literature review on the benefits and limitations of industry-leading AutoML tools
Quaranta, L., Azevedo, K., Calefato, F., & Kalinowski, M. (2024) · Information and Software Technology · doi:10.1016/j.infsof.2024.107608 · Cited by 24 · see citing works
Lee, H., & Li, W.-W. (2024) · Remote Sensing of Environment · doi:10.1016/j.rse.2024.114213 · Cited by 28 · see citing works
A Survey of Deep Active Learning for Foundation Models
Wan, T., Xu, K., Yu, T., Wang, X., Feng, D., Ding, B. Y., & Wang, H. (2023) · Intelligent Computing · doi:10.34133/icomputing.0058 · Cited by 22 · see citing works
Self-citationTen Years of Active Learning Techniques and Object Detection: A Systematic Review
Garcia, D., Carias, J., Adão, T., Jesus, R., Cunha, A., & Magalhães, L. G. (2023) · Applied Sciences · doi:10.3390/app131910667 · Cited by 17 · see citing works
Enabling people-centric climate action using human-in-the-loop artificial intelligence: a review
Debnath, R., Tkachenko, N., & Bhattacharyya, M. (2025) · Current Opinion in Behavioral Sciences · doi:10.1016/j.cobeha.2025.101482 · Cited by 12 · see citing works
Pičuljan, N., & Car, Ž. (2023) · Applied Sciences · doi:10.3390/app13106234 · Cited by 10 · see citing works
Active learning with Bayesian CNN Using the BALD Method for Hyperspectral Image Classification
Qadir, M. S., & Bilgin, G. (2023) · Mesopotamian Journal of Big Data · doi:10.58496/mjbd/2023/008 · Cited by 7 · see citing works
Deep learning framework for enhanced MRI analysis in healthcare diagnosis
Wen, X. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128487 · Cited by 6 · see citing works
Automatic Pruning and Quality Assurance of Object Detection Datasets for Autonomous Driving
Kim, K., Kakani, V., & Kim, H. (2025) · Electronics · doi:10.3390/electronics14091882 · Cited by 5 · see citing works
EchoVisuAL: Efficient Segmentation of Echocardiograms Using Deep Active Learning
Galter, I. R., Schneltzer, E., Marr, C., IMPC Consortium, Spielmann, N., & de Angelis, M. H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-66958-3_27 · Cited by 2 · see citing works
Yang, J., Tan, J., Wang, H.-B., Chen, G., Wu, S., & Zhao, J.-B. (2025) · Machine-mediated learning · doi:10.1007/s10994-024-06684-y · Cited by 2 · see citing works
Dymchenko, S., Purandare, A., & Raffin, B. (2024) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/scw63240.2024.00012
Active Learning for Railway Semantic Segmentation through Ant Colony Optimization
Alexandrescu, A.-R., & Dioşan, L. S. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.09.491
An active learning framework for adversarial training of deep neural networks
Ghosh, S., Chatterjee, A., & Fiondella, L. (2025) · Neural Computing and Applications · doi:10.1007/s00521-024-10851-6
FedRAL: Cost-Effective Distributed Annotation via Federated Reinforced Active Learning
Lazaridis, Y., Kastellos, A., Psaltis, A., & Daras, P. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10930759
Image steganalysis using reinforcement learning-based active learning and scope loss function
Al-Obaidi, S. A. R., Lighvan, . Z., & Alnaseri, M. T. (2025) · Intelligent Decision Technologies · doi:10.1177/18724981241309450
Tohidifar, A., & Kim, D. (2025) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784486115.056
Feature space variation-based active learning sample query strategy for graph deep learning
Chen, X., Lin, M., Wang, Y., Li, J., Ye, F., & Fu, Y.-G. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131165
Anomaly detection in rotating machinery via active learning of unlabeled vibration samples
Li, G., Hou, X., & Zhang, Q. (2026) · Journal of Vibroengineering · doi:10.21595/jve.2026.25485
Adaptive Active Learning with Dynamic Uncertainty-Diversity Balancing for Object Detection
Auh, J., Cho, C., & Kim, S. (2026) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-026-02380-2
Naeni, L. Y., Théau, J., Homayouni, S., Langlois, A., Varin, M., Genest, M.-A., & Rahimzad, M. (2026) · Canadian Journal of Remote Sensing · doi:10.1080/07038992.2026.2709837
Minarwati, & Hardiadi, A. P. (2026) · International Conference on Electronics Representation and Algorithm (ICERA) · doi:10.1109/icera72709.2026.11666714
- Authors
- Takezoe, R., Liu, X., Mao, S., Chen, M. T., Feng, Z., Zhang, S., & Wang, X.
- Affiliations
- Peking University (CN)
- National University of Singapore (SG)
- Chinese Academy of Sciences (CN)
- Intellifusion Inc. ,
- Venue
- APSIPA Transactions on Signal and Information Processing
- Publisher
- Emerald
- Published
- 2023-12-06
- Volume
- 12
- Issue
- 1
- Pages
- 1-38
- ISSN
- 2048-7703 (ISSN-L)
- OpenAlex
- W4313199175
- Cited by
- 26
- References
- 109
- Citations by year
- 2026: 5 · 2025: 8 · 2024: 8 · 2023: 5
- FWCI
- 2.30
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- APSIPA Transactions on Signal and Information Processing (publishedVersion, cc-by-nc)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Keywords
- active learning (machine learning), deep active learning, data selection, deep neural network, computer vision, automated machine learning, data automation, model training efficiency, democratization of AI
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
