{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:50:47Z","timestamp":1760230247794,"version":"build-2065373602"},"reference-count":46,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T00:00:00Z","timestamp":1657670400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>One way to improve annotation efficiency is active learning. The goal of active learning is to select images from many unlabeled images, where labeling will improve the accuracy of the machine learning model the most. To select the most informative unlabeled images, conventional methods use deep neural networks with a large number of computation nodes and long computation time, but we propose a non-deep neural network method that does not require any additional training for unlabeled image selection. The proposed method trains a task model on labeled images, and then the model predicts unlabeled images. Based on this prediction, an uncertainty indicator is generated for each unlabeled image. Images with a high uncertainty index are considered to have a high information content, and are selected for annotation. Our proposed method is based on a very simple and powerful idea: select samples near the decision boundary of the model. Experimental results on multiple datasets show that the proposed method achieves higher accuracy than conventional active learning methods on multiple tasks and up to 14 times faster execution time from 1.2\u00a0\u00d7\u00a0106 s to 8.3\u00a0\u00d7\u00a0104 s. The proposed method outperforms the current SoTA method by 1% accuracy on CIFAR-10.<\/jats:p>","DOI":"10.3390\/s22145244","type":"journal-article","created":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T00:12:40Z","timestamp":1657757560000},"page":"5244","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Non-Deep Active Learning for Deep Neural Networks"],"prefix":"10.3390","volume":"22","author":[{"given":"Yasufumi","family":"Kawano","sequence":"first","affiliation":[{"name":"Department of Electronics and Electrical Engineering, Faculty of Science and Technology, Keio University, 3-14-1, Hiyoshi, Kohoku-ku, Yokohama 223-8522, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshiki","family":"Nota","sequence":"additional","affiliation":[{"name":"Meidensha Corporation, 2-1-1, Osaki, Shinagawa, Tokyo 141-0032, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rinpei","family":"Mochizuki","sequence":"additional","affiliation":[{"name":"Meidensha Corporation, 2-1-1, Osaki, Shinagawa, Tokyo 141-0032, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-0027","authenticated-orcid":false,"given":"Yoshimitsu","family":"Aoki","sequence":"additional","affiliation":[{"name":"Department of Electronics and Electrical Engineering, Faculty of Science and Technology, Keio University, 3-14-1, Hiyoshi, Kohoku-ku, Yokohama 223-8522, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chen, X., and He, K. (2021, January 20\u201325). Exploring Simple Siamese Representation Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref_2","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13\u201318). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_3","unstructured":"Grill, J., Strub, F., Altche, F., Tallec, C., Richemond, P.H., Buchatskaya, E., Doersch, C., Pires, B.A., Guo, Z.D., and Azar, M.G. (2020). Bootstrap your own latent: A new approach to self-supervised Learning. arXiv."},{"key":"ref_4","unstructured":"Sellars, P., Rivero, A.I.A., and Schonlieb, C. (2021). LaplaceNet: A Hybrid Energy-Neural Model for Deep Semi-Supervised Classification. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Nassar, I., Herath, S., Abbasnejad, E., Buntine, W., and Haffari, G. (2021, January 20\u201325). All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00716"},{"key":"ref_6","unstructured":"Settles, B. (2022, June 06). Active Learning Literature Survey. Available online: https:\/\/minds.wisconsin.edu\/handle\/1793\/60660."},{"key":"ref_7","unstructured":"Gal, Y., Islam, R., and Ghahramani, Z. (2017, January 6\u201311). Deep bayesian active learning with image data. Proceedings of the 2017 International Conference on Machine Learning, Sydney, NSW, Australia."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zhang, J., and Zhang, Y. (2012, January 28\u201330). Multi-sensor image classification based on active learning. Proceedings of the International Conference on Image and Signal Processing, Agadir, Morocco.","DOI":"10.1109\/CISP.2012.6469725"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2218","DOI":"10.1109\/TGRS.2008.2010404","article-title":"Active learning methods for remote sensing image classification","volume":"47","author":"Tuia","year":"2009","journal-title":"Trans. Geosci. Remote Sens."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Jain, S.D., and Grauman, K. (2016, January 27\u201330). Active image segmentation propagation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.313"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Vezhnevets, A., Buhmann, J.M., and Ferrari, V. (2012, January 16\u201321). Active learning for semantic segmentation with expected change. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6248050"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sinha, S., Ebrahimi, S., and Darrell, T. (2019). Variational adversarial active learning. arXiv.","DOI":"10.1109\/ICCV.2019.00607"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, B., Li, L., Yang, S., Wang, S., Zha, Z.-J., and Huang, Q. (2020, January 13\u201319). State-Relabeling Adversarial Active Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00878"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, Y., Ma, K., Ma1, R., Guan, H., and Zheng, Y. (2020, January 23\u201328). Dual Adversarial Network for Deep Active Learning. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58586-0_40"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kim, K., Park, D., Kim, K.I., and Chun, S.Y. (2021, January 20\u201325). Task-Aware Variational Adversarial Active Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00807"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4752568","DOI":"10.1155\/2021\/4752568","article-title":"Redundancy Removal Adversarial Active Learning Based on Norm Online Uncertainty Indicator","volume":"2021","author":"Guo","year":"2021","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yoo, D., and Kweon, I.S. (2019). Learning loss for active learning. arXiv.","DOI":"10.1109\/CVPR.2019.00018"},{"key":"ref_18","unstructured":"Li, X., Yang, P., Wang, T., Zhan, X., Xu, M., Dou, D., and Xu, C. (2022). Deep Active Learning with Noise Stability. arXiv."},{"key":"ref_19","unstructured":"Xie, Y., Tomizuka, M., and Zhan, W. (2021). Towards General and Efficient Active Learning. arXiv."},{"key":"ref_20","first-page":"10041","article-title":"Nearest Neighbor Classifier Embedded Network for Active Learning","volume":"35","author":"Wan","year":"2021","journal-title":"Proc. Aaai Conf. Artif. Intell."},{"key":"ref_21","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Beluch, W.H., Genewein, T., N\u00fcrnberger, A.N., and Kohler, J.M. (2018, January 18\u201323). The power of ensembles for active learning in image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00976"},{"key":"ref_23","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 19\u201324). Dropout as a bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the International Conference on Machine Learning, New York, NY, USA."},{"key":"ref_24","unstructured":"Bilgic, M., and Getoor, L. (2009, January 20\u201324). Link-based active learning. Proceedings of the 2009 NIPS Workshop on Analyzing Networks and Learning with Graphs, Barcelona, Spain."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hasan, M., and Roy-Chowdhury, A.K. (2015, January 7\u201313). Context aware active learning of activity recognition models. Proceedings of the IEEE International Conference on Computer Vision, Washington, DC, USA.","DOI":"10.1109\/ICCV.2015.516"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Aodha, O.M., Campbell, N.D., Kautz, J., and Brostow, G.J. (2014, January 23\u201328). Hierarchical subquery evaluation for active learning on a graph. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.79"},{"key":"ref_27","first-page":"1289","article-title":"Multiple-instance active learning","volume":"20","author":"Settles","year":"2008","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_28","unstructured":"Roy, N., and McCallum, A. (2001, January 1\u201328). Toward optimal active learning through monte carlo estimation of error reduction. Proceedings of the International Conference on Machine Learning, Williamstown, MA, USA."},{"key":"ref_29","unstructured":"Ding, C.K., Rodner, E., Freytag, A., and Denzler, J. (2016). Active and continuous exploration with deep neural networks and expected model output changes. arXiv."},{"key":"ref_30","unstructured":"Sener, O., and Savarese, S. (2017). Active learning for convolutional neural networks: A core-set approach. arXiv."},{"key":"ref_31","first-page":"17","article-title":"Interactive video indexing with statistical active learning","volume":"14","author":"Zha","year":"2012","journal-title":"IEEE Trans."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhang, Y., Chen, J., Zhang, S., and Chen, D.Z. (2017, January 11\u201313). Suggestive annotation: A deep active learning framework for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Quebec City, QC, Canada.","DOI":"10.1007\/978-3-319-66179-7_46"},{"key":"ref_33","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-encoding variational bayes. arXiv."},{"key":"ref_34","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume":"28","author":"Sohn","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_35","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_36","unstructured":"Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv."},{"key":"ref_37","unstructured":"Zhu, J., and Bento, J. (2017). Generative adversarial active learning. arXiv."},{"key":"ref_38","unstructured":"Gorriz, M., Carlier, A., Faure, E., and Nieto, X.G. (2017). Cost-effective active learning for melanoma segmentation. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2591","DOI":"10.1109\/TCSVT.2016.2589879","article-title":"Cost-effective active learning for deep image classification","volume":"27","author":"Wang","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_40","first-page":"45","article-title":"Support vector machine active learning with applications to text classification","volume":"2","author":"Tong","year":"2001","journal-title":"J. Mach. Learn. Res."},{"key":"ref_41","unstructured":"Brinker, K. (2003, January 21\u201324). Incorporating diversity in active learning with support vector machines. Proceedings of the Twentieth International Conference, Washington, DC, USA."},{"key":"ref_42","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images, Citeseer. Technical Report."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2016, January 27\u201330). The cityscapes dataset for semantic urban scene understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., and Tang, X. (2015, January 7\u201313). Deep learning face attributes in the wild. Proceedings of the IEEE International Conference on Computer Vision, Washington, DC, USA.","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref_45","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Yu, F., Koltun, V., and Funkhouser, T. (2017, January 21\u201326). Dilated Residual Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.75"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/14\/5244\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:49:45Z","timestamp":1760140185000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/14\/5244"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,13]]},"references-count":46,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["s22145244"],"URL":"https:\/\/doi.org\/10.3390\/s22145244","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,7,13]]}}}