{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T05:25:56Z","timestamp":1763443556938,"version":"3.45.0"},"reference-count":44,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011789","name":"Jilin Province Science and Technology Department","doi-asserted-by":"publisher","award":["YDZJ202401610ZYTS"],"award-info":[{"award-number":["YDZJ202401610ZYTS"]}],"id":[{"id":"10.13039\/501100011789","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Accurate uncertainty estimation in unlabeled data represents a fundamental challenge in active learning. Traditional deep active learning approaches suffer from a critical limitation: uncertainty-based selection strategies tend to concentrate excessively around noisy decision boundaries, while diversity-based methods may miss samples that are crucial for decision-making. This over-reliance on confidence metrics when employing deep neural networks as backbone architectures often results in suboptimal data selection. We introduce Distance-Measured Data Mixing (DM2), a novel framework that estimates sample uncertainty through distance-weighted data mixing to capture inter-sample relationships and the underlying data manifold structure. This approach enables informative sample selection across the entire data distribution while maintaining focus on near-boundary regions without overfitting to the most ambiguous instances. To address noise and instability issues inherent in boundary regions, we propose a boundary-aware feature fusion mechanism integrated with fast gradient adversarial training. This technique generates adversarial counterparts of selected near-boundary samples and trains them jointly with the original instances, thereby enhancing model robustness and generalization capabilities under complex or imbalanced data conditions. Comprehensive experiments across diverse tasks, model architectures, and data modalities demonstrate that our approach consistently surpasses strong uncertainty-based and diversity-based baselines while significantly reducing the number of labeled samples required for effective learning.<\/jats:p>","DOI":"10.3390\/e27111159","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T16:46:22Z","timestamp":1763138782000},"page":"1159","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust Deep Active Learning via Distance-Measured Data Mixing and Adversarial Training"],"prefix":"10.3390","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8879-8445","authenticated-orcid":false,"given":"Shinan","family":"Song","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5054-5684","authenticated-orcid":false,"given":"Xing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China"}]},{"given":"Shike","family":"Dong","sequence":"additional","affiliation":[{"name":"Sendelta International Academy Shenzhen, Shenzhen 518100, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4897-2645","authenticated-orcid":false,"given":"Jingyan","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Bigdata and Internet, Shenzhen Technology University, Shenzhen 518118, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Parvaneh, A., Abbasnejad, E., Teney, D., Haffari, G.R., Van Den Hengel, A., and Shi, J.Q. (2022, January 18\u201324). Active learning by feature mixing. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01192"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Munjal, P., Hayat, N., Hayat, M., Sourati, J., and Khan, S. (2022, January 18\u201324). Towards robust and reproducible active learning using neural networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00032"},{"key":"ref_3","unstructured":"Settles, B. (2024, January 01). Active Learning Literature Survey. Technical Report. Available online: https:\/\/minds.wisconsin.edu\/handle\/1793\/60660."},{"key":"ref_4","unstructured":"Gal, Y., Islam, R., and Ghahramani, Z. (2017, January 6\u201311). Deep bayesian active learning with image data. Proceedings of the International Conference on Machine Learning, PMLR, Sydney, Australia."},{"key":"ref_5","unstructured":"Lewis, D.D. (1994, January 3\u20136). A sequential algorithm for training text classifiers: Corrigendum and additional data. Proceedings of the ACM SIGIR Forum, New York, NY, USA."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1002\/widm.1132","article-title":"Active learning with support vector machines","volume":"4","author":"Kremer","year":"2014","journal-title":"WIREs Data Min. Knowl. Discov."},{"key":"ref_7","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 20\u201322). Dropout as a bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the International Conference on Machine Learning, PMLR, New York, NY, USA."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1023\/A:1007330508534","article-title":"Selective sampling using the query by committee algorithm","volume":"28","author":"Freund","year":"1997","journal-title":"Mach. Learn."},{"key":"ref_9","unstructured":"Gorriz, M., Carlier, A., Faure, E., and Giro-i Nieto, X. (2017). Cost-effective active learning for melanoma segmentation. arXiv."},{"key":"ref_10","unstructured":"Ducoffe, M., and Precioso, F. (2018). Adversarial active learning for deep networks: A margin based approach. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Mayer, C., and Timofte, R. (2020, January 1\u20135). Adversarial sampling for active learning. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Snowmass Village, CO, USA.","DOI":"10.1109\/WACV45572.2020.9093556"},{"key":"ref_12","unstructured":"Sener, O., and Savarese, S. (2017). Active learning for convolutional neural networks: A core-set approach. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Caramalau, R., Bhattarai, B., and Kim, T.K. (2021, January 19\u201325). Sequential graph convolutional network for active learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR46437.2021.00946"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yoo, D., and Kweon, I.S. (2019, January 15\u201320). Learning loss for active learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00018"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ding, H., Zhong, H., Li, W., Dai, J., and He, C. (2021, January 11\u201317). Influence selection for active learning. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00914"},{"key":"ref_16","unstructured":"Wang, T., Li, X., Yang, P., Hu, G., Zeng, X., Huang, S., Xu, C.Z., and Xu, M. (March, January 22). Boosting active learning via improving test performance. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual."},{"key":"ref_17","unstructured":"Koh, P.W., and Liang, P. (2017, January 6\u201311). Understanding black-box predictions via influence functions. Proceedings of the International Conference on Machine Learning. PMLR, Sydney, Australia."},{"key":"ref_18","unstructured":"Sinha, S., Ebrahimi, S., and Darrell, T. (November, January 27). Variational adversarial active learning. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_19","unstructured":"Ash, J.T., Zhang, C., Krishnamurthy, A., Langford, J., and Agarwal, A. (2019). Deep batch active learning by diverse, uncertain gradient lower bounds. arXiv."},{"key":"ref_20","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images. [Master\u2019s Thesis, University of Toronto]."},{"key":"ref_21","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wang, D., and Shang, Y. (2014, January 6\u201311). A new active labeling method for deep learning. Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN), Beijing, China.","DOI":"10.1109\/IJCNN.2014.6889457"},{"key":"ref_23","unstructured":"Kirsch, A., van Amersfoort, J., and Gal, Y. (2019, January 8\u201314). BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada. Available online: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/95323660ed2124450caaac2c46b5ed90-Paper.pdf."},{"key":"ref_24","unstructured":"Houlsby, N., Husz\u00e1r, F., Ghahramani, Z., and Lengyel, M. (2011). Bayesian active learning for classification and preference learning. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3153","DOI":"10.1109\/LRA.2020.2974682","article-title":"A general framework for uncertainty estimation in deep learning","volume":"5","author":"Loquercio","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kuo, W., H\u00e4ne, C., Yuh, E., Mukherjee, P., and Malik, J. (2018, January 16\u201320). Cost-sensitive active learning for intracranial hemorrhage detection. Proceedings of the Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2018: 21st International Conference, Granada, Spain. Proceedings, Part III 11.","DOI":"10.1007\/978-3-030-00931-1_82"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Beluch, W.H., Genewein, T., N\u00fcrnberger, A., and K\u00f6hler, 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_28","first-page":"22354","article-title":"Active learning through a covering lens","volume":"35","author":"Yehuda","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Elhamifar, E., Sapiro, G., Yang, A., and Sasrty, S.S. (2013, January 1\u20138). A convex optimization framework for active learning. Proceedings of the IEEE International Conference on Computer Vision, Sydney, Australia.","DOI":"10.1109\/ICCV.2013.33"},{"key":"ref_30","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, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.516"},{"key":"ref_31","first-page":"11933","article-title":"Batch active learning at scale","volume":"34","author":"Citovsky","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_32","unstructured":"Li, X., Yang, P., Gu, Y., Zhan, X., Wang, T., Xu, M., and Xu, C. (2024, January 26\u201327). Deep active learning with noise stability. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, ON, Canada."},{"key":"ref_33","unstructured":"Yang, C., Wu, Q., Li, H., and Chen, Y. (2017). Generative poisoning attack method against neural networks. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Guo, R., Chen, Q., Liu, H., and Wang, W. (2024). Adversarial robustness enhancement for deep learning-based soft sensors: An adversarial training strategy using historical gradients and domain adaptation. Sensors, 24.","DOI":"10.3390\/s24123909"},{"key":"ref_35","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2024, January 01). Automatic Differentiation in Pytorch. Available online: https:\/\/openreview.net\/pdf?id=BJJsrmfCZ."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_37","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Wang, Z., Qinami, K., Karakozis, I.C., Genova, K., Nair, P., Hata, K., and Russakovsky, O. (2020, January 13\u201319). Towards fairness in visual recognition: Effective strategies for bias mitigation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00894"},{"key":"ref_39","first-page":"237","article-title":"Augmax: Adversarial composition of random augmentations for robust training","volume":"34","author":"Wang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_40","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., and Ng, A.Y. (2011, January 12\u201317). Reading digits in natural images with unsupervised feature learning. Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, Granada, Spain."},{"key":"ref_41","unstructured":"Bottou, L. (2010, January 22\u201327). Large-scale machine learning with stochastic gradient descent. Proceedings of the COMPSTAT\u20192010: 19th International Conference on Computational Statistics, France, Paris. Keynote, Invited and Contributed Papers."},{"key":"ref_42","first-page":"12827","article-title":"Uncertainty aware semi-supervised learning on graph data","volume":"33","author":"Zhao","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_44","unstructured":"Mittal, S. (2024, January 15\u201316). Image Classification of Satellite Using VGG16 Model. Proceedings of the 2024 2nd International Conference on Disruptive Technologies (ICDT), Greater Noida, India."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/11\/1159\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T05:24:27Z","timestamp":1763443467000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/11\/1159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":44,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["e27111159"],"URL":"https:\/\/doi.org\/10.3390\/e27111159","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2025,11,14]]}}}