{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T18:03:28Z","timestamp":1770833008183,"version":"3.50.1"},"reference-count":43,"publisher":"MDPI AG","issue":"24","license":[{"start":{"date-parts":[[2019,12,5]],"date-time":"2019-12-05T00:00:00Z","timestamp":1575504000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"This work was supported by the Deanship of Scientific Research at King Saud University through the Local Research Group Program under Project","award":["RG-1435-055"],"award-info":[{"award-number":["RG-1435-055"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The current literature of remote sensing (RS) scene classification shows that state-of-the-art results are achieved using feature extraction methods, where convolutional neural networks (CNNs) (mostly VGG16 with 138.36 M parameters) are used as feature extractors and then simple to complex handcrafted modules are added for additional feature learning and classification, thus coming back to feature engineering. In this paper, we revisit the fine-tuning approach for deeper networks (GoogLeNet and Beyond) and show that it has not been well exploited due to the negative effect of the vanishing gradient problem encountered when transferring knowledge to small datasets. The aim of this work is two-fold. Firstly, we provide best practices for fine-tuning pre-trained CNNs using the root-mean-square propagation (RMSprop) method. Secondly, we propose a simple yet effective solution for tackling the vanishing gradient problem by injecting gradients at an earlier layer of the network using an auxiliary classification loss function. Then, we fine-tune the resulting regularized network by optimizing both the primary and auxiliary losses. As for pre-trained CNNs, we consider in this work inception-based networks and EfficientNets with small weights: GoogLeNet (7 M) and EfficientNet-B0 (5.3 M) and their deeper versions Inception-v3 (23.83 M) and EfficientNet-B3 (12 M), respectively. The former networks have been used previously in the context of RS and yielded low accuracies compared to VGG16, while the latter are new state-of-the-art models. Extensive experimental results on several benchmark datasets reveal clearly that if fine-tuning is done in an appropriate way, it can settle new state-of-the-art results with low computational cost.<\/jats:p>","DOI":"10.3390\/rs11242908","type":"journal-article","created":{"date-parts":[[2019,12,5]],"date-time":"2019-12-05T11:16:23Z","timestamp":1575544583000},"page":"2908","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":85,"title":["Simple Yet Effective Fine-Tuning of Deep CNNs Using an Auxiliary Classification Loss for Remote Sensing Scene Classification"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9287-0596","authenticated-orcid":false,"given":"Yakoub","family":"Bazi","sequence":"first","affiliation":[{"name":"Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8105-9746","authenticated-orcid":false,"given":"Mohamad M.","family":"Al Rahhal","sequence":"additional","affiliation":[{"name":"Information System Department, College of Applied Computer Science, King Saud University, Riyadh 11543, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2164-043X","authenticated-orcid":false,"given":"Haikel","family":"Alhichri","sequence":"additional","affiliation":[{"name":"Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia"}]},{"given":"Naif","family":"Alajlan","sequence":"additional","affiliation":[{"name":"Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia"}]}],"member":"1968","published-online":{"date-parts":[[2019,12,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_2","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the International Conference on Machine Learning, Lille, France."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the Inception Architecture for Computer Vision. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2016). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. arXiv.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Sun, H., Li, S., Zheng, X., and Lu, X. (2019). Remote Sensing Scene Classification by Gated Bidirectional Network. IEEE Trans. Geosci. Remote Sens., 1\u201315.","DOI":"10.1109\/TGRS.2019.2931801"},{"key":"ref_6","unstructured":"Castelluccio, M., Poggi, G., Sansone, C., and Verdoliva, L. (2015). Land Use Classification in Remote Sensing Images by Convolutional Neural Networks. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2811","DOI":"10.1109\/TGRS.2017.2783902","article-title":"When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs","volume":"56","author":"Cheng","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/j.patcog.2016.07.001","article-title":"Towards better exploiting convolutional neural networks for remote sensing scene classification","volume":"61","author":"Nogueira","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1944","DOI":"10.1109\/LGRS.2019.2911855","article-title":"Remote Sensing Scene Classification Using Convolutional Features and Deep Forest Classifier","volume":"16","author":"Boualleg","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","article-title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","volume":"105","author":"Cheng","year":"2017","journal-title":"Proc. IEEE"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1109\/TGRS.2018.2864987","article-title":"Scene Classification With Recurrent Attention of VHR Remote Sensing Images","volume":"57","author":"Wang","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1932","DOI":"10.1109\/LGRS.2018.2864216","article-title":"Improving Recognition of Complex Aerial Scenes Using a Deep Weakly Supervised Learning Paradigm","volume":"15","author":"Singh","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1109\/JSTARS.2017.2761800","article-title":"Scene Classification via Triplet Networks","volume":"11","author":"Liu","year":"2018","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1109\/LGRS.2016.2616440","article-title":"Deep Filter Banks for Land-Use Scene Classification","volume":"13","author":"Wu","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1793","DOI":"10.1109\/TGRS.2015.2488681","article-title":"Scene Classification via a Gradient Boosting Random Convolutional Network Framework","volume":"54","author":"Zhang","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1109\/LGRS.2017.2731997","article-title":"Remote Sensing Image Scene Classification Using Bag of Convolutional Features","volume":"14","author":"Cheng","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2149","DOI":"10.1080\/01431161.2016.1171928","article-title":"Using convolutional features and a sparse autoencoder for land-use scene classification","volume":"37","author":"Othman","year":"2016","journal-title":"Int. J. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"704","DOI":"10.1109\/LGRS.2017.2672643","article-title":"Land-Use Classification via Extreme Learning Classifier Based on Deep Convolutional Features","volume":"14","author":"Weng","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TGRS.2017.2743243","article-title":"Learning Multiscale Deep Features for High-Resolution Satellite Image Scene Classification","volume":"56","author":"Liu","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhong, Y., Fei, F., Zhu, Q., and Qin, Q. (2018). Scene Classification Based on a Deep Random-Scale Stretched Convolutional Neural Network. Remote Sens., 10.","DOI":"10.3390\/rs10030444"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Alhichri, H., Alajlan, N., Bazi, Y., and Rabczuk, T. (2018, January 3\u20135). Multi-Scale Convolutional Neural Network for Remote Sensing Scene Classification. Proceedings of the 2018 IEEE International Conference on Electro\/Information Technology (EIT), Rochester, MI, USA.","DOI":"10.1109\/EIT.2018.8500107"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.1109\/LGRS.2018.2859024","article-title":"IORN: An Effective Remote Sensing Image Scene Classification Framework","volume":"15","author":"Wang","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7109","DOI":"10.1109\/TGRS.2018.2848473","article-title":"Scene Classification Based on Multiscale Convolutional Neural Network","volume":"56","author":"Liu","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1109\/TGRS.2017.2748120","article-title":"Diversity-Promoting Deep Structural Metric Learning for Remote Sensing Scene Classification","volume":"56","author":"Gong","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1109\/LGRS.2017.2786241","article-title":"Aerial Scene Classification via Multilevel Fusion Based on Deep Convolutional Neural Networks","volume":"15","author":"Yu","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1109\/LGRS.2017.2779469","article-title":"Scene Classification Based on Two-Stage Deep Feature Fusion","volume":"15","author":"Liu","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1109\/LGRS.2015.2499239","article-title":"Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks","volume":"13","author":"Marmanis","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"4104","DOI":"10.1109\/JSTARS.2017.2705419","article-title":"Aggregating Rich Hierarchical Features for Scene Classification in Remote Sensing Imagery","volume":"10","author":"Wang","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5653","DOI":"10.1109\/TGRS.2017.2711275","article-title":"Integrating Multilayer Features of Convolutional Neural Networks for Remote Sensing Scene Classification","volume":"55","author":"Li","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"4775","DOI":"10.1109\/TGRS.2017.2700322","article-title":"Deep Feature Fusion for VHR Remote Sensing Scene Classification","volume":"55","author":"Chaib","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_31","unstructured":"Hasanpour, S.H., Rouhani, M., Fayyaz, M., and Sabokrou, M. (2016). Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures. arXiv."},{"key":"ref_32","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 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_33","unstructured":"Tan, M., and Le, Q.V. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Yang, Y., and Newsam, S. (2010, January 2\u20135). Bag-of-visual-words and Spatial Extensions for Land-use Classification. Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, San Jose, CA, USA.","DOI":"10.1145\/1869790.1869829"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3965","DOI":"10.1109\/TGRS.2017.2685945","article-title":"AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification","volume":"55","author":"Xia","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"4441","DOI":"10.1109\/TGRS.2017.2692281","article-title":"Domain Adaptation Network for Cross-Scene Classification","volume":"55","author":"Othman","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_37","unstructured":"Othman, E., Bazi, Y., and Alhichri, H. (2019, May 05). Remote_Sensing_Dataset-Google Drive. Available online: http:\/\/bit.ly\/ksa_dataset."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1109\/T-C.1969.222599","article-title":"Experiments with the n-tuple Method of Pattern Recognition","volume":"100","author":"Ullmann","year":"1969","journal-title":"IEEE Trans. Comput."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"6899","DOI":"10.1109\/TGRS.2018.2845668","article-title":"Remote Sensing Scene Classification Using Multilayer Stacked Covariance Pooling","volume":"56","author":"He","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/s13640-018-0398-z","article-title":"Remote sensing scene classification based on rotation-invariant feature learning and joint decision making","volume":"2019","author":"Zhou","year":"2019","journal-title":"J. Image Video Proc."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/j.ijleo.2018.06.024","article-title":"Scene classification of remote sensing image based on deep network and multi-scale features fusion","volume":"171","author":"Yang","year":"2018","journal-title":"Optik"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Liang, Y., Monteiro, S.T., and Saber, E.S. (2016, January 18\u201320). Transfer learning for high resolution aerial image classification. Proceedings of the 2016 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), Washington, DC, USA.","DOI":"10.1109\/AIPR.2016.8010600"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/24\/2908\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:40:35Z","timestamp":1760190035000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/24\/2908"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,5]]},"references-count":43,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2019,12]]}},"alternative-id":["rs11242908"],"URL":"https:\/\/doi.org\/10.3390\/rs11242908","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,5]]}}}