{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:54:54Z","timestamp":1760151294051,"version":"build-2065373602"},"reference-count":34,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T00:00:00Z","timestamp":1646352000000},"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>With the development of deep learning, researchers design deep network structures in order to extract rich high-level semantic information. Nowadays, most popular algorithms are designed based on the complexity of visible image features. However, compared with visible image features, infrared image features are more homogeneous, and the application of deep networks is prone to extracting redundant features. Therefore, it is important to prune the network layers where redundant features are extracted. Therefore, this paper proposes a pruning method for deep convolutional network based on heat map generation metrics. The \u2018network layer performance evaluation metrics\u2019 are obtained from the number of pixel activations in the heat map. The network layer with the lowest \u2018network layer performance evaluation metrics\u2019 is pruned. To address the problem that the simultaneous deletion of multiple structures may result in incorrect pruning, the Alternating training and self-pruning strategy is proposed. Using a cyclic process of pruning each model once and retraining the pruned model to reduce the incorrect pruning of network layers. The experimental results show that proposed method in this paper improved the performance of CSPDarknet, Darknet and Resnet.<\/jats:p>","DOI":"10.3390\/s22052022","type":"journal-article","created":{"date-parts":[[2022,3,6]],"date-time":"2022-03-06T20:40:02Z","timestamp":1646599202000},"page":"2022","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A Pruning Method for Deep Convolutional Network Based on Heat Map Generation Metrics"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3151-5755","authenticated-orcid":false,"given":"Wenli","family":"Zhang","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"}]},{"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"}]},{"given":"Kaizhen","family":"Chen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"}]},{"given":"Yuxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"}]},{"given":"Tingsong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"Ssd: Single shot multibox detector","volume":"Volume 9905","author":"Liu","year":"2016","journal-title":"Computer Vision\u2014ECCV 2016"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","unstructured":"Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"ref_4","unstructured":"Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollar, P. (2017, January 22\u201329). Focal Loss for Dense Object Detection. Proceedings of the 2017 IEEE International Conference on Computer Vision ICCV, Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1016\/j.asoc.2019.01.024","article-title":"Deep infrared pedestrian classification based on automatic image matting","volume":"77","author":"Liang","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"102053","DOI":"10.1016\/j.aquaeng.2020.102053","article-title":"Deep learning-based appearance features extraction for automated carp species identification","volume":"89","author":"Banan","year":"2020","journal-title":"Aquac. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1109\/LGRS.2018.2795531","article-title":"Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with DSM","volume":"15","author":"Sun","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5\u20139 October 2015, Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Gai, W., Qi, M., Ma, M., Wang, L., Yang, C., Liu, J., Bian, Y., de Melo, G., Liu, S., and Meng, X. (2020). Employing Shadows for Multi-Person Tracking Based on a Single RGB-D Camera. Sensors, 20.","DOI":"10.3390\/s20041056"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Rasoulidanesh, M., Yadav, S., Herath, S., Vaghei, Y., and Payandeh, S. (2019). Deep Attention Models for Human Tracking Using RGBD. Sensors, 19.","DOI":"10.3390\/s19040750"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1109\/TMM.2017.2751965","article-title":"Object detection and tracking under occlusion for object-level RGB-D video segmentation","volume":"20","author":"Xie","year":"2017","journal-title":"IEEE Trans. Multimed."},{"key":"ref_14","first-page":"403","article-title":"High-resolution thermal face dataset for face and expression recognition","volume":"25","author":"Kowalski","year":"2018","journal-title":"Metrol. Meas. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., and Fergus, R. (2014). Visualizing and understanding convolutional networks. Computer Vision\u2014ECCV 2016, Springer.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref_16","first-page":"1","article-title":"Discrimination-aware network pruning for deep model compression","volume":"99","author":"Liu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Chen, C.-F., Lai, J.-H., Morariu, V.I., Han, X., Gao, M., Lin, C.-Y., and Davis, L.S. (2018, January 18\u201323). Nisp: Pruning networks using neuron importance score propagation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Mallya, A., Tyree, S., Frosio, I., and Kautz, J. (2020, January 15\u201320). Importance Estimation for Neural Network Pruning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) IEEE, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Huang, Z., and Wang, N. (2018). Data-driven sparse structure selection for deep neural networks. arXiv.","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., and Sun, J. (2017, January 22\u201329). Channel pruning for accelerating very deep neural networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref_21","unstructured":"Zeng, W., Xiong, Y., and Urtasun, R. (2021). Network Automatic Pruning: Start NAP and Take a Nap. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2525","DOI":"10.1109\/TPAMI.2018.2858232","article-title":"Thinet: Pruning cnn filters for a thinner net","volume":"41","author":"Luo","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., and Zhang, C. (2017, January 22\u201329). Learning efficient convolutional networks through network slimming. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Luo, H.J., and Wu, J. (2020, January 13\u201319). Neural Network Pruning with Residual-Connections and Limited-Data. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) IEEE, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00153"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"123175","DOI":"10.1109\/ACCESS.2020.3007611","article-title":"Two-Stream RGB-D Human Detection Algorithm Based on RFB Network","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, W., Guo, X., Wang, J., Wang, N., and Chen, K. (2021). Asymmetric Adaptive Fusion in a Two-Stream Network for RGB-D Human Detection. Sensors, 21.","DOI":"10.3390\/s21030916"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, X., and Zhu, X. (2019). Vehicle Detection in the Aerial Infrared Images via an Improved Yolov3 Network. Proceedings of the 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP), Wuxi, China, 19\u201321 July 2019, IEEE.","DOI":"10.1109\/SIPROCESS.2019.8868430"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (2016, January 27\u201330). Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedntam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chattopadhay, A., Sarkar, A., Howlader, P., and Balasubramanian, V.N. (2018). Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA, 12\u201315 March 2018, IEEE.","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, Z., Du, M., Yang, F., Zhang, Z., Mardziel, P., and Hi, X. (2020, January 14\u201319). Score-CAM: Score-weighted visual explanations for convolutional neural networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"5743","DOI":"10.1109\/TIP.2016.2614135","article-title":"Learning collaborative sparse representation for grayscale-thermal tracking","volume":"25","author":"Li","year":"2016","journal-title":"IEEE Trans. Image Processing"},{"key":"ref_33","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., and Graf, H.P. (2016). Pruning Filters for Efficient ConvNets. arXiv."},{"key":"ref_34","unstructured":"Zhuang, L., Sun, M., Zhou, T., Huang, G., and Darrell, T. (2019). Rethinking the Value of Network Pruning. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/5\/2022\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:32:16Z","timestamp":1760135536000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/5\/2022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,4]]},"references-count":34,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,3]]}},"alternative-id":["s22052022"],"URL":"https:\/\/doi.org\/10.3390\/s22052022","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,3,4]]}}}