张昊楠 讲师

• 学院： 电子与控制工程学院
• 性别： 男
• 出生年月：
• 职称： 讲师
• 学位： 博士
• 学历：
• 毕业院校： 西安交通大学
• 联系电话：
• 电子邮箱： haonanzhang@chd.edu.cn
• 通讯地址：
• 邮编：
• 传真：
• 办公地址：
• 教育经历：

张昊楠，男，长安大学电子与控制工程学院讲师。长期从事模型压缩与加速、计算机视觉、自动驾驶、环境感知、VLM等领域的研究，相关成果已经发表在CVPR、ACMMM、IEEE Transactions on Pattern Analysis and Machine Intelligence、IEEE Transactions on Neural Networks and Learning Systems、IEEE Transactions on Multimedia、IEEE Transactions on Circuits and Systems for Video Technology、IEEE Transactions on Intelligent Vehicles、Machine Learning等国际顶级期刊和会议上。

担任IEEE Transactions on Image Processing、IEEE Transactions on Circuits and Systems for Video Technology、IEEE Transactions on Neural Networks and Learning Systems、ICLR、AAAI、ICML、NeurlPS、ACMMM、ICME、ICASSP等国际期刊或会议的审稿人。

模型压缩与加速、计算机视觉、自动驾驶、环境感知、VLM等。

[1] Haonan Zhang, Longjun Liu, Fei Hui, Bo Zhang, Hengmin Zhang, Zhiyuan Zha. CLEAN: Category knowledge-driven compression framework for efficient 3D object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025.

[2] Haonan Zhang, Longjun Liu, Yi Zhang, Xinyu Lei, Fei Hui, Bihan Wen. DenseKD: Dense knowledge distillation by exploiting region and sample importance[J]. IEEE Transactions on Neural Networks and Learning Systems, 2025.

[3] Haonan Zhang, Longjun Liu, Yuqi Huang, Zhao Yang, Xinyu Lei, Bihan Wen. CaKDP: Category-aware knowledge distillation and pruning framework for lightweight 3d object detection[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024: 15331-15341.

[4] Haonan Zhang, Longjun Liu, Yuqi Huang, Xinyu Lei, Lei Tong, Bihan Wen. InstKD: Towards lightweight 3D object detection with instance-aware knowledge distillation[J]. IEEE Transactions on Intelligent Vehicles, 2024.

[5] Haonan Zhang, Longjun Liu, Hengyi Zhou, Liang Si, Hongbin Sun, Nannin Zheng. FCHP: Exploring the discriminative feature and feature correlation of feature maps for hierarchical DNN pruning and compression[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(10): 6807-6820.

[6] Haonan Zhang, Longjun Liu, Bingyao Kang, Nanning Zheng. Hierarchical model compression via shape-edge representation of feature maps—an enlightenment from the primate visual system[J]. IEEE Transactions on Multimedia, 2022, 25: 6958-6970.

[7] Haonan Zhang, Longjun Liu, Hengyi Zhou, Hongbin Sun, Nanning Zheng. CMD: controllable matrix decomposition with global optimization for deep neural network compression[J]. Machine Learning, 2022, 111(3): 831-851.

[8] Haonan Zhang, Longjun Liu, Hengyi Zhou, Wenxuan Hou, Hongbin Sun, Nanning Zheng. AKECP: Adaptive knowledge extraction from feature maps for fast and efficient channel pruning[C]. Proceedings of the ACM International Conference on Multimedia (ACMMM), 2021: 648-657.

[9] Haonan Zhang, Chun Yin, Xugang Huang, Sara Dadras, Kai Chen, Soodeh Dadras, Bing Zhu. Design of hypervelocity-impact damage assessment technique based on variational Bayesian[J]. Proceedings of the IFAC World Congress, 2020, 53(2): 814-819.

[10]  Yuqi Huang, Longjun Liu, Yingke Gao,  Haonan Zhang, Haoteng Li. D2S: Towards efficient sparse 3D object detection via dense to sparse knowledge distillation[C]. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025: 1-5.

[11] Hongyi He, Longjun Liu, Haonan Zhang, Nannin Zheng.IS-DARTS: Stabilizing darts through precise measurement on candidate importance[C]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(11): 12367-12375. 

[12]  Xinyu Lei, Longjun Liu, Puhang Jia, Haoteng Li. Haonan Zhang. Low-light infrared and visible image fusion with imbalanced thermal radiation distribution[J]. IEEE Transactions on Instrumentation and Measurement, 2024.

[13] Yi Zhang, Yingke Gao, Haonan Zhang, Xinyu Lei, Longjun Liu.  Cross-layer patch alignment and intra-and-inter patch relations for knowledge distillation[C]. Proceedings of the IEEE International Conference on Image Processing (ICIP), 2023: 535-539.        

[14] Hengyi Zhou, Longjun Liu, Haonan Zhang, Nanning Zheng. Rethinking the mechanism of the pattern pruning and the circle importance hypothesis[C]. Proceedings of the ACM International Conference on Multimedia (ACMMM), 2022: 4899-4908. 

[15] Wenxuan Hou, Longjun Liu, Haonan Zhang, Hongbin Sun, Nanning Zheng. DFSNet: Dividing-fuse deep neural networks with searching strategy for distributed DNN architecture[J]. Neurocomputing, 2022, 483: 488-500.   

[16] Hengyi Zhou, Longjun Liu, Haonan Zhang, Hongyi He, Nanning Zheng. CMB: a novel structural re-parameterization block without extra training parameters[C]. Proceedings of the International Joint Conference on Neural Networks (IJCNN), 2022: 1-9.