Biography
Currently, I am a second year Ph.D. student of Department of Computer Science and Technology in Nanjing University and a member of LAMDA Group, led by professor Zhi-Hua Zhou.
Before that, I received my B.Sc. degree from College of Computer Science and Technology, Jilin University in June 2015. In the same year, I was admitted to study for my Ph.D. degree in Nanjing University.
You can download my brief CV here.
Research Interest
My research interests include: Computer Vision and Deep Learning.
I am focusing on computer vision studies with resource constraints:
- Weakly supervised fine-grained object recognition and localization;
- CNN model compression and acceleration;
- Efficient visual representations.
A resource constrained scenario means a computing task must be accomplished with limited resource supply, such as computing time, storage space, etc. A generalized definition also refers to the lackness of supervision information, i.e., the weakly supervised learning.
Publications
You can also refer to my Google Scholar Profile.
Conference Papers
-
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression.
Jian-Hao Luo, Jianxin Wu, and Weiyao Lin.
IEEE International Conference on Computer Vision (ICCV’17), pages 5058-5066, 2017.
[project page]
-
In Defense of Fully Connected Layers in Visual Representation Transfer..
Chen-Lin Zhang, Jian-Hao Luo, Xiu-Shen Wei, and Jianxin Wu.
the 18th Pacific-Rim Conference on Multimedia (PCM’17), pages 807-817, 2017.
Journal Articles
-
ThiNet: Pruning CNN Filters for a Thinner Net.
Jian-Hao Luo, Hao Zhang, Hong-Yu Zhou, Chen-Wei Xie, Jianxin Wu, and Weiyao Lin.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted for publication.
[IEEE Xplore] [code] -
Resource Constrained Deep Learning: Challenges and Practices.
Jianxin Wu, Bin-Bin Gao, Xiu-Shen Wei, and Jian-Hao Luo.
SCIENTIA SINICA Informationis, 48(5):501-510, 2018. (in Chinese)
(吴建鑫, 高斌斌, 魏秀参, 罗建豪. 资源受限的深度学习：挑战与实践. 中国科学: 信息科学, 48(5): 501-510, 2018.) -
Image Categorization with Resource Constraints: Introduction, Challenges and Advances.
Jian-Hao Luo, Wang Zhou, and Jianxin Wu.
Frontiers of Computer Science (FCS). 11(1):13-26, 2017.
[springer link] -
Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval.
Xiu-Shen Wei, Jian-Hao Luo, Jianxin Wu, and Zhi-Hua Zhou.
IEEE Transactions on Image Processing (TIP).26(6):2868-2881, 2017.
[project page] [IEEE link] -
A Survey on Fine-Grained Image Categorization Using Deep Convolutional Features.
Jian-Hao Luo and Jianxin Wu.
Acta Automatica Sinica (AAS), 43(8):1306-1318, 2017. (in Chinese)
(罗建豪, 吴建鑫. 基于深度卷积特征的细粒度图像分类研究综述. 自动化学报, 43(8): 1306-1318, 2017.)
Technical Reports
-
AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference.
Jian-Hao Luo and Jianxin Wu.
arXiv preprint arXiv:1805.08941, 2018. -
Learning Effective Binary Visual Representations with Deep Networks.
Jianxin Wu and Jian-Hao Luo.
arXiv preprint arXiv:1803.03004, 2018. -
An entropy-based pruning method for CNN compression.
Jian-Hao Luo and Jianxin Wu.
arXiv preprint arXiv:1706.05791, 2017. -
Dense CNN learning with equivalent mappings.
Jianxin Wu, Chen-Wei Xie, and Jian-Hao Luo.
arXiv preprint arXiv:1605.07251, 2016.
Professional Activities
Conference Reviewer:
Journal Reviewer:
Journal of the Association for Information Science and Technology (JASIST), 2017
Teaching Assistants:
- Programming Basics. (for undergraduate students. Spring, 2016)
- Pattern Recognition. (for undergraduate and graduated students. Spring, 2017)