关注
Jiefeng Peng
Jiefeng Peng
Dark Matter AI Inc.
在 dm-ai.cn 的电子邮件经过验证
标题
引用次数
引用次数
年份
Block-wisely supervised neural architecture search with knowledge distillation
C Li, J Peng, L Yuan, G Wang, X Liang, L Lin, X Chang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
1262020
Bossnas: Exploring hybrid cnn-transformers with block-wisely self-supervised neural architecture search
C Li, T Tang, G Wang, J Peng, B Wang, X Liang, X Chang
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
502021
Attentive crowd flow machines
L Liu, R Zhang, J Peng, G Li, B Du, L Lin
Proceedings of the 26th ACM international conference on Multimedia, 1553-1561, 2018
482018
Kalman normalization: Normalizing internal representations across network layers
G Wang, J Peng, P Luo, X Wang, L Lin
Advances in neural information processing systems, 21-31, 2018
262018
Batch kalman normalization: Towards training deep neural networks with micro-batches
G Wang, J Peng, P Luo, X Wang, L Lin
arXiv preprint arXiv:1802.03133, 2018
172018
Learning deep representations for semantic image parsing: a comprehensive overview
L Huang, J Peng, R Zhang, G Li, L Lin
Frontiers of Computer Science 12 (5), 840-857, 2018
92018
EfficientBERT: progressively searching multilayer perceptron via warm-up knowledge distillation
C Dong, G Wang, H Xu, J Peng, X Ren, X Liang
arXiv preprint arXiv:2109.07222, 2021
52021
Pi-NAS: Improving neural architecture search by reducing supernet training consistency shift
J Peng, J Zhang, C Li, G Wang, X Liang, L Lin
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
42021
The Semantic Knowledge Embedded Deep Representation Learning and Its Applications on Visual Understanding
R Zhang, J Peng, W Yang, L Liang
J. Comput. Res. Dev 54, 1251-1266, 2017
22017
Unifying Dynamic Optimizer Search and Network Architecture Search
B Yang, X Liang, J Zhong, J Peng, G Wang, L Lin
2021 IEEE International Conference on Multimedia and Expo (ICME), 1-6, 2021
2021
系统目前无法执行此操作,请稍后再试。
文章 1–10