Zobrazeno 1 - 10
of 101
pro vyhledávání: '"zhang, zhaoning"'
Face recognition has made significant progress in recent years due to deep convolutional neural networks (CNN). In many face recognition (FR) scenarios, face images are acquired from a sequence with huge intra-variations. These intra-variations, whic
Externí odkaz:
http://arxiv.org/abs/2106.04852
Autor:
Peng, Baoyun, Jin, Xiao, Liu, Jiaheng, Zhou, Shunfeng, Wu, Yichao, Liu, Yu, Li, Dongsheng, Zhang, Zhaoning
Most teacher-student frameworks based on knowledge distillation (KD) depend on a strong congruent constraint on instance level. However, they usually ignore the correlation between multiple instances, which is also valuable for knowledge transfer. In
Externí odkaz:
http://arxiv.org/abs/1904.01802
Real-time generic object detection on mobile platforms is a crucial but challenging computer vision task. However, previous CNN-based detectors suffer from enormous computational cost, which hinders them from real-time inference in computation-constr
Externí odkaz:
http://arxiv.org/abs/1903.11752
Modern object detectors usually suffer from low accuracy issues, as foregrounds always drown in tons of backgrounds and become hard examples during training. Compared with those proposal-based ones, real-time detectors are in far more serious trouble
Externí odkaz:
http://arxiv.org/abs/1804.04606
Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds. However, training depthwise convolution layers with GPUs is slow in current deep learning frameworks because their implementation
Externí odkaz:
http://arxiv.org/abs/1803.09926
Compact neural networks are inclined to exploit "sparsely-connected" convolutions such as depthwise convolution and group convolution for employment in mobile applications. Compared with standard "fully-connected" convolutions, these convolutions are
Externí odkaz:
http://arxiv.org/abs/1803.09127
We present Fast-Downsampling MobileNet (FD-MobileNet), an efficient and accurate network for very limited computational budgets (e.g., 10-140 MFLOPs). Our key idea is applying an aggressive downsampling strategy to MobileNet framework. In FD-MobileNe
Externí odkaz:
http://arxiv.org/abs/1802.03750
One of the major challenges in object detection is to propose detectors with highly accurate localization of objects. The online sampling of high-loss region proposals (hard examples) uses the multitask loss with equal weight settings across all loss
Externí odkaz:
http://arxiv.org/abs/1705.02233
Autor:
Tang, Yu, Li, Qiao, Yin, Lujia, Li, Dongsheng, Zhang, Yiming, Wang, Chenyu, Zhang, Xingcheng, Qiao, Linbo, Zhang, Zhaoning, Lu, Kai
Publikováno v:
ACM Transactions on Architecture & Code Optimization; Dec2024, Vol. 21 Issue 4, p1-25, 25p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.