-
Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization
Huge computational costs brought by convolution and batch normalization ...
05/27/2021 ∙ by Yukuan Yang, et al. ∙
0
∙
share
read it
-
Training and Inference for Integer-Based Semantic Segmentation Network
Semantic segmentation has been a major topic in research and industry in...
11/30/2020 ∙ by Jiayi Yang, et al. ∙
0
∙
share
read it
-
Restoring Negative Information in Few-Shot Object Detection
Few-shot learning has recently emerged as a new challenge in the deep le...
10/22/2020 ∙ by Yukuan Yang, et al. ∙
0
∙
share
read it
-
Transfer Learning in General Lensless Imaging through Scattering Media
Recently deep neural networks (DNNs) have been successfully introduced t...
12/28/2019 ∙ by Yukuan Yang, et al. ∙
15
∙
share
read it
-
Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers
Deep neural network (DNN) quantization converting floating-point (FP) da...
09/05/2019 ∙ by Yukuan Yang, et al. ∙
0
∙
share
read it
Yukuan Yang
is this you? claim profile
0
followers
Tsinghua University
∙
The Regents of the University of California
