scholarly journals Unpaired Deep Cross-Modality Synthesis with Fast Training

Author(s):  
Lei Xiang ◽  
Yang Li ◽  
Weili Lin ◽  
Qian Wang ◽  
Dinggang Shen
Keyword(s):  
Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4496
Author(s):  
Vlad Pandelea ◽  
Edoardo Ragusa ◽  
Tommaso Apicella ◽  
Paolo Gastaldo ◽  
Erik Cambria

Emotion recognition, among other natural language processing tasks, has greatly benefited from the use of large transformer models. Deploying these models on resource-constrained devices, however, is a major challenge due to their computational cost. In this paper, we show that the combination of large transformers, as high-quality feature extractors, and simple hardware-friendly classifiers based on linear separators can achieve competitive performance while allowing real-time inference and fast training. Various solutions including batch and Online Sequential Learning are analyzed. Additionally, our experiments show that latency and performance can be further improved via dimensionality reduction and pre-training, respectively. The resulting system is implemented on two types of edge device, namely an edge accelerator and two smartphones.


Author(s):  
Xiaodong Yi ◽  
Ziyue Luo ◽  
Chen Meng ◽  
Mengdi Wang ◽  
Guoping Long ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document