.png){kind=icon}
.png){kind=icon}
Return
Optimized Hierarchical Cascaded Processing
.png){kind=icon}
PRE
AI
DOI：10.1109/JETCAS.2018.2839347.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently, there has been an increasing demand for advanced classification capabilities embedded on wearable battery constrained devices, such as smartphones or watches. Achieving such functionality with a tight power and energy budget has proven a real challenge, specifically for large-scale neural network-based applications. Previously, cascaded systems have been proposed to minimize energy consumption for such applications, either through using a single wake-up stage, or by using a linear- or tree based cascade of consecutive classifiers that allow early termination. In this paper, we expand upon these concepts by generalizing cascades to hierarchical cascaded processing, where a hierarchy of increasingly complex classifiers, each designed and trained for a specific subtask is used. This hierarchical approach significantly outperforms the wake-up based approach by up to 2 orders of magnitude in energy consumption at iso-accuracy, specifically in systems with sparse input data such as speech recognition and visual object detection. This paper presents a general design framework for such systems and illustrates how to optimize them toward minimum energy consumption. The text further proposes a roofline model for cascaded systems, derives system level trade-offs and proves the approaches validity through a visual classification case-study.
Keywords:
Hierarchical cascaded processing
hierarchical systems
cascaded systems
deep learning
object recognition
ubiquitous computing
hierarchical cascaded processing
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.8
Papers:
1.4K
Citations:
2.8K