Conditional Classification: A Solution for Computational Energy Reduction

Simple item page
dc.contributor.authorMirzaeian, Ali
dc.contributor.authorManoj P D, Sai
dc.contributor.authorVakil, Ashkan
dc.contributor.authorHomayoun, Houman
dc.contributor.authorSasan, Avesta
dc.date.accessioned2021-02-03T19:26:53Z
dc.date.available2021-02-03T19:26:53Z
dc.date.issued2021
dc.description.abstractDeep convolutional neural networks have shown high efficiency in computer visions and other applications. However, with the increase in the depth of the networks, the computational complexity is growing exponentially. In this paper, we propose a novel solution to reduce the computational complexity of convolutional neural network models used for many class image classification. Our proposed technique breaks the classification task into two steps: 1) coarse-grain classification, in which the input samples are classified among a set of hyper-classes, 2) fine-grain classification, in which the final labels are predicted among those hyper-classes detected at the first step. We illustrate that our proposed classifier can reach the level of accuracy reported by the best in class classification models with less computational complexity (Flop Count) by only activating parts of the model that are needed for the image classification.
dc.identifier.citationAli Mirzaeian, Sai Manoj, Ashkan Vakil, Houman Homayoun, Avesta Sasan. Conditional Classification: A Solution for Computational Energy Reduction. California, ISQED 2021.
dc.identifier.urihttps://hdl.handle.net/1920/11948
dc.language.isoen_US
dc.rightsAttribution-ShareAlike 3.0 United States
dc.rights.urihttps://creativecommons.org/licenses/by-sa/3.0/us/
dc.subjectNeural networks
dc.subjectConvolutional neural network
dc.subjectHierarchical clustering
dc.titleConditional Classification: A Solution for Computational Energy Reduction
dc.typeWorking Paper

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
isqed_2021_conditional_classification.pdf
Size:
682.71 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.52 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Volgenau School of Engineering Graduate Research