Conditional Classification: A Solution for Computational Energy Reduction




Mirzaeian, Ali
Manoj P D, Sai
Vakil, Ashkan
Homayoun, Houman
Sasan, Avesta

Journal Title

Journal ISSN

Volume Title



Deep 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.



Neural networks, Convolutional neural network, Hierarchical clustering


Ali Mirzaeian, Sai Manoj, Ashkan Vakil, Houman Homayoun, Avesta Sasan. Conditional Classification: A Solution for Computational Energy Reduction. California, ISQED 2021.