# Reducing Inference Energy Consumption Using Dual Complementary CNNs

arXiv: https://arxiv.org/abs/2412.01039 · HTML: https://mlsanity.com/paper/2412.01039/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Builds on (most cited first, 8 of 8)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices](https://mlsanity.com/paper/2012.03257/) (2020)
- [FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge](https://mlsanity.com/paper/1904.04421/) (2019)
- [A Survey of Methods for Low-Power Deep Learning and Computer Vision](https://mlsanity.com/paper/2003.11066/) (2020)
- [Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach](https://mlsanity.com/paper/1901.10584/) (2019)
- [DNNShifter: An Efficient DNN Pruning System for Edge Computing](https://mlsanity.com/paper/2309.06973/) (2023)
- [Midgar: Detection of people through computer vision in the Internet of Things scenarios to improve the security in Smart Cities, Smart Towns, and Smart Homes](https://mlsanity.com/paper/1701.02632/) (2017)
- [A New Approach for Evaluating the Performance of Distributed Latency-Sensitive Services](https://mlsanity.com/paper/2407.00015/) (2024)

## Built on by (most cited first, 2 of 2)

- [A Brief Review for Compression and Transfer Learning Techniques in DeepFake Detection](https://mlsanity.com/paper/2504.21066/) (2025)
- [Efficient Neural Network Model Selection for Few-Class Application Datasets](https://mlsanity.com/paper/2606.19712/) (2026)

## Abstract (arXiv)

Energy efficiency of Convolutional Neural Networks (CNNs) has become an important area of research, with various strategies being developed to minimize the power consumption of these models. Previous efforts, including techniques like model pruning, quantization, and hardware optimization, have made significant strides in this direction. However, there remains a need for more effective on device AI solutions that balance energy efficiency with model performance. In this paper, we propose a novel approach to reduce the energy requirements of inference of CNNs. Our methodology employs two small Complementary CNNs that collaborate with each other by covering each other's "weaknesses" in predictions. If the confidence for a prediction of the first CNN is considered low, the second CNN is invoked with the aim of producing a higher confidence prediction. This dual-CNN setup significantly reduces energy consumption compared to using a single large deep CNN. Additionally, we propose a memory component that retains previous classifications for identical inputs, bypassing the need to re-invoke the CNNs for the same input, further saving energy. Our experiments on a Jetson Nano computer demonstrate an energy reduction of up to 85.8% achieved on modified datasets where each sample was duplicated once. These findings indicate that leveraging a complementary CNN pair along with a memory component effectively reduces inference energy while maintaining high accuracy.