# Designing Adaptive Neural Networks for Energy-Constrained Image Classification

arXiv: https://arxiv.org/abs/1808.01550 · HTML: https://mlsanity.com/paper/1808.01550/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2018.

## Built on by (most cited first, 18 of 18)

- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [Trustworthy AI: A Computational Perspective](https://mlsanity.com/paper/2107.06641/) (2021)
- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [A Systematic Review of Green AI](https://mlsanity.com/paper/2301.11047/) (2023)
- [Towards Green Automated Machine Learning: Status Quo and Future Directions](https://mlsanity.com/paper/2111.05850/) (2021)
- [A survey on multi-objective hyperparameter optimization algorithms for Machine Learning](https://mlsanity.com/paper/2111.13755/) (2021)
- [AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference](https://mlsanity.com/paper/2105.04104/) (2021)
- [Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks](https://mlsanity.com/paper/2104.07085/) (2021)
- [Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design](https://mlsanity.com/paper/2103.15750/) (2021)
- [Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks](https://mlsanity.com/paper/2201.02711/) (2022)
- [NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks](https://mlsanity.com/paper/2401.13330/) (2024)
- [DCT Perceptron Layer: A Transform Domain Approach for Convolution Layer](https://mlsanity.com/paper/2211.08577/) (2022)
- [MultiTASC: A Multi-Tenancy-Aware Scheduler for Cascaded DNN Inference at the Consumer Edge](https://mlsanity.com/paper/2306.12830/) (2023)
- [A Closer Look at Data Augmentation Strategies for Finetuning-Based Low/Few-Shot Object Detection](https://mlsanity.com/paper/2408.10940/) (2024)
- [Choosing to Be Green: Advancing Green AI via Dynamic Model Selection](https://mlsanity.com/paper/2509.19996/) (2025)
- [SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platforms](https://mlsanity.com/paper/2103.12896/) (2021)
- [Are You Worthy of My Trust?: A Socioethical Perspective on the Impacts of Trustworthy AI Systems on the Environment and Human Society](https://mlsanity.com/paper/2309.09450/) (2023)
- [Automated Customization of On-Thing Inference for Quality-of-Experience Enhancement](https://mlsanity.com/paper/2112.06918/) (2021)

## Abstract (arXiv)

As convolutional neural networks (CNNs) enable state-of-the-art computer vision applications, their high energy consumption has emerged as a key impediment to their deployment on embedded and mobile devices. Towards efficient image classification under hardware constraints, prior work has proposed adaptive CNNs, i.e., systems of networks with different accuracy and computation characteristics, where a selection scheme adaptively selects the network to be evaluated for each input image. While previous efforts have investigated different network selection schemes, we find that they do not necessarily result in energy savings when deployed on mobile systems. The key limitation of existing methods is that they learn only how data should be processed among the CNNs and not the network architectures, with each network being treated as a blackbox. To address this limitation, we pursue a more powerful design paradigm where the architecture settings of the CNNs are treated as hyper-parameters to be globally optimized. We cast the design of adaptive CNNs as a hyper-parameter optimization problem with respect to energy, accuracy, and communication constraints imposed by the mobile device. To efficiently solve this problem, we adapt Bayesian optimization to the properties of the design space, reaching near-optimal configurations in few tens of function evaluations. Our method reduces the energy consumed for image classification on a mobile device by up to 6x, compared to the best previously published work that uses CNNs as blackboxes. Finally, we evaluate two image classification practices, i.e., classifying all images locally versus over the cloud under energy and communication constraints.