# A Data and Compute Efficient Design for Limited-Resources Deep Learning

arXiv: https://arxiv.org/abs/2004.09691 · HTML: https://mlsanity.com/paper/2004.09691/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [Does equivariance matter at scale?](https://mlsanity.com/paper/2410.23179/) (2024)
- [The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry](https://mlsanity.com/paper/2211.09231/) (2022)
- [Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators](https://mlsanity.com/paper/2106.00694/) (2021)
- [Investigating how ReLU-networks encode symmetries](https://mlsanity.com/paper/2305.17017/) (2023)
- [Astroformer: More Data Might not be all you need for Classification](https://mlsanity.com/paper/2304.05350/) (2023)
- [Translational Equivariance in Kernelizable Attention](https://mlsanity.com/paper/2102.07680/) (2021)
- [Exploiting Learned Symmetries in Group Equivariant Convolutions](https://mlsanity.com/paper/2106.04914/) (2021)
- [Measuring the Impact of Rotation Equivariance on Aerial Object Detection](https://mlsanity.com/paper/2507.09896/) (2025)
- [PDE-CNNs: Axiomatic Derivations and Applications](https://mlsanity.com/paper/2403.15182/) (2024)

## Abstract (arXiv)

Thanks to their improved data efficiency, equivariant neural networks have gained increased interest in the deep learning community. They have been successfully applied in the medical domain where symmetries in the data can be effectively exploited to build more accurate and robust models. To be able to reach a much larger body of patients, mobile, on-device implementations of deep learning solutions have been developed for medical applications. However, equivariant models are commonly implemented using large and computationally expensive architectures, not suitable to run on mobile devices. In this work, we design and test an equivariant version of MobileNetV2 and further optimize it with model quantization to enable more efficient inference. We achieve close-to state of the art performance on the Patch Camelyon (PCam) medical dataset while being more computationally efficient.