# Non-discriminative data or weak model? On the relative importance of data and model resolution

arXiv: https://arxiv.org/abs/1909.03205 · HTML: https://mlsanity.com/paper/1909.03205/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2019.

## Built on by (most cited first, 12 of 12)

- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [High-Performance Large-Scale Image Recognition Without Normalization](https://mlsanity.com/paper/2102.06171/) (2021)
- [ResMLP: Feedforward networks for image classification with data-efficient training](https://mlsanity.com/paper/2105.03404/) (2021)
- [Patches Are All You Need?](https://mlsanity.com/paper/2201.09792/) (2022)
- [Rethinking Text Line Recognition Models](https://mlsanity.com/paper/2104.07787/) (2021)
- [Augmenting Convolutional networks with attention-based aggregation](https://mlsanity.com/paper/2112.13692/) (2021)
- [Foveation in the Era of Deep Learning](https://mlsanity.com/paper/2312.01450/) (2023)
- [BasisNet: Two-stage Model Synthesis for Efficient Inference](https://mlsanity.com/paper/2105.03014/) (2021)
- [MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters](https://mlsanity.com/paper/2311.04251/) (2023)
- [Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks](https://mlsanity.com/paper/2107.10963/) (2021)
- [A lightweight Transformer-based model for fish landmark detection](https://mlsanity.com/paper/2209.05777/) (2022)
- [Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding](https://mlsanity.com/paper/2409.08695/) (2024)

## Abstract (arXiv)

We explore the question of how the resolution of the input image ("input resolution") affects the performance of a neural network when compared to the resolution of the hidden layers ("internal resolution"). Adjusting these characteristics is frequently used as a hyperparameter providing a trade-off between model performance and accuracy. An intuitive interpretation is that the reduced information content in the low-resolution input causes decay in the accuracy. In this paper, we show that up to a point, the input resolution alone plays little role in the network performance, and it is the internal resolution that is the critical driver of model quality. We then build on these insights to develop novel neural network architectures that we call Isometric Neural Networks. These models maintain a fixed internal resolution throughout their entire depth. We demonstrate that they lead to high accuracy models with low activation footprint and parameter count.