# Characterizing and Taming Resolution in Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2110.14819 · HTML: https://mlsanity.com/paper/2110.14819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 28 Oct 2021.

## Builds on (most cited first, 25 of 25)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [A Study of BFLOAT16 for Deep Learning Training](https://mlsanity.com/paper/1905.12322/) (2019)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [Ansor: Generating High-Performance Tensor Programs for Deep Learning](https://mlsanity.com/paper/2006.06762/) (2020)
- [Learning to Optimize Tensor Programs](https://mlsanity.com/paper/1805.08166/) (2018)
- [Scale-Equivariant Steerable Networks](https://mlsanity.com/paper/1910.11093/) (2019)
- [TVM: An Automated End-to-End Optimizing Compiler for Deep Learning](https://mlsanity.com/paper/1802.04799/) (2018)
- [Analyzing and Mitigating Data Stalls in DNN Training](https://mlsanity.com/paper/2007.06775/) (2020)
- [Locally Scale-Invariant Convolutional Neural Networks](https://mlsanity.com/paper/1412.5104/) (2014)
- [Resolution Switchable Networks for Runtime Efficient Image Recognition](https://mlsanity.com/paper/2007.09558/) (2020)
- [Fast Video Classification via Adaptive Cascading of Deep Models](https://mlsanity.com/paper/1611.06453/) (2016)
- [EVA2: Exploiting Temporal Redundancy in Live Computer Vision](https://mlsanity.com/paper/1803.06312/) (2018)
- [Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency](https://mlsanity.com/paper/1908.08986/) (2019)
- [Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking](https://mlsanity.com/paper/1806.04321/) (2018)
- [Energy-Efficient Hybrid Stochastic-Binary Neural Networks for Near-Sensor Computing](https://mlsanity.com/paper/1706.02344/) (2017)
- [Vignette: Perceptual Compression for Video Storage and Processing Systems](https://mlsanity.com/paper/1902.01372/) (2019)
- [Accelerating SpMM Kernel with Cache-First Edge Sampling for Graph Neural Networks](https://mlsanity.com/paper/2104.10716/) (2021)

## Abstract (arXiv)

Image resolution has a significant effect on the accuracy and computational, storage, and bandwidth costs of computer vision model inference. These costs are exacerbated when scaling out models to large inference serving systems and make image resolution an attractive target for optimization. However, the choice of resolution inherently introduces additional tightly coupled choices, such as image crop size, image detail, and compute kernel implementation that impact computational, storage, and bandwidth costs. Further complicating this setting, the optimal choices from the perspective of these metrics are highly dependent on the dataset and problem scenario. We characterize this tradeoff space, quantitatively studying the accuracy and efficiency tradeoff via systematic and automated tuning of image resolution, image quality and convolutional neural network operators. With the insights from this study, we propose a dynamic resolution mechanism that removes the need to statically choose a resolution ahead of time.