mlsanityData to 7 Oct 2026

Characterizing and Taming Resolution in Convolutional Neural Networks

arXiv 2110.14819 ↗First posted 28 Oct 2021cs.CV cs.LGcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 41 references that are in the map. First posted on arXiv 28 Oct 2021.

Builds on

25 of 41 references.

References · 25

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  7. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
  8. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  9. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  10. 2019A Study of BFLOAT16 for Deep Learning Trainingcited by 227
  11. 2019Fixing the train-test resolution discrepancycited by 209
  12. 2020Ansor: Generating High-Performance Tensor Programs for Deep Learningcited by 199
13 more
  1. 2018Learning to Optimize Tensor Programscited by 138
  2. 2019Scale-Equivariant Steerable Networkscited by 110
  3. 2018TVM: An Automated End-to-End Optimizing Compiler for Deep Learningcited by 62
  4. 2020Analyzing and Mitigating Data Stalls in DNN Trainingcited by 35
  5. 2014Locally Scale-Invariant Convolutional Neural Networkscited by 34
  6. 2020Resolution Switchable Networks for Runtime Efficient Image Recognitioncited by 19
  7. 2016Fast Video Classification via Adaptive Cascading of Deep Modelscited by 17
  8. 2018EVA2: Exploiting Temporal Redundancy in Live Computer Visioncited by 13
  9. 2019Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliencycited by 12
  10. 2018Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Maskingcited by 11
  11. 2017Energy-Efficient Hybrid Stochastic-Binary Neural Networks for Near-Sensor Computingcited by 3
  12. 2019Vignette: Perceptual Compression for Video Storage and Processing Systemscited by 3
  13. 2021Accelerating SpMM Kernel with Cache-First Edge Sampling for Graph Neural Networkscited by 2

Built on by

Not cited yet.