# Dynamic Resolution Network

arXiv: https://arxiv.org/abs/2106.02898 · HTML: https://mlsanity.com/paper/2106.02898/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 50 references that are in the map.
- First posted on arXiv 5 Jun 2021.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [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)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [BlockDrop: Dynamic Inference Paths in Residual Networks](https://mlsanity.com/paper/1711.08393/) (2017)
- [Data-Driven Sparse Structure Selection for Deep Neural Networks](https://mlsanity.com/paper/1707.01213/) (2017)
- [A* Sampling](https://mlsanity.com/paper/1411.0030/) (2014)
- [Convolutional Networks with Adaptive Inference Graphs](https://mlsanity.com/paper/1711.11503/) (2017)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution](https://mlsanity.com/paper/1904.05049/) (2019)
- [Distilling Knowledge from Graph Convolutional Networks](https://mlsanity.com/paper/2003.10477/) (2020)
- [CondenseNet: An Efficient DenseNet using Learned Group Convolutions](https://mlsanity.com/paper/1711.09224/) (2017)
- [Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification](https://mlsanity.com/paper/2010.05300/) (2020)
- [Provable Filter Pruning for Efficient Neural Networks](https://mlsanity.com/paper/1911.07412/) (2019)
- [SCOP: Scientific Control for Reliable Neural Network Pruning](https://mlsanity.com/paper/2010.10732/) (2020)
- [Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference](https://mlsanity.com/paper/1912.03203/) (2019)

## Built on by (most cited first, 30 of 31)

- [Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models](https://mlsanity.com/paper/2403.12966/) (2024)
- [Adaptive Rotated Convolution for Rotated Object Detection](https://mlsanity.com/paper/2303.07820/) (2023)
- [Latency-aware Spatial-wise Dynamic Networks](https://mlsanity.com/paper/2210.06223/) (2022)
- [Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences](https://mlsanity.com/paper/2310.04621/) (2023)
- [Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing](https://mlsanity.com/paper/2306.16060/) (2023)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [DynaMask: Dynamic Mask Selection for Instance Segmentation](https://mlsanity.com/paper/2303.07868/) (2023)
- [AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition](https://mlsanity.com/paper/2308.08327/) (2023)
- [Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference](https://mlsanity.com/paper/2312.10193/) (2023)
- [Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference](https://mlsanity.com/paper/2404.03085/) (2024)
- [CARES: Context-Aware Resolution Selector for VLMs](https://mlsanity.com/paper/2510.19496/) (2025)
- [Deeper Insights into the Robustness of ViTs towards Common Corruptions](https://mlsanity.com/paper/2204.12143/) (2022)
- [Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation](https://mlsanity.com/paper/2206.06575/) (2022)
- [SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision](https://mlsanity.com/paper/2207.06242/) (2022)
- [Multi-resolution Rescored ByteTrack for Video Object Detection on Ultra-low-power Embedded Systems](https://mlsanity.com/paper/2404.11488/) (2024)
- [Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware](https://mlsanity.com/paper/2607.06915/) (2026)
- [Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting](https://mlsanity.com/paper/2207.06694/) (2022)
- [Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch](https://mlsanity.com/paper/2505.23763/) (2025)
- [DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors](https://mlsanity.com/paper/2311.17098/) (2023)
- [Adaptive Depth Networks with Skippable Sub-Paths](https://mlsanity.com/paper/2312.16392/) (2023)
- [VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse](https://mlsanity.com/paper/2512.14531/) (2025)
- [Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency](https://mlsanity.com/paper/2112.00954/) (2021)
- [Learning Unified Representations for Multi-Resolution Face Recognition](https://mlsanity.com/paper/2310.09563/) (2023)
- [Mondrian: On-Device High-Performance Video Analytics with Compressive Packed Inference](https://mlsanity.com/paper/2403.07598/) (2024)
- [Dynamic Resolution Guidance for Facial Expression Recognition](https://mlsanity.com/paper/2404.06365/) (2024)
- [DPNet: Dynamic Pooling Network for Tiny Object Detection](https://mlsanity.com/paper/2505.02797/) (2025)
- [Multi-Resolution End-to-End Deep Neural Network for Optimizing Latency-Accuracy Tradeoff in Autonomous Driving](https://mlsanity.com/paper/2605.29138/) (2026)
- [EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI](https://mlsanity.com/paper/2607.06982/) (2026)
- [On Exploring Input Resolution Scaling For Anytime LiDAR Object Detection](https://mlsanity.com/paper/2607.08391/) (2026)
- [Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning](https://mlsanity.com/paper/2607.11473/) (2026)

## Abstract (arXiv)

Deep convolutional neural networks (CNNs) are often of sophisticated design with numerous learnable parameters for the accuracy reason. To alleviate the expensive costs of deploying them on mobile devices, recent works have made huge efforts for excavating redundancy in pre-defined architectures. Nevertheless, the redundancy on the input resolution of modern CNNs has not been fully investigated, i.e., the resolution of input image is fixed. In this paper, we observe that the smallest resolution for accurately predicting the given image is different using the same neural network. To this end, we propose a novel dynamic-resolution network (DRNet) in which the input resolution is determined dynamically based on each input sample. Wherein, a resolution predictor with negligible computational costs is explored and optimized jointly with the desired network. Specifically, the predictor learns the smallest resolution that can retain and even exceed the original recognition accuracy for each image. During the inference, each input image will be resized to its predicted resolution for minimizing the overall computation burden. We then conduct extensive experiments on several benchmark networks and datasets. The results show that our DRNet can be embedded in any off-the-shelf network architecture to obtain a considerable reduction in computational complexity. For instance, DR-ResNet-50 achieves similar performance with an about 34% computation reduction, while gaining 1.4% accuracy increase with 10% computation reduction compared to the original ResNet-50 on ImageNet.