# Resolution Switchable Networks for Runtime Efficient Image Recognition

arXiv: https://arxiv.org/abs/2007.09558 · HTML: https://mlsanity.com/paper/2007.09558/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2020.

## Built on by (most cited first, 19 of 19)

- [Dynamic Resolution Network](https://mlsanity.com/paper/2106.02898/) (2021)
- [Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion](https://mlsanity.com/paper/2108.05009/) (2021)
- [Multi-Scale Aligned Distillation for Low-Resolution Detection](https://mlsanity.com/paper/2109.06875/) (2021)
- [Bit-Mixer: Mixed-precision networks with runtime bit-width selection](https://mlsanity.com/paper/2103.17267/) (2021)
- [Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks](https://mlsanity.com/paper/2110.09195/) (2021)
- [EBJR: Energy-Based Joint Reasoning for Adaptive Inference](https://mlsanity.com/paper/2110.10343/) (2021)
- [SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision](https://mlsanity.com/paper/2207.06242/) (2022)
- [Large-to-small Image Resolution Asymmetry in Deep Metric Learning](https://mlsanity.com/paper/2210.05463/) (2022)
- [Compacting Binary Neural Networks by Sparse Kernel Selection](https://mlsanity.com/paper/2303.14470/) (2023)
- [DynaShare: Task and Instance Conditioned Parameter Sharing for Multi-Task Learning](https://mlsanity.com/paper/2305.17305/) (2023)
- [Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting](https://mlsanity.com/paper/2207.06694/) (2022)
- [Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better](https://mlsanity.com/paper/2109.12507/) (2021)
- [Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling](https://mlsanity.com/paper/2207.05249/) (2022)
- [Characterizing and Taming Resolution in Convolutional Neural Networks](https://mlsanity.com/paper/2110.14819/) (2021)
- [Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency](https://mlsanity.com/paper/2112.00954/) (2021)
- [Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.11448/) (2024)
- [Exploring Deep-to-Shallow Transformable Neural Networks for Intelligent Embedded Systems](https://mlsanity.com/paper/2512.19731/) (2025)
- [Multi-Resolution End-to-End Deep Neural Network for Optimizing Latency-Accuracy Tradeoff in Autonomous Driving](https://mlsanity.com/paper/2605.29138/) (2026)
- [On Exploring Input Resolution Scaling For Anytime LiDAR Object Detection](https://mlsanity.com/paper/2607.08391/) (2026)

## Abstract (arXiv)

We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Thus the running speed can be selected to meet various computational resource limits. Networks trained with the proposed method are named Resolution Switchable Networks (RS-Nets). The basic training framework shares network parameters for handling images which differ in resolution, yet keeps separate batch normalization layers. Though it is parameter-efficient in design, it leads to inconsistent accuracy variations at different resolutions, for which we provide a detailed analysis from the aspect of the train-test recognition discrepancy. A multi-resolution ensemble distillation is further designed, where a teacher is learnt on the fly as a weighted ensemble over resolutions. Thanks to the ensemble and knowledge distillation, RS-Nets enjoy accuracy improvements at a wide range of resolutions compared with individually trained models. Extensive experiments on the ImageNet dataset are provided, and we additionally consider quantization problems. Code and models are available at https://github.com/yikaiw/RS-Nets.