Resolution Switchable Networks for Runtime Efficient Image Recognition

07/19/2020
by   Yikai Wang, et al.
0

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.

READ FULL TEXT
research
07/13/2020

Learning to Learn Parameterized Classification Networks for Scalable Input Images

Convolutional Neural Networks (CNNs) do not have a predictable recogniti...
research
07/14/2022

Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting

End-to-end text spotting has attached great attention recently due to it...
research
03/12/2019

Universally Slimmable Networks and Improved Training Techniques

Slimmable networks are a family of neural networks that can instantly ad...
research
12/21/2018

Slimmable Neural Networks

We present a simple and general method to train a single neural network ...
research
06/12/2018

Knowledge Distillation by On-the-Fly Native Ensemble

Knowledge distillation is effective to train small and generalisable net...
research
12/01/2022

ResFormer: Scaling ViTs with Multi-Resolution Training

Vision Transformers (ViTs) have achieved overwhelming success, yet they ...
research
09/20/2020

Scale-Localized Abstract Reasoning

We consider the abstract relational reasoning task, which is commonly us...

Please sign up or login with your details

Forgot password? Click here to reset