MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution
Preprint
Abstract
We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime. Our method trains a cohort of sub-networks with different widths using different input resolutions to mutually learn multi-scale representations for each sub-network. It achieves consistently better ImageNet top-1 accuracy over the state-of-the-art adaptive network US-Net under different computation constraints, and outperforms the best compound scaled MobileNet in EfficientNet by 1.5%. The superiority of our method is also validated on COCO object detection and instance segmentation as well as transfer learning. Surprisingly, the training strategy of MutualNet can also boost the performance of a single network, which substantially outperforms the powerful AutoAugmentation in both efficiency (GPU search hours: 15000 vs. 0) and accuracy (ImageNet: 77.6% vs. 78.6%).Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave Convolution2019
- Universally Slimmable Networks and Improved Training Techniques2019
- Structured Pruning of Neural Networks With Budget-Aware Regularization2019
- Structured Pruning of Deep Convolutional Neural NetworksACM Journal on Emerging Technologies in Computing Systems, 2017
- Wide Residual Networks2016
- Microsoft COCO: Common Objects in Context2014