Shape Adaptor: A Learnable Resizing Module
arXiv:2008.00892
Abstract
We present a novel resizing module for neural networks: shape adaptor, a drop-in enhancement built on top of traditional resizing layers, such as pooling, bilinear sampling, and strided convolution. Whilst traditional resizing layers have fixed and deterministic reshaping factors, our module allows for a learnable reshaping factor. Our implementation enables shape adaptors to be trained end-to-end without any additional supervision, through which network architectures can be optimised for each individual task, in a fully automated way. We performed experiments across seven image classification datasets, and results show that by simply using a set of our shape adaptors instead of the original resizing layers, performance increases consistently over human-designed networks, across all datasets. Additionally, we show the effectiveness of shape adaptors on two other applications: network compression and transfer learning. The source code is available at: https://github.com/lorenmt/shape-adaptor.
arXiv commentPublished at ECCV 2020
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- DARTS: Differentiable Architecture Search
- Fine-Grained Visual Classification of Aircraft
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Making Convolutional Networks Shift-Invariant Again
- Random Search and Reproducibility for Neural Architecture Search