DeepAI AI Chat
Log In Sign Up

Shape Adaptor: A Learnable Resizing Module

by   Shikun Liu, et al.

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:


page 1

page 2

page 3

page 4


Efficient semantic image segmentation with superpixel pooling

In this work, we evaluate the use of superpixel pooling layers in deep n...

Representation-Agnostic Shape Fields

3D shape analysis has been widely explored in the era of deep learning. ...

Dilated convolution with learnable spacings

Dilated convolution is basically a convolution with a wider kernel creat...

Image Inpainting with Learnable Bidirectional Attention Maps

Most convolutional network (CNN)-based inpainting methods adopt standard...

Partial Network Cloning

In this paper, we study a novel task that enables partial knowledge tran...

CapsProm: A Capsule Network For Promoter Prediction

Locating the promoter region in DNA sequences is of paramount importance...

Auto-tuning of Deep Neural Networks by Conflicting Layer Removal

Designing neural network architectures is a challenging task and knowing...

Code Repositories


The implementation of "Shape Adaptor: A Learnable Resizing Module" [ECCV 2020].

view repo