# Shape Adaptor: A Learnable Resizing Module

arXiv: https://arxiv.org/abs/2008.00892 · HTML: https://mlsanity.com/paper/2008.00892/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2208.05271/) (2022)
- [Pooling Revisited: Your Receptive Field is Suboptimal](https://mlsanity.com/paper/2205.15254/) (2022)
- [Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance](https://mlsanity.com/paper/2211.14487/) (2022)
- [Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture](https://mlsanity.com/paper/2306.11982/) (2023)
- [Scale-Space Hypernetworks for Efficient Biomedical Imaging](https://mlsanity.com/paper/2304.05448/) (2023)
- [Resolution Allocation with Learnable Resizing and Spectral Filter Parameterization](https://mlsanity.com/paper/2610.20274/) (2026)

## Abstract (arXiv)

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.