# Recurrent Spatial Transformer Networks

arXiv: https://arxiv.org/abs/1509.05329 · HTML: https://mlsanity.com/paper/1509.05329/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2015.

## Built on by (most cited first, 3 of 3)

- [Internally Rewarded Reinforcement Learning](https://mlsanity.com/paper/2302.00270/) (2023)
- [Magnifying Networks for Images with Billions of Pixels](https://mlsanity.com/paper/2112.06121/) (2021)
- [Flow Equivariant Recurrent Neural Networks](https://mlsanity.com/paper/2507.14793/) (2025)

## Abstract (arXiv)

We integrate the recently proposed spatial transformer network (SPN) [Jaderberg et. al 2015] into a recurrent neural network (RNN) to form an RNN-SPN model. We use the RNN-SPN to classify digits in cluttered MNIST sequences. The proposed model achieves a single digit error of 1.5% compared to 2.9% for a convolutional networks and 2.0% for convolutional networks with SPN layers. The SPN outputs a zoomed, rotated and skewed version of the input image. We investigate different down-sampling factors (ratio of pixel in input and output) for the SPN and show that the RNN-SPN model is able to down-sample the input images without deteriorating performance. The down-sampling in RNN-SPN can be thought of as adaptive down-sampling that minimizes the information loss in the regions of interest. We attribute the superior performance of the RNN-SPN to the fact that it can attend to a sequence of regions of interest.