# Rethinking Recurrent Neural Networks and Other Improvements for Image Classification

arXiv: https://arxiv.org/abs/2007.15161 · HTML: https://mlsanity.com/paper/2007.15161/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 4 of 4)

- [Quantum Self-Supervised Learning](https://mlsanity.com/paper/2103.14653/) (2021)
- [Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer](https://mlsanity.com/paper/2302.09187/) (2023)
- [Signature-Graph Networks](https://mlsanity.com/paper/2110.11551/) (2021)
- [Sequential Random Network for Fine-grained Image Classification](https://mlsanity.com/paper/2103.07230/) (2021)

## Abstract (arXiv)

Over the long history of machine learning, which dates back several decades, recurrent neural networks (RNNs) have been used mainly for sequential data and time series and generally with 1D information. Even in some rare studies on 2D images, these networks are used merely to learn and generate data sequentially rather than for image recognition tasks. In this study, we propose integrating an RNN as an additional layer when designing image recognition models. We also develop end-to-end multimodel ensembles that produce expert predictions using several models. In addition, we extend the training strategy so that our model performs comparably to leading models and can even match the state-of-the-art models on several challenging datasets (e.g., SVHN (0.99), Cifar-100 (0.9027) and Cifar-10 (0.9852)). Moreover, our model sets a new record on the Surrey dataset (0.949). The source code of the methods provided in this article is available at https://github.com/leonlha/e2e-3m and http://nguyenhuuphong.me.