# ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks

arXiv: https://arxiv.org/abs/1505.00393 · HTML: https://mlsanity.com/paper/1505.00393/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2015.

## Built on by (most cited first, 24 of 24)

- [Visual Attention Methods in Deep Learning: An In-Depth Survey](https://mlsanity.com/paper/2204.07756/) (2022)
- [TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data](https://mlsanity.com/paper/2106.03096/) (2021)
- [Position, Padding and Predictions: A Deeper Look at Position Information in CNNs](https://mlsanity.com/paper/2101.12322/) (2021)
- [Sequencer: Deep LSTM for Image Classification](https://mlsanity.com/paper/2205.01972/) (2022)
- [A Deep Neural Network Surrogate Modeling Benchmark for Temperature Field Prediction of Heat Source Layout](https://mlsanity.com/paper/2103.11177/) (2021)
- [Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection](https://mlsanity.com/paper/2103.04009/) (2021)
- [Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling](https://mlsanity.com/paper/2103.08877/) (2021)
- [An End-to-End Breast Tumour Classification Model Using Context-Based Patch Modelling- A BiLSTM Approach for Image Classification](https://mlsanity.com/paper/2106.02864/) (2021)
- [EXPERT: Public Benchmarks for Dynamic Heterogeneous Academic Graphs](https://mlsanity.com/paper/2204.07203/) (2022)
- [Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression](https://mlsanity.com/paper/2208.00919/) (2022)
- [ContinuityLearner: Geometric Continuity Feature Learning for Lane Segmentation](https://mlsanity.com/paper/2108.03507/) (2021)
- [On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Models](https://mlsanity.com/paper/2110.03054/) (2021)
- [Learning from Data with Noisy Labels Using Temporal Self-Ensemble](https://mlsanity.com/paper/2207.10354/) (2022)
- [Adversarial Attacks Assessment of Salient Object Detection via Symbolic Learning](https://mlsanity.com/paper/2309.05900/) (2023)
- [A Racing Dataset and Baseline Model for Track Detection in Autonomous Racing](https://mlsanity.com/paper/2502.14068/) (2025)
- [Heterogeneity-Oblivious Robust Federated Learning](https://mlsanity.com/paper/2508.03579/) (2025)
- [R-MelNet: Reduced Mel-Spectral Modeling for Neural TTS](https://mlsanity.com/paper/2206.15276/) (2022)
- [Comparative Analysis of State-of-the-Art Deep Learning Models for Detecting COVID-19 Lung Infection from Chest X-Ray Images](https://mlsanity.com/paper/2208.01637/) (2022)
- [DartsReNet: Exploring new RNN cells in ReNet architectures](https://mlsanity.com/paper/2304.05838/) (2023)
- [Anticipating Technical Expertise and Capability Evolution in Research Communities using Dynamic Graph Transformers](https://mlsanity.com/paper/2307.09665/) (2023)
- [Pruning Distorted Images in MNIST Handwritten Digits](https://mlsanity.com/paper/2307.14343/) (2023)
- [An Approach for Efficient Neural Architecture Search Space Definition](https://mlsanity.com/paper/2310.17669/) (2023)
- [Tackling Tuberculosis: A Comparative Dive into Machine Learning for Tuberculosis Detection](https://mlsanity.com/paper/2512.02364/) (2025)
- [Scale-Consistent State-Space Dynamics via Fractal of Stationary Transformations](https://mlsanity.com/paper/2601.19551/) (2026)

## Abstract (arXiv)

In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks. The proposed network, called ReNet, replaces the ubiquitous convolution+pooling layer of the deep convolutional neural network with four recurrent neural networks that sweep horizontally and vertically in both directions across the image. We evaluate the proposed ReNet on three widely-used benchmark datasets; MNIST, CIFAR-10 and SVHN. The result suggests that ReNet is a viable alternative to the deep convolutional neural network, and that further investigation is needed.