# Supervised Dimensionality Reduction and Image Classification Utilizing Convolutional Autoencoders

arXiv: https://arxiv.org/abs/2208.12152 · HTML: https://mlsanity.com/paper/2208.12152/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 45 references that are in the map.
- First posted on arXiv 25 Aug 2022.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [Metrics for Multi-Class Classification: an Overview](https://mlsanity.com/paper/2008.05756/) (2020)
- [Training Neural Networks with Local Error Signals](https://mlsanity.com/paper/1901.06656/) (2019)
- [Understanding Deep Convolutional Networks](https://mlsanity.com/paper/1601.04920/) (2016)
- [SpinalNet: Deep Neural Network with Gradual Input](https://mlsanity.com/paper/2007.03347/) (2020)
- [Brain Tumor Type Classification via Capsule Networks](https://mlsanity.com/paper/1802.10200/) (2018)
- [Contrastive Cross-site Learning with Redesigned Net for COVID-19 CT Classification](https://mlsanity.com/paper/2009.07652/) (2020)
- [Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids Construction](https://mlsanity.com/paper/1901.07752/) (2019)
- [Capsule Networks for Brain Tumor Classification based on MRI Images and Course Tumor Boundaries](https://mlsanity.com/paper/1811.00597/) (2018)
- [Discriminative Recurrent Sparse Auto-Encoders](https://mlsanity.com/paper/1301.3775/) (2013)
- [Supervised dimensionality reduction by a Linear Discriminant Analysis on pre-trained CNN features](https://mlsanity.com/paper/2006.12127/) (2020)

## Abstract (arXiv)

The joint optimization of the reconstruction and classification error is a hard non convex problem, especially when a non linear mapping is utilized. In order to overcome this obstacle, a novel optimization strategy is proposed, in which a Convolutional Autoencoder for dimensionality reduction and a classifier composed by a Fully Connected Network, are combined to simultaneously produce supervised dimensionality reduction and predictions. It turned out that this methodology can also be greatly beneficial in enforcing explainability of deep learning architectures. Additionally, the resulting Latent Space, optimized for the classification task, can be utilized to improve traditional, interpretable classification algorithms. The experimental results, showed that the proposed methodology achieved competitive results against the state of the art deep learning methods, while being much more efficient in terms of parameter count. Finally, it was empirically justified that the proposed methodology introduces advanced explainability regarding, not only the data structure through the produced latent space, but also about the classification behaviour.