# When Neural Networks Using Different Sensors Create Similar Features

arXiv: https://arxiv.org/abs/2111.02732 · HTML: https://mlsanity.com/paper/2111.02732/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 4 Nov 2021.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [On Linear Identifiability of Learned Representations](https://mlsanity.com/paper/2007.00810/) (2020)
- [Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasets](https://mlsanity.com/paper/1905.10854/) (2019)
- [Model Similarity Mitigates Test Set Overuse](https://mlsanity.com/paper/1905.12580/) (2019)
- [Why is the Mahalanobis Distance Effective for Anomaly Detection?](https://mlsanity.com/paper/2003.00402/) (2020)
- [Human Action Recognition Using Deep Multilevel Multimodal (M2) Fusion of Depth and Inertial Sensors](https://mlsanity.com/paper/1910.11482/) (2019)

## Abstract (arXiv)

Multimodal problems are omnipresent in the real world: autonomous driving, robotic grasping, scene understanding, etc... We draw from the well-developed analysis of similarity to provide an example of a problem where neural networks are trained from different sensors, and where the features extracted from these sensors still carry similar information. More precisely, we demonstrate that for each sensor, the linear combination of the features from the last layer that correlates the most with other sensors corresponds to the classification components of the classification layer.