When Neural Networks Using Different Sensors Create Similar Features
Not on the map. Why?
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.
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
8 of 13 references.
References · 8
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2019Similarity of Neural Network Representations Revisitedcited by 1,755
- 2018Insights on representational similarity in neural networks with canonical correlationcited by 324
- 2020On Linear Identifiability of Learned Representationscited by 105
- 2019Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasetscited by 56
- 2019Model Similarity Mitigates Test Set Overusecited by 38
- 2020Why is the Mahalanobis Distance Effective for Anomaly Detection?cited by 28
- 2019Human Action Recognition Using Deep Multilevel Multimodal (M2) Fusion of Depth and Inertial Sensorscited by 9
Built on by
Not cited yet.