Comparison of Embedded Spaces for Deep Learning Classification

2024/08/03 by Scholl, Stefan · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2408.01767

Abstract

Embedded spaces are a key feature in deep learning. Good embedded spaces represent the data well to support classification and advanced techniques such as open-set recognition, few-short learning and explainability. This paper presents a compact overview of different techniques to design embedded spaces for classification. It compares different loss functions and constraints on the network parameters with respect to the achievable geometric structure of the embedded space. The techniques are demonstrated with two and three-dimensional embeddings for the MNIST, Fashion MNIST and CIFAR-10 datasets, allowing visual inspection of the embedded spaces.

Cited by

• NM-Hebb: Coupling Local Hebbian Plasticity with Metric Learning for More Accurate and Interpretable CNNs

Related

• Space Explanations of Neural Network Classification
• Dimensionality reduction and width of deep neural networks based on topological degree theory
• Hypothesis Spaces for Deep Learning
• SPACE: Structured Compression and Sharing of Representational Space for Continual Learning
• OL 'E: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for\n Deep Learning