Abstract:

In this paper, we investigate performing joint dimensionality reduction and classification using a novel histogram neural network. Motivated by a popular dimensionality reduction approach, t-Distributed Stochastic Neighbor Embedding (t-SNE), our proposed method incorporates a classification loss computed on samples in a low-dimensional embedding space. We compare the learned sample embeddings against coordinates found by t-SNE in terms of classification accuracy and qualitative assessment. We also explore use of various divergence measures in the t-SNE objective. The proposed method has several advantages such as readily embedding out-of-sample points and reducing feature dimensionality while retaining class discriminability. Our results show that the proposed approach maintains and/or improves classification performance and reveals characteristics of features produced by neural networks that may be helpful for other applications.

Links:

Citation:

J. Peeples, S. Walker, C. McCurley, A. Zare, J. Keller, and W. Xu, “Divergence Regulated Encoder Network for Joint Dimensionality Reduction and Classification,” in IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022, Art no. 3511305, doi: 10.1109/LGRS.2022.3156532.

@Article{peeples2021DREN,
Title = {Divergence Regulated Encoder Network for Joint Dimensionality Reduction and Classification}, 
Author = {Joshua Peeples and Sarah Walker and Connor McCurley and Alina Zare and James Keller and Weihuang Xu},  
Journal = {IEEE Geoscience and Remote Sensing Letters (GRSL)}, 
year={2022},
volume={19},
number={},
pages={1-5},
doi={10.1109/LGRS.2022.3156532}}