Xiaomeng Ye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaomeng Ye has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- David Leake
Indiana University
3 shared publications David Crandall
Indiana University Bloomington
2 shared publications- David Crandall
Indiana University, Bloomington, USA
1 shared publication Yu Wang
Indiana University Bloomington
1 shared publication- Yu Wang
Indiana University
1 shared publication Ziwei Zhao
Indiana University 47408 Bloomington IN USA
1 shared publication
Latest Publications
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 8, 6857-6865
Run Like a Neural Network, Explain Like k-Nearest Neighbor
Deep neural networks have achieved remarkable performance across a variety of applications. However, their decision-making processes are opaque. In contrast, k-nearest neighbor (k-NN) provides interpretable predictions by relying on similar cases, but it lacks important capabilities of neural networks. The neural network k-nearest neighbor (NN-kNN) model is designed to bridge this gap, combining the benefits of neural networks with the instance-based interpretability of k-NN. However, the initial formulation of NN-kNN had limitations including scalability issues, reliance on surface-level features, and an excessive number of parameters. This paper improves NN-kNN by enhancing its scalability, parameter efficiency, ease of integration with feature extractors, and training simplicity. An evaluation of the revised architecture for image and language classification tasks illustrates its promise as a flexible and interpretable method.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 8, 6857-6865
Open AccessRun Like a Neural Network, Explain Like k-Nearest Neighbor
Deep neural networks have achieved remarkable performance across a variety of applications. However, their decision-making processes are opaque. In contrast, k-nearest neighbor (k-NN) provides interpretable predictions by relying on similar cases, but it lacks important capabilities of neural networks. The neural network k-nearest neighbor (NN-kNN) model is designed to bridge this gap, combining the benefits of neural networks with the instance-based interpretability of k-NN. However, the initial formulation of NN-kNN had limitations including scalability issues, reliance on surface-level features, and an excessive number of parameters. This paper improves NN-kNN by enhancing its scalability, parameter efficiency, ease of integration with feature extractors, and training simplicity. An evaluation of the revised architecture for image and language classification tasks illustrates its promise as a flexible and interpretable method.
- Open Access
Case-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric
This short paper presents preliminary research on the Case-Enhanced Vision Transformer (CEViT), a similarity measurement method aimed at improving the explainability of similarity assessments for image data. Initial experimental results suggest that integrating CEViT into k-Nearest Neighbor (k-NN) classification yields classification accuracy comparable to state-of-the-art computer vision models, while adding capabilities for illustrating differences between classes. CEViT explanations can be influenced by prior cases, to illustrate aspects of similarity relevant to those cases.
Open AccessCase-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric
This short paper presents preliminary research on the Case-Enhanced Vision Transformer (CEViT), a similarity measurement method aimed at improving the explainability of similarity assessments for image data. Initial experimental results suggest that integrating CEViT into k-Nearest Neighbor (k-NN) classification yields classification accuracy comparable to state-of-the-art computer vision models, while adding capabilities for illustrating differences between classes. CEViT explanations can be influenced by prior cases, to illustrate aspects of similarity relevant to those cases.
- 24 June 2024
- Published by Springer Nature
- p. 354-370
Towards Network Implementation of CBR: Case Study of a Neural Network K-NN Algorithm
- 24 June 2024
- Published by Springer Nature
- p. 354-370
Towards Network Implementation of CBR: Case Study of a Neural Network K-NN Algorithm