A Study of the Robustness of KNN Classifiers Trained Using Soft Labels

By Neamat El Gayar, Friedhelm Schwenker, Günther Palm. 2006

89 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Civil and Structural Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dapeng Oliver Wu
2. Xiyao Ma
3. Michel Verleysen
4. Benoît Frénay
5. Matthias Schonlau
6. Xiaolin Li
7. Yanlin Zhou
8. Ilia Sucholutsky

In Biomedical Engineering

1. Michel Verleysen
2. Benoît Frénay

In Civil and Structural Engineering

1. Michel Verleysen
2. Benoît Frénay

Citations in the corpus

• Distilled One-Shot Federated Learning (2020, background): “Soft labels have a long history, being proposed for model distillation by Hinton et al. [11] and for k-nearest neighbors by El Gayar et al. [5].”
• Soft-Label Dataset Distillation and Text Dataset Distillation (2019, background): “‘Soft’ labels were recently proposed as an effective way of distilling networks by feeding the output probabilities of a larger network directly to a smaller network [3], and have previously been studied in the context of different machine learning algorithms [10].”
• Classification in the Presence of Label Noise: A Survey (2014, methodology): “In this spirit, El Gayar et al. [263] propose a method that is similar to [136].”