Using misclassified training samples to improve classification

Citations Over Time

Abstract

This paper proposes an improved classification strategy using misclassified training samples. It is shown that a subset of the misclassified training set forms isolated pockets. In the proposed approach, apart from providing the parameters derived out of the training samples to a classifier, the location of these misclassified pockets is also provided. The proposed strategy overcomes any weakness a given classifier may have by changing the classification decision for a given test sample based on the location of the test sample with respect to the misclassified pockets. Three diversely different classifiers and a simple composite classifier are used to test the strategy. The proposed strategy is implemented on both simulated and real data and it is shown that a reduced error rate can be obtained when this strategy is used.

Related Papers

• → Classifier Training from a Generative Model(2019)10 cited
• Synthetic Infrared Data For Target Identification Training and Testing(2002)
• → Towards a domain-independent ASR-confidence classifier(2012)
• → Using Psuedolabels for training Sentiment Classifiers makes the model generalize better across datasets(2021)
• → Using Psuedolabels for training Sentiment Classifiers makes the model\n generalize better across datasets(2021)