Classification and comparison via neural networks

Yildiz, Ilkay, Tian, Peng, Dy, Jennifer , Erdogmus, Deniz, Brown, James, Kalpathy-Cramer, Jayashree, Ostmo, Susan, Campbell, J Peter, Chiang, Michael F and Ioannidis, Stratis (2019) Classification and comparison via neural networks. Neural Networks, 118 . pp. 65-80. ISSN 0893-6080

Full content URL:

Full text not available from this repository.

Item Type:Article
Item Status:Live Archive


We consider learning from comparison labels generated as follows: given two samples in a dataset, a labeler produces a label indicating their relative order. Such comparison labels scale quadratically with the dataset size; most importantly, in practice, they often exhibit lower variance compared to class labels. We propose a new neural network architecture based on siamese networks to incorporate both class and comparison labels in the same training pipeline, using Bradley–Terry and Thurstone loss functions. Our architecture leads to a significant improvement in predicting both class and comparison labels, increasing classification AUC by as much as 35% and comparison AUC by as much as 6% on several real-life datasets. We further show that, by incorporating comparisons, training from few samples becomes possible: a deep neural network of 5.9 million parameters trained on 80 images attains a 0.92 AUC when incorporating comparisons.

Keywords:neural networks, retina, deep learning
Subjects:G Mathematical and Computer Sciences > G760 Machine Learning
G Mathematical and Computer Sciences > G730 Neural Computing
G Mathematical and Computer Sciences > G740 Computer Vision
G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
ID Code:38025
Deposited On:05 Nov 2019 10:42

Repository Staff Only: item control page