2019/05/30 by Gabriel Dulac-Arnold, Neil Zeghidour, Dulac-Arnold, Gabriel +8 · 13 citations
Computer Science · Mathematics · #Advanced Neural Network Applications #Artificial intelligence #Artificial neural network #Benchmark (surveying) #Binary classification #Binary number #Class (philosophy) #Computer science #Contextual image classification #Data mining #Deep learning #Differentiable function #Digital Imaging for Blood Diseases #FOS: Computer and information sciences #Geography #Image (mathematics) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine learning #Mathematics #Multi-label classification #Multiclass classification #Pattern recognition (psychology) #Relevance (law) #Support vector machine #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1905.12909
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2019/05/30 · arxiv created 2019/06/26 · arxiv updated 2019/06/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
We propose a learning algorithm capable of learning from label proportions instead of direct data labels. In this scenario, our data are arranged into various bags of a certain size, and only the proportions of each label within a given bag are known. This is a common situation in cases where per-data labeling is lengthy, but a more general label is easily accessible. Several approaches have been proposed to learn in this setting with linear models in the multiclass setting, or with nonlinear models in the binary classification setting. Here we investigate the more general nonlinear multiclass setting, and compare two differentiable loss functions to train end-to-end deep neural networks from bags with label proportions. We illustrate the relevance of our methods on an image classification benchmark, and demonstrate the possibility to learn accurate image classifiers from bags of images.