Deep multi-class learning from label proportions
This addresses the challenge of reducing labeling effort in machine learning, though it is incremental as it extends existing methods to a more general setting.
The paper tackles the problem of learning from label proportions in the nonlinear multiclass setting, proposing two differentiable loss functions for training deep neural networks and demonstrating accurate image classification from bags of images.
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.