Deep multi-class learning from label proportions

Abstract

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.

References in corpus (4)

• Learning with a Wasserstein Loss
• Wasserstein Discriminant Analysis
• Ranking via Sinkhorn Propagation
• Co-training for Demographic Classification Using Deep Learning from Label Proportions

Cited by in corpus (8)

• Differentiable Deep Clustering with Cluster Size Constraints
• Learning from Label Proportions with Consistency Regularization
• Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training
• Learning from Label Proportions: A Mutual Contamination Framework
• Learning from Multiple Corrupted Sources, with Application to Learning from Label Proportions
• Training image classifiers using Semi-Weak Label Data
• Two-stage Training for Learning from Label Proportions
• Fast learning from label proportions with small bags