Learning from Label Proportions with Prototypical Contrastive Clustering


  • Laura Elena Cué La Rosa Electrical Engineering Department, Pontifical Catholic University of Rio de Janeiro, Brazil
  • Dário Augusto Borges Oliveira Data Science in Earth Observation, Technical University of Munich (TUM), Germany




Computer Vision (CV), Machine Learning (ML)


The use of priors to avoid manual labeling for training machine learning methods has received much attention in the last few years. One of the critical subthemes in this regard is Learning from Label Proportions (LLP), where only the information about class proportions is available for training the models. While various LLP training settings verse in the literature, most approaches focus on bag-level label proportions errors, often leading to suboptimal solutions. This paper proposes a new model that jointly uses prototypical contrastive learning and bag-level cluster proportions to implement efficient LLP classification. Our proposal explicitly relaxes the equipartition constraint commonly used in prototypical contrastive learning methods and incorporates the exact cluster proportions into the optimal transport algorithm used for cluster assignments. At inference time, we compute the clusters' assignment, delivering instance-level classification. We experimented with our method on two widely used image classification benchmarks and report a new state-of-art LLP performance, achieving results close to fully supervised methods.




How to Cite

Rosa, L. E. C. L., & Oliveira, D. A. B. (2022). Learning from Label Proportions with Prototypical Contrastive Clustering. Proceedings of the AAAI Conference on Artificial Intelligence, 36(2), 2153-2161. https://doi.org/10.1609/aaai.v36i2.20112



AAAI Technical Track on Computer Vision II