A Unified Approach to Count-Based Weakly Supervised Learning
Vinay Shukla, Zhe Zeng, Kareem Ahmed, Guy Van den Broeck
Abstract
High-quality labels are often very scarce, whereas unlabeled data with inferred weak labels occurs more naturally. In many cases, these weak labels dictate the frequency of each respective class over a set of instances. In this paper, we develop a unified approach to learning from such weakly-labeled data, which we call *count-based weakly-supervised learning*. At the heart of our approach is the ability to compute the probability of exactly $k$ out of $n$ outputs being set to true. This computation is differentiable, exact, and efficient. Building upon the previous computation, we derive a *count loss* penalizing the model for deviations in its distribution from an arithmetic constraint defined over label counts.
BibTeX
@inproceedings{
shukla2023a,
title={A Unified Approach to Count-Based Weakly Supervised Learning},
author={Vinay Shukla and Zhe Zeng and Kareem Ahmed and Guy Van den Broeck},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=IyAHCbMq3a}
}