Poster
in
Workshop: Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators
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 out of 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. We evaluate our approach on three common weakly-supervised learning paradigms and observe that our proposed approach achieves state-of-the-art or highly competitive results across all three of the paradigms.
Chat is not available.