Skip to yearly menu bar Skip to main content


A Unified Approach to Count-Based Weakly Supervised Learning

Vinay Shukla · Zhe Zeng · Kareem Ahmed · Guy Van den Broeck

Great Hall & Hall B1+B2 (level 1) #1023
[ ]
Wed 13 Dec 8:45 a.m. PST — 10:45 a.m. PST

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.

Chat is not available.