Importance of negative sampling in weak label learning

TL;DR

This paper investigates the importance of negative sampling strategies in weak-label learning, demonstrating that selecting informative negative instances improves classification accuracy and reduces computational costs.

Contribution

It introduces and evaluates negative sampling strategies tailored for weak-label learning, addressing the open problem of negative instance selection.

Findings

Improved classification performance on CIFAR-10 and AudioSet datasets.

Reduced computational cost compared to random sampling.

Negative instance selection benefits weak-label learning.

Abstract

Weak-label learning is a challenging task that requires learning from data "bags" containing positive and negative instances, but only the bag labels are known. The pool of negative instances is usually larger than positive instances, thus making selecting the most informative negative instance critical for performance. Such a selection strategy for negative instances from each bag is an open problem that has not been well studied for weak-label learning. In this paper, we study several sampling strategies that can measure the usefulness of negative instances for weak-label learning and select them accordingly. We test our method on CIFAR-10 and AudioSet datasets and show that it improves the weak-label classification performance and reduces the computational cost compared to random sampling methods. Our work reveals that negative instances are not all equally irrelevant, and selecting them wisely can benefit weak-label learning.