Sorry, you need to enable JavaScript to visit this website.

Importance of Negative Sampling in Weak Label Learning

DOI:
10.60864/05b2-0j30
Citation Author(s):
Ankit Shah, Fuyu Tang, Zelin Ye, Rita Singh, Bhiksha Raj
Submitted by:
Ankit Shah
Last updated:
6 June 2024 - 10:54am
Document Type:
Poster
Document Year:
2024
Presenters:
Ankit Shah
Paper Code:
MLSP-P22.5
 

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.

up
0 users have voted: