Importance of negative sampling in weak label learning
Published in ICASSP 2024 - IEEE International Conference on Acoustics, Speech and Signal Processing, 2024
Weak label learning involves training models when only presence or absence of classes is known at the bag level, without precise temporal or spatial boundaries. This paper analyzes the importance of negative sampling strategies in weak label learning. We show that careful selection of negative examples significantly impacts model performance and propose principled approaches for constructing effective negative samples. Our experiments demonstrate substantial improvements on audio event detection benchmarks.
Recommended citation: @inproceedings{shah2024importance, title={Importance of Negative Sampling in Weak Label Learning}, author={Shah, Ankit and Tang, Fuyu and Ye, Zelin and Singh, Rita and Raj, Bhiksha}, booktitle={ICASSP 2024 - IEEE International Conference on Acoustics, Speech and Signal Processing}, pages={7530--7534}, year={2024}, organization={IEEE} }
Download Paper