Using binarized model predictions as pseudo-labels to supervise the attention module improves weakly labeled audio tagging mAP by about 1 point absolute over the authors' no-attention baseline.
Imagenet classification with deep convolutional neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Self-supervised Attention Model for Weakly Labeled Audio Event Classification
Using binarized model predictions as pseudo-labels to supervise the attention module improves weakly labeled audio tagging mAP by about 1 point absolute over the authors' no-attention baseline.