Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation

Open paper
Benchmark Model Rank Results
audio-classification-on-vggsoundCLAP (supervised)#1Top 1 Accuracy: 75.4
audio-classification-on-vggsoundCLAP+K2C Aug. (zero-shot)#18Top 1 Accuracy: 46.2
audio-classification-on-fsd50kCLAP (supervised)#5mAP: 64.9

Rank counts only results with a code link.