Audio Classification On Audioset
المقاييس
Test mAP
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Test mAP |
|---|---|
| eat-self-supervised-pre-training-with | 0.486 |
| efficient-large-scale-audio-tagging-via | 0.483 |
| masked-modeling-duo-towards-a-universal-audio | 0.485 |
| النموذج 4 | 0.533 |
| end-to-end-audio-strikes-back-boosting | 0.405 |
| beats-audio-pre-training-with-acoustic | 0.486 |
| contrastive-audio-visual-masked-autoencoder | 0.512 |
| look-listen-and-learn | 0.249 |
| omnivec2-a-novel-transformer-based-network | 0.558 |
| psla-improving-audio-event-classification | 0.443 |
| end-to-end-audio-strikes-back-boosting | 0.426 |
| self-supervised-audio-teacher-student | 0.480 |
| contrastive-audio-visual-masked-autoencoder | 0.466 |
| dtf-at-decoupled-time-frequency-audio | 0.486 |
| audiovisual-masked-autoencoders | 0.466 |
| ast-audio-spectrogram-transformer | 0.485 |
| beats-audio-pre-training-with-acoustic | 0.506 |
| equiav-leveraging-equivariance-for-audio | 0.546 |
| self-supervised-multimodal-versatile-networks | 0.309 |
| contrastive-audio-visual-masked-autoencoder | 0.262 |
| audiovisual-masked-autoencoders | 0.518 |
| sslam-enhancing-self-supervised-models-with | 0.502 |
| m2d-clap-masked-modeling-duo-meets-clap-for | 0.485 |
| attention-bottlenecks-for-multimodal-fusion | 0.496 |
| multi-format-contrastive-learning-of-audio | 0.376 |
| dynamic-convolutional-neural-networks-as | 0.490 |
| eranns-efficient-residual-audio-neural | 0.450 |
| max-ast-combining-convolution-local-and | 0.481 |
| dass-distilled-audio-state-space-models-are | 0.472 |
| perceiver-general-perception-with-iterative | 0.449 |
| efficient-training-of-audio-transformers-with | 0.471 |
| efficient-large-scale-audio-tagging-via | 0.498 |
| uavm-a-unified-model-for-audio-visual | 0.504 |
| efficient-training-of-audio-transformers-with | 0.496 |
| conformer-based-self-supervised-learning-for | 0.411 |
| psla-improving-audio-event-classification | 0.474 |
| omnivec-learning-robust-representations-with | 0.548 |
| self-supervised-audio-teacher-student | 0.497 |
| النموذج 39 | 0.471 |
| hts-at-a-hierarchical-token-semantic-audio | 0.487 |
| masked-modeling-duo-towards-a-universal-audio | 0.479 |
| large-scale-audiovisual-learning-of-sounds | 0.462 |
| dass-distilled-audio-state-space-models-are | 0.476 |
| play-it-back-iterative-attention-for-audio | 0.477 |
| unsupervised-learning-of-semantic-audio | 0.244 |
| النموذج 46 | 0.484 |
| ast-audio-spectrogram-transformer | 0.459 |
| vatt-transformers-for-multimodal-self | 0.394 |
| panns-large-scale-pretrained-audio-neural-1 | 0.431 |
| a-sequential-self-teaching-approach-for | 0.398 |