| Benchmark | Model | Rank | Results |
|---|---|---|---|
| audio-tagging-on-audioset | Perceiver (mel spectrogram + video - tuned) | #15 | mean average precision: 0.440 |
| audio-classification-on-audioset | Perceiver | #34 | Test mAP: 0.449 |
| 3d-point-cloud-classification-on-modelnet40 | Perceiver | #107 | Mean Accuracy: 14.3 |
| image-classification-on-imagenet | Perceiver (FF) | #893 | Top 1 Accuracy: 78%Number of params: 44.9MGFLOPs: 707.2 |
| image-classification-on-imagenet | Perceiver | #954 | Top 1 Accuracy: 76.4% |