UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition

Open paper
Benchmark Model Rank Results
image-classification-on-imagenetUniRepLKNet-XL++#64Top 1 Accuracy: 88%
image-classification-on-imagenetUniRepLKNet-L++#66Top 1 Accuracy: 87.9%
image-classification-on-imagenetUniRepLKNet-B++#93Top 1 Accuracy: 87.4%
image-classification-on-imagenetUniRepLKNet-S++#148Top 1 Accuracy: 86.4%
image-classification-on-imagenetUniRepLKNet-S#370Top 1 Accuracy: 83.9%
image-classification-on-imagenetUniRepLKNet-T#448Top 1 Accuracy: 83.2%
image-classification-on-imagenetUniRepLKNet-N#605Top 1 Accuracy: 81.6%
image-classification-on-imagenetUniRepLKNet-P#680Top 1 Accuracy: 80.2%
image-classification-on-imagenetUniRepLKNet-F#776Top 1 Accuracy: 78.6%
image-classification-on-imagenetUniRepLKNet-A#837Top 1 Accuracy: 77%
object-detection-on-coco-2017UniRepLKNet-XL++#6mAP: 56.4
object-detection-on-coco-2017UniRepLKNet-L++#7mAP: 55.8
object-detection-on-coco-2017UniRepLKNet-B++#8mAP: 54.8
object-detection-on-coco-2017UniRepLKNet-S++#9mAP: 54.3
object-detection-on-coco-2017UniRepLKNet-S#11mAP: 53
object-detection-on-coco-2017UniRepLKNet-T#13mAP: 51.7
semantic-segmentation-on-ade20kUniRepLKNet-XL#44Validation mIoU: 55.6
semantic-segmentation-on-ade20kUniRepLKNet-L++#50Validation mIoU: 55
semantic-segmentation-on-ade20kUniRepLKNet-B++#69Validation mIoU: 53.9
semantic-segmentation-on-ade20kUniRepLKNet-S++#85Validation mIoU: 52.7
semantic-segmentation-on-ade20kUniRepLKNet-S#102Validation mIoU: 51
semantic-segmentation-on-ade20kUniRepLKNet-T#135Validation mIoU: 49.1

Rank counts only results with a code link.