DeBiFormer-S (IN1k pretrain, Retina)

Reported on 5 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

3DonCOCO 2017
mAP· 2024-10-11
45.6
best: 56.4 (UniRepLKNet-XL++)
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention arXiv:2410.08582
2D ClassificationonCOCO 2017
mAP· 2024-10-11
45.6
best: 56.4 (UniRepLKNet-XL++)
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention arXiv:2410.08582
2D Object DetectiononCOCO 2017
mAP· 2024-10-11
45.6
best: 56.4 (UniRepLKNet-XL++)
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention arXiv:2410.08582
16konCOCO 2017
mAP· 2024-10-11
45.6
best: 56.4 (UniRepLKNet-XL++)
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention arXiv:2410.08582

Computer Vision1 result

Object DetectiononCOCO 2017
mAP· 2024-10-11
45.6
best: 56.4 (UniRepLKNet-XL++)
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention arXiv:2410.08582