TransNeXt-Small (IN-1K pretrain, DINO 1x)

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 minival
box AP· 2023-11-28
56.6
best: 66 (PE_spatial (DETA))
TransNeXt: Robust Foveal Visual Perception for Vision Transformers arXiv:2311.17132
2D ClassificationonCOCO minival
box AP· 2023-11-28
56.6
best: 66 (PE_spatial (DETA))
TransNeXt: Robust Foveal Visual Perception for Vision Transformers arXiv:2311.17132
2D Object DetectiononCOCO minival
box AP· 2023-11-28
56.6
best: 66 (PE_spatial (DETA))
TransNeXt: Robust Foveal Visual Perception for Vision Transformers arXiv:2311.17132
16konCOCO minival
box AP· 2023-11-28
56.6
best: 66 (PE_spatial (DETA))
TransNeXt: Robust Foveal Visual Perception for Vision Transformers arXiv:2311.17132

Computer Vision1 result

Object DetectiononCOCO minival
box AP· 2023-11-28
56.6
best: 66 (PE_spatial (DETA))
TransNeXt: Robust Foveal Visual Perception for Vision Transformers arXiv:2311.17132