ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision2 results

Instance SegmentationonCityscapes val
AP· uses extra data· 2025-05-26
49
SOTA
The Missing Point in Vision Transformers for Universal Image Segmentation arXiv:2505.19795
Instance SegmentationonCityscapes val
mask AP· uses extra data· 2025-05-26
49
SOTA
The Missing Point in Vision Transformers for Universal Image Segmentation arXiv:2505.19795