Instance Segmentation on Cityscapes val

17개 결과 · ⬇ CSV · JSON

mask AP

Rank	Model	mask AP	AP50	AP	Extra Training Data	Paper	Code	Year
1	ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)	49.0	–	49.0	✓	The Missing Point in Vision Transformers for Universal Image Segmentation	sajjad-sh33/vit-p	2025
2	OneFormer (ConvNeXt-L, single-scale, Mapillary-Pretrained)	48.7	–	–	✓	OneFormer: One Transformer to Rule Universal Image Segmentation	huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1	2022
3	OpenSeeD( SwinL, single-scale)	48.5	–	–	✓	A Simple Framework for Open-Vocabulary Segmentation and Detection	microsoft/X-Decoder · idea-research/openseed	2023
4	AFF-Base (single-scale, point-based Mask2Former)	46.2	74.2	–		AutoFocusFormer: Image Segmentation off the Grid	apple/ml-autofocusformer	2023
5	OneFormer (DiNAT-L, single-scale)	45.6	–	–		OneFormer: One Transformer to Rule Universal Image Segmentation	huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1	2022
5	OneFormer (Swin-L, single-scale)	45.6	–	–		OneFormer: One Transformer to Rule Universal Image Segmentation	huggingface/transformers · SHI-Labs/OneFormer · yangyucheng000/University · +1	2022
7	DiNAT-L (single-scale, Mask2Former)	45.1	72.6	–		Dilated Neighborhood Attention Transformer	huggingface/transformers · SHI-Labs/Neighborhood-Attention-Transformer · leondgarse/keras_cv_attention_models · +4	2022
8	AFF-Small (single-scale, point-based Mask2Former)	44.0	72.8	–		AutoFocusFormer: Image Segmentation off the Grid	apple/ml-autofocusformer	2023
9	Mask2Former (Swin-L, single-scale)	43.7	–	–		Masked-attention Mask Transformer for Universal Image Segmentation	huggingface/transformers · open-mmlab/mmdetection · facebookresearch/Mask2Former · +4	2021
10	Mask2Former (Swin-B)	42	–	–		Masked-attention Mask Transformer for Universal Image Segmentation	huggingface/transformers · open-mmlab/mmdetection · facebookresearch/Mask2Former · +4	2021