Instance Segmentation on ADE20K val

Metric: APL (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	APL▼	Extra Data	Paper	Date↕	Code
1	OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained)	64.3	No	OneFormer: One Transformer to Rule Universal Ima...	2022-11-10	Code
2	OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-pretrain)	59.7	Yes	OneFormer: One Transformer to Rule Universal Ima...	2022-11-10	Code
3	X-Decoder (Davit-d5, Deform, single-scale, 1280x1280)	59.6	Yes	Generalized Decoding for Pixel, Image, and Langu...	2022-12-21	Code
4	DiNAT-L (Mask2Former, single-scale)	55.5	No	Dilated Neighborhood Attention Transformer	2022-09-29	Code
5	Mask2Former (Swin-L, single-scale)	54.7	No	Masked-attention Mask Transformer for Universal ...	2021-12-02	Code
6	Mask2Former (Swin-L + FAPN)	54.6	No	Masked-attention Mask Transformer for Universal ...	2021-12-02	Code
7	Mask2Former (ResNet-50)	43.1	No	Masked-attention Mask Transformer for Universal ...	2021-12-02	Code

#1OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained)SOTA
64.3
APL· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation Code
#2OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-pretrain)
59.7
APL· Extra Data· 2022-11-10
OneFormer: One Transformer to Rule Universal Image Segmentation Code
#3X-Decoder (Davit-d5, Deform, single-scale, 1280x1280)
59.6
APL· Extra Data· 2022-12-21
Generalized Decoding for Pixel, Image, and Language Code
#4DiNAT-L (Mask2Former, single-scale)SOTA
55.5
APL· 2022-09-29
Dilated Neighborhood Attention Transformer Code
#5Mask2Former (Swin-L, single-scale)SOTA
54.7
APL· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation Code
#6Mask2Former (Swin-L + FAPN)
54.6
APL· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation Code
#7Mask2Former (ResNet-50)
43.1
APL· 2021-12-02
Masked-attention Mask Transformer for Universal Image Segmentation Code