HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Instance Segmentation On Ade20K Val

Metrics

AP
APL
APM
APS

Results

Performance results of various models on this benchmark

Paper Title
OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained)44.264.349.923.7OneFormer: One Transformer to Rule Universal Image Segmentation
OpenSeeD42.6---A Simple Framework for Open-Vocabulary Segmentation and Detection
OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-pretrain)40.259.744.419.2OneFormer: One Transformer to Rule Universal Image Segmentation
X-Decoder (Davit-d5, Deform, single-scale, 1280x1280)38.759.643.318.9Generalized Decoding for Pixel, Image, and Language
OneFormer (DiNAT-L, single-scale)36.0---OneFormer: One Transformer to Rule Universal Image Segmentation
OneFormer (Swin-L, single-scale)35.9---OneFormer: One Transformer to Rule Universal Image Segmentation
X-Decoder (L)35.8---Generalized Decoding for Pixel, Image, and Language
DiNAT-L (Mask2Former, single-scale)35.455.539.016.3Dilated Neighborhood Attention Transformer
Mask2Former (Swin-L, single-scale)34.954.74016.3Masked-attention Mask Transformer for Universal Image Segmentation
Mask2Former (Swin-L + FAPN)33.454.637.614.6Masked-attention Mask Transformer for Universal Image Segmentation
Mask2Former (ResNet50)26.4--10.4Masked-attention Mask Transformer for Universal Image Segmentation
Mask2Former (ResNet-50)-43.128.9-Masked-attention Mask Transformer for Universal Image Segmentation
0 of 12 row(s) selected.
Instance Segmentation On Ade20K Val | SOTA | HyperAI