Semantic-Segment-Anything
Semantic-Segment-Anything copied to clipboard
evaluation results available?
Looks like, with SSA, it becomes possible to compare the performances of SAM against SOTA on popular benchmark datasets. Would you report the validation results of SSA for semantic segmentation or instance segmentation on AED20k or coco?
Thank you. We have introduced a close-set semantic segmentation pipeline and tested its performance on both Cityscapes and ADE20K in the README. We will include more benchmark results soon.