MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation

Benchmark Model Rank Results
open-vocabulary-semantic-segmentation-on-ade20k-847MaskCLIP++#3mIoU: 16.8
open-vocabulary-semantic-segmentation-on-pascal-context-459MaskCLIP++#3mIoU: 23.9
open-vocabulary-semantic-segmentation-on-pascal-context-59MaskCLIP++#4mIoU: 62.5
open-vocabulary-semantic-segmentation-on-ade20k-150MaskCLIP++#5mIoU: 38.2
open-vocabulary-semantic-segmentation-on-pascalvoc-20MaskCLIP++#5mIoU: 96.8