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

Benchmark Model Rank Results
open-vocabulary-semantic-segmentation-on-1MaskCLIP++#3mIoU: 62.5
open-vocabulary-semantic-segmentation-on-2MaskCLIP++#3mIoU: 38.2
open-vocabulary-semantic-segmentation-on-3MaskCLIP++#2mIoU: 16.8
open-vocabulary-semantic-segmentation-on-5MaskCLIP++#4mIoU: 96.8
open-vocabulary-semantic-segmentation-on-7MaskCLIP++#2mIoU: 23.9