Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective

Benchmark Model Rank Results
unsupervised-semantic-segmentation-with-language-image-pre-training-on-ade20kRF-CLIP–Mean IoU (val): 20.4
unsupervised-semantic-segmentation-with-language-image-pre-training-on-coco-objectRF-CLIP–mIoU: 37.9
unsupervised-semantic-segmentation-with-language-image-pre-training-on-pascal-context-59RF-CLIP–mIoU: 39.8
unsupervised-semantic-segmentation-with-language-image-pre-training-on-pascalvoc-20RF-CLIP–mIoU: 87.0