Open Vocabulary Semantic Segmentation On Coco
評価指標
mIoU
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | mIoU | Paper Title | Repository |
|---|---|---|---|
| TTD (TCL) | 23.7 | TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias | - |
| CLIP Surgery (original CLIP without any fine-tuning) | 21.9 | A Closer Look at the Explainability of Contrastive Language-Image Pre-training | - |
| POMP | - | Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition | - |
| ZegFormer | - | Decoupling Zero-Shot Semantic Segmentation | - |
| TTD (MaskCLIP) | 19.4 | TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias | - |
| ZSSeg | - | A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model | - |
| LaVG | 23.2 | In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation | - |
0 of 7 row(s) selected.