HyperAIHyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

Unsupervised Semantic Segmentation With 7

评估指标

mIoU

评测结果

各个模型在此基准测试上的表现结果

模型名称
mIoU
Paper TitleRepository
ProxyCLIP83.3ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation-
MaskCLIP74.9Extract Free Dense Labels from CLIP-
TCL83.2Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs-
GroupViT (RedCaps)79.7GroupViT: Semantic Segmentation Emerges from Text Supervision-
Trident88.7Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation-
TagAlign87.9TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification-
COSMOS ViT-B/1677.7COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training-
ReCo57.7ReCo: Retrieve and Co-segment for Zero-shot Transfer-
0 of 8 row(s) selected.
Unsupervised Semantic Segmentation With 7 | SOTA | HyperAI超神经