HyperAI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
HyperAI超神经

Unsupervised Semantic Segmentation With 9

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
MaskCLIP16.4Extract Free Dense Labels from CLIP
TCL22.4Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs
TTD (MaskCLIP)19.4TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
COSMOS ViT-B/1623.2COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
TagAlign25.3TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
ReCo14.8ReCo: Retrieve and Co-segment for Zero-shot Transfer-
Trident28.6Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
TTD (TCL)23.7TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
ProxyCLIP26.8ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation
GroupViT11.1GroupViT: Semantic Segmentation Emerges from Text Supervision
0 of 10 row(s) selected.