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 4

评估指标

Mean IoU (val)

评测结果

各个模型在此基准测试上的表现结果

模型名称
Mean IoU (val)
Paper TitleRepository
COSMOS ViT-B/1617.7COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
TagAlign17.3TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
TTD (TCL)17.0TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
GroupViT (RedCaps)9.2GroupViT: Semantic Segmentation Emerges from Text Supervision
ReCo11.2ReCo: Retrieve and Co-segment for Zero-shot Transfer-
Trident26.7Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
ProxyCLIP24.2ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation
TCL17.1Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs
TTD (MaskCLIP)12.7TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
MaskCLIP9.8Extract Free Dense Labels from CLIP
CLIPpy ViT-B13.5Perceptual Grouping in Contrastive Vision-Language Models
0 of 11 row(s) selected.