HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Unsupervised Semantic Segmentation With 7

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
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.