HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Unsupervised Semantic Segmentation With 4

평가 지표

Mean IoU (val)

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Mean IoU (val)	Paper Title	Repository
COSMOS ViT-B/16	17.7	COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training	-
TagAlign	17.3	TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification	-
TTD (TCL)	17.0	TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias	-
GroupViT (RedCaps)	9.2	GroupViT: Semantic Segmentation Emerges from Text Supervision	-
ReCo	11.2	ReCo: Retrieve and Co-segment for Zero-shot Transfer	-
Trident	26.7	Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation	-
ProxyCLIP	24.2	ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation	-
TCL	17.1	Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs	-
TTD (MaskCLIP)	12.7	TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias	-
MaskCLIP	9.8	Extract Free Dense Labels from CLIP	-
CLIPpy ViT-B	13.5	Perceptual Grouping in Contrastive Vision-Language Models	-

0 of 11 row(s) selected.

Unsupervised Semantic Segmentation With 4 | SOTA | HyperAI초신경