HyperAI초신경

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

한국어

HyperAI초신경

Open Vocabulary Semantic Segmentation On 7

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	mIoU	Paper Title	Repository
MaskCLIP	10	Open-Vocabulary Universal Image Segmentation with MaskCLIP
SILC	25.8	SILC: Improving Vision Language Pretraining with Self-Distillation	-
MAFT+	21.6	Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation
MAFT-ViTL	15.7	Learning Mask-aware CLIP Representations for Zero-Shot Segmentation	-
MaskCLIP++	23.9	MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation
ODISE	14.5	Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
SED	22.6	SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation
EBSeg-L	21.0	Open-Vocabulary Semantic Segmentation with Image Embedding Balancing
Mask-Adapter	22.7	Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation	-
SCAN	16.7	Open-Vocabulary Segmentation with Semantic-Assisted Calibration
CAT-Seg	23.8	CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
FC-CLIP	18.2	Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
OVSeg Swin-B	12.4	Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP

0 of 13 row(s) selected.