Open Vocabulary Semantic Segmentation On 2

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	mIoU	Paper Title	Repository
TTD (MaskCLIP)	12.7	TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
MAFT-ViTL	32.0	Learning Mask-aware CLIP Representations for Zero-Shot Segmentation	-
FC-CLIP	34.1	Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
MAFT+	36.1	Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation
CAT-Seg	37.9	CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
OVSeg + OpenDAS	35.8	OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation	-
SimSeg	20.5	A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model
SCAN	33.5	Open-Vocabulary Segmentation with Semantic-Assisted Calibration
Mask-Adapter	38.2	Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation	-
MaskCLIP	23.7	Open-Vocabulary Universal Image Segmentation with MaskCLIP
POMP	20.7	-	-
EBSeg-L	32.8	Open-Vocabulary Semantic Segmentation with Image Embedding Balancing
TTD (TCL)	17.0	TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
ODISE	29.9	Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
PACL	31.4	Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning
SILC	37.7	SILC: Improving Vision Language Pretraining with Self-Distillation	-
OVSeg Swin-B	29.6	Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP
LaVG	15.8	In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation
MaskCLIP++	38.2	MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation
CLIPSelf	34.5	CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction	-

0 of 21 row(s) selected.