Open Vocabulary Semantic Segmentation On 1

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	mIoU	Paper Title	Repository
TCL	33.9	Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs
PACL	50.1	Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning
TaAlign(trained with image-text pairs)	37.6	TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
Mask-Adapter	60.4	Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation	-
FC-CLIP	58.4	Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
MAFT+	59.4	Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation
MAFT-ViTL	58.5	Learning Mask-aware CLIP Representations for Zero-Shot Segmentation	-
CAT-Seg	63.3	CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
OVSeg Swin-B	55.7	Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP
SED	60.6	SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation
LaVG	34.7	In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation
HyperSeg	64.6	HyperSeg: Towards Universal Visual Segmentation with Large Language Model
TTD (TCL)	37.4	TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
SimSeg	47.7	A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model
SILC	63.5	SILC: Improving Vision Language Pretraining with Self-Distillation	-
MaskCLIP	45.9	Open-Vocabulary Universal Image Segmentation with MaskCLIP
EBSeg-L	60.2	Open-Vocabulary Semantic Segmentation with Image Embedding Balancing
CLIP Surgery (original CLIP without any fine-tuning)	29.3	A Closer Look at the Explainability of Contrastive Language-Image Pre-training
MaskCLIP++	62.5	MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation
SCAN	59.3	Open-Vocabulary Segmentation with Semantic-Assisted Calibration

0 of 23 row(s) selected.