Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Open Vocabulary Semantic Segmentation On 3

Metrics

mIoU

Results

Performance results of various models on this benchmark

Model Name	mIoU	Paper Title	Repository
ODISE	11.1	Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
EBSeg-L	13.7	Open-Vocabulary Semantic Segmentation with Image Embedding Balancing
MaskCLIP++	16.8	MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation
CAT-Seg	16.0	CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
SAN	13.7	Side Adapter Network for Open-Vocabulary Semantic Segmentation	-
MaskCLIP	8.2	Open-Vocabulary Universal Image Segmentation with MaskCLIP
SILC	15.0	SILC: Improving Vision Language Pretraining with Self-Distillation	-
SED	13.9	SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation
SimSeg	7	A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model
FC-CLIP	14.8	Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
SCAN	14.0	Open-Vocabulary Segmentation with Semantic-Assisted Calibration
MAFT+	15.1	Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation
OVSeg Swin-B	9	Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP
MAFT-ViTL	12.1	Learning Mask-aware CLIP Representations for Zero-Shot Segmentation	-
Mask-Adapter	16.2	Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation	-
PosSAM	14.9	PosSAM: Panoptic Open-vocabulary Segment Anything
CLIPSelf	12.4	CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction	-

0 of 17 row(s) selected.