Open Vocabulary Semantic Segmentation on ADE20K-847

Metric: mIoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	mIoU▼	Extra Data	Paper	Date↕	Code
1	UMG-CLIP-E/14	17.3	No	UMG-CLIP: A Unified Multi-Granularity Vision Gen...	2024-01-12	Code
2	MaskCLIP++	16.8	No	MaskCLIP++: A Mask-Based CLIP Fine-tuning Framew...	2024-12-16	Code
3	Mask-Adapter	16.2	No	Mask-Adapter: The Devil is in the Masks for Open...	2024-12-05	Code
4	CAT-Seg	16	No	CAT-Seg: Cost Aggregation for Open-Vocabulary Se...	2023-03-21	Code
5	UMG-CLIP-L/14	15.4	No	UMG-CLIP: A Unified Multi-Granularity Vision Gen...	2024-01-12	Code
6	MAFT+	15.1	No	Collaborative Vision-Text Representation Optimiz...	2024-08-01	Code
7	SILC	15	No	SILC: Improving Vision Language Pretraining with...	2023-10-20	-
8	PosSAM	14.9	No	PosSAM: Panoptic Open-vocabulary Segment Anything	2024-03-14	Code
9	FC-CLIP	14.8	No	Convolutions Die Hard: Open-Vocabulary Segmentat...	2023-08-04	Code
10	SCAN	14	No	Open-Vocabulary Segmentation with Semantic-Assis...	2023-12-07	Code
11	SED	13.9	No	SED: A Simple Encoder-Decoder for Open-Vocabular...	2023-11-27	Code
12	SAN	13.7	No	Side Adapter Network for Open-Vocabulary Semanti...	2023-02-23	Code
13	EBSeg-L	13.7	No	Open-Vocabulary Semantic Segmentation with Image...	2024-06-14	Code
14	CLIPSelf	12.4	No	CLIPSelf: Vision Transformer Distills Itself for...	2023-10-02	Code
15	MAFT-ViTL	12.1	No	Learning Mask-aware CLIP Representations for Zer...	2023-09-30	Code
16	ODISE	11.1	No	Open-Vocabulary Panoptic Segmentation with Text-...	2023-03-08	Code
17	OVSeg Swin-B	9	No	Open-Vocabulary Semantic Segmentation with Mask-...	2022-10-09	Code
18	MaskCLIP	8.2	No	Open-Vocabulary Universal Image Segmentation wit...	2022-08-18	Code
19	SimSeg	7	No	A Simple Baseline for Open-Vocabulary Semantic S...	2021-12-29	Code

#1UMG-CLIP-E/14SOTA
17.3
mIoU· 2024-01-12
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding Code
#2MaskCLIP++
16.8
mIoU· 2024-12-16
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation Code
#3Mask-Adapter
16.2
mIoU· 2024-12-05
Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation Code
#4CAT-SegSOTA
16
mIoU· 2023-03-21
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation Code
#5UMG-CLIP-L/14
15.4
mIoU· 2024-01-12
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding Code
#6MAFT+
15.1
mIoU· 2024-08-01
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation Code
#7SILC
15
mIoU· 2023-10-20
SILC: Improving Vision Language Pretraining with Self-Distillation
#8PosSAM
14.9
mIoU· 2024-03-14
PosSAM: Panoptic Open-vocabulary Segment Anything Code
#9FC-CLIP
14.8
mIoU· 2023-08-04
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP Code
#10SCAN
14
mIoU· 2023-12-07
Open-Vocabulary Segmentation with Semantic-Assisted Calibration Code
#11SED
13.9
mIoU· 2023-11-27
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation Code
#12SANSOTA
13.7
mIoU· 2023-02-23
Side Adapter Network for Open-Vocabulary Semantic Segmentation Code
#13EBSeg-L
13.7
mIoU· 2024-06-14
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing Code
#14CLIPSelf
12.4
mIoU· 2023-10-02
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction Code
#15MAFT-ViTL
12.1
mIoU· 2023-09-30
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation Code
#16ODISE
11.1
mIoU· 2023-03-08
Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models Code
#17OVSeg Swin-BSOTA
9
mIoU· 2022-10-09
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP Code
#18MaskCLIPSOTA
8.2
mIoU· 2022-08-18
Open-Vocabulary Universal Image Segmentation with MaskCLIP Code
#19SimSegSOTA
7
mIoU· 2021-12-29
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model Code