Open Vocabulary Semantic Segmentation on PASCAL Context-459

Metric: mIoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	mIoU▼	Extra Data	Paper	Date↕	Code
1	SILC	25.8	No	SILC: Improving Vision Language Pretraining with...	2023-10-20	-
2	UMG-CLIP-E/14	25.2	No	UMG-CLIP: A Unified Multi-Granularity Vision Gen...	2024-01-12	Code
3	MaskCLIP++	23.9	No	MaskCLIP++: A Mask-Based CLIP Fine-tuning Framew...	2024-12-16	Code
4	CAT-Seg	23.8	No	CAT-Seg: Cost Aggregation for Open-Vocabulary Se...	2023-03-21	Code
5	UMG-CLIP-L/14	23.2	No	UMG-CLIP: A Unified Multi-Granularity Vision Gen...	2024-01-12	Code
6	Mask-Adapter	22.7	No	Mask-Adapter: The Devil is in the Masks for Open...	2024-12-05	Code
7	SED	22.6	No	SED: A Simple Encoder-Decoder for Open-Vocabular...	2023-11-27	Code
8	MAFT+	21.6	No	Collaborative Vision-Text Representation Optimiz...	2024-08-01	Code
9	EBSeg-L	21	No	Open-Vocabulary Semantic Segmentation with Image...	2024-06-14	Code
10	FC-CLIP	18.2	No	Convolutions Die Hard: Open-Vocabulary Segmentat...	2023-08-04	Code
11	SCAN	16.7	No	Open-Vocabulary Segmentation with Semantic-Assis...	2023-12-07	Code
12	MAFT-ViTL	15.7	No	Learning Mask-aware CLIP Representations for Zer...	2023-09-30	Code
13	ODISE	14.5	No	Open-Vocabulary Panoptic Segmentation with Text-...	2023-03-08	Code
14	OVSeg Swin-B	12.4	No	Open-Vocabulary Semantic Segmentation with Mask-...	2022-10-09	Code
15	MaskCLIP	10	No	Extract Free Dense Labels from CLIP	2021-12-02	Code

#1SILCSOTA
25.8
mIoU· 2023-10-20
SILC: Improving Vision Language Pretraining with Self-Distillation
#2UMG-CLIP-E/14
25.2
mIoU· 2024-01-12
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding Code
#3MaskCLIP++
23.9
mIoU· 2024-12-16
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation Code
#4CAT-SegSOTA
23.8
mIoU· 2023-03-21
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation Code
#5UMG-CLIP-L/14
23.2
mIoU· 2024-01-12
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding Code
#6Mask-Adapter
22.7
mIoU· 2024-12-05
Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation Code
#7SED
22.6
mIoU· 2023-11-27
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation Code
#8MAFT+
21.6
mIoU· 2024-08-01
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation Code
#9EBSeg-L
21
mIoU· 2024-06-14
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing Code
#10FC-CLIP
18.2
mIoU· 2023-08-04
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP Code
#11SCAN
16.7
mIoU· 2023-12-07
Open-Vocabulary Segmentation with Semantic-Assisted Calibration Code
#12MAFT-ViTL
15.7
mIoU· 2023-09-30
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation Code
#13ODISESOTA
14.5
mIoU· 2023-03-08
Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models Code
#14OVSeg Swin-BSOTA
12.4
mIoU· 2022-10-09
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP Code
#15MaskCLIPSOTA
10
mIoU· 2021-12-02
Extract Free Dense Labels from CLIP Code