Domain Adaptation on GTA5 to Cityscapes

Metric: mIoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide augmentations

Sort:

#	Model↕	mIoU▼	Augmentations	Paper	Date↕	Code
1	HALO	77.8	Yes	Hyperbolic Active Learning for Semantic Segmenta...	2023-06-19	Code
2	DCF	77.7	No	Transferring to Real-World Layouts: A Depth-awar...	2023-11-21	Code
3	ILM-ASSL	76.1	Yes	Iterative Loop Method Combining Active and Semi-...	2023-01-31	Code
4	MIC	75.9	No	MIC: Masked Image Consistency for Context-Enhanc...	2022-12-02	Code
5	HRDA+PiPa	75.6	No	PiPa: Pixel- and Patch-wise Self-supervised Lear...	2022-11-14	Code
6	HRDA	73.8	No	HRDA: Context-Aware High-Resolution Domain-Adapt...	2022-04-27	Code
7	FREDOM - Transformer	73.6	No	FREDOM: Fairness Domain Adaptation Approach to S...	2023-04-04	Code
8	HALO	73.3	No	Hyperbolic Active Learning for Semantic Segmenta...	2023-06-19	Code
9	SePiCo	70.3	No	SePiCo: Semantic-Guided Pixel Contrast for Domai...	2022-04-19	Code
10	DAFormer + ProCST	69.4	Yes	ProCST: Boosting Semantic Segmentation Using Pro...	2022-04-25	Code
11	DAFormer	68.3	No	DAFormer: Improving Network Architectures and Tr...	2021-11-29	Code
12	MIC + Guidance Training	67	No	Improve Cross-domain Mixed Sampling with Guidanc...	2024-03-22	Code
13	Sepico + HIAST	64.1	No	Hard-aware Instance Adaptive Self-training for U...	2023-02-14	Code
14	TransDA-B	63.9	No	Smoothing Matters: Momentum Transformer for Doma...	2022-03-15	Code
15	DDB	62.7	No	Deliberated Domain Bridging for Domain Adaptive ...	2022-09-16	Code
16	EHTDI*	62	No	Exploring High-quality Target Domain Information...	2022-08-12	Code
17	FREDOM - DeepLabV2	61.3	No	FREDOM: Fairness Domain Adaptation Approach to S...	2023-04-04	Code
18	BiSMAP	61.2	No	Bidirectional Self-Training with Multiple Anisot...	2022-04-16	Code
19	G2L	59.7	No	-	-	-
20	FAFS	58.8	No	-	-	-
21	ProDA+CRA	58.6	No	Cross-Region Domain Adaptation for Class-level A...	2021-09-14	-
22	ProDA	57.5	No	Prototypical Pseudo Label Denoising and Target S...	2021-01-26	Code
23	ProCA	56.3	No	Prototypical Contrast Adaptation for Domain Adap...	2022-07-14	Code
24	AdaptSeg + HIAST	56.3	No	Hard-aware Instance Adaptive Self-training for U...	2023-02-14	Code
25	GtA-SFDA (DeepLabv2-ResNet101)	53.4	No	Generalize then Adapt: Source-Free Domain Adapti...	2021-08-25	Code
26	MRNet + Rectifying Label	50.3	No	Rectifying Pseudo Label Learning via Uncertainty...	2020-03-08	Code
27	CCM	49.9	No	-	-	Code
28	MRNet + Adaboost	49	No	Adaptive Boosting for Domain Adaptation: Towards...	2021-03-29	Code
29	MRNet	48.3	No	Unsupervised Scene Adaptation with Memory Regula...	2019-12-24	Code

#1HALOSOTA
77.8
mIoU· Augmentations· 2023-06-19
Hyperbolic Active Learning for Semantic Segmentation under Domain Shift Code
#2DCF
77.7
mIoU· 2023-11-21
Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation Code
#3ILM-ASSLSOTA
76.1
mIoU· Augmentations· 2023-01-31
Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation Code
#4MICSOTA
75.9
mIoU· 2022-12-02
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation Code
#5HRDA+PiPaSOTA
75.6
mIoU· 2022-11-14
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation Code
#6HRDASOTA
73.8
mIoU· 2022-04-27
HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation Code
#7FREDOM - Transformer
73.6
mIoU· 2023-04-04
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding Code
#8HALO
73.3
mIoU· 2023-06-19
Hyperbolic Active Learning for Semantic Segmentation under Domain Shift Code
#9SePiCoSOTA
70.3
mIoU· 2022-04-19
SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation Code
#10DAFormer + ProCST
69.4
mIoU· Augmentations· 2022-04-25
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer Code
#11DAFormerSOTA
68.3
mIoU· 2021-11-29
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation Code
#12MIC + Guidance Training
67
mIoU· 2024-03-22
Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation Code
#13Sepico + HIAST
64.1
mIoU· 2023-02-14
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation Code
#14TransDA-B
63.9
mIoU· 2022-03-15
Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation Code
#15DDB
62.7
mIoU· 2022-09-16
Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation Code
#16EHTDI*
62
mIoU· 2022-08-12
Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation Code
#17FREDOM - DeepLabV2
61.3
mIoU· 2023-04-04
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding Code
#18BiSMAP
61.2
mIoU· 2022-04-16
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation Code
#19G2L
59.7
mIoU
No paper
#20FAFS
58.8
mIoU
No paper
#21ProDA+CRASOTA
58.6
mIoU· 2021-09-14
Cross-Region Domain Adaptation for Class-level Alignment
#22ProDASOTA
57.5
mIoU· 2021-01-26
Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation Code
#23ProCA
56.3
mIoU· 2022-07-14
Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation Code
#24AdaptSeg + HIAST
56.3
mIoU· 2023-02-14
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation Code
#25GtA-SFDA (DeepLabv2-ResNet101)
53.4
mIoU· 2021-08-25
Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation Code
#26MRNet + Rectifying LabelSOTA
50.3
mIoU· 2020-03-08
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation Code
#27CCM
49.9
mIoU
No paperCode
#28MRNet + Adaboost
49
mIoU· 2021-03-29
Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation Code
#29MRNetSOTA
48.3
mIoU· 2019-12-24
Unsupervised Scene Adaptation with Memory Regularization in vivo Code