Domain Adaptation On Synthia To Cityscapes

Metrics

mIoU

Results

Performance results of various models on this benchmark

Model Name	mIoU	Paper Title	Repository
PyCDA (VGG-16)	35.9	Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach	-
MIC + Guidance Training	63.8	Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation	-
CD-AM (VGG-16)	40.8	Context-Aware Domain Adaptation in Semantic Segmentation	-
MIC	67.3	MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation	-
STPL	51.8	Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation	-
SAC (ResNet-101)	52.6	Self-supervised Augmentation Consistency for Adapting Semantic Segmentation	-
ProDA+CRA	56.9	Cross-Region Domain Adaptation for Class-level Alignment	-
SePiCo (DeepLabv2-ResNet-101)	58.1	SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation	-
LDR (VGG-16)	41.1	Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation	-
PIT (VGG-16)	38.1	Cross-Domain Semantic Segmentation via Domain-Invariant Interactive Relation Transfer	-
HALO	78.1	Hyperbolic Active Learning for Semantic Segmentation under Domain Shift	-
PyCDA (ResNet-101)	46.7	Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach	-
FDA (VGG-16)	40.5	FDA: Fourier Domain Adaptation for Semantic Segmentation	-
FREDOM - Transformer	67	FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding	-
BiMaL	46.2	BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation	-
FADA (ResNet-101)	45.2	Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation	-
IAST (ResNet-101)	49.8	Instance Adaptive Self-Training for Unsupervised Domain Adaptation	-
SePiCo	64.3	SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation	-
ILM-ASSL	76.6	Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation	-
DCF	69.3	Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation	-

0 of 33 row(s) selected.