AI Paper Atlas

Research map / Benchmarks / SYNTHIA to Cityscapes

SYNTHIA to Cityscapes leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SYNTHIA to Cityscapes. Best mIoU: 72.8 (MADAv2* (5%), TPAMI 2023).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

SYNTHIA to Cityscapes · mIoU

10 papers, each with its best reported number for its own method; higher is better.

#mIoU ↑MethodPaperTopic
172.8MADAv2* (5%)
DeepLab v3+ ResNet-101
MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation
TPAMI 2023 · Table 1
Domain adaptation and generalization
270.6RI-SAALSAAL: Sharpness-Aware Active Learning
ICML 2023 · Table 4
CNN features
368.7HRDA + CDAC
HRDA
CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation
ICCV 2023 · Table 2
Domain adaptation and generalization
462.1ADFormer (Swin-S)
Swin-S
Attention Decomposition for Cross-Domain Semantic Segmentation
ECCV 2024 · Table 6
Domain adaptation and generalization
556.7Ours+ProDA
ResNet-101
Undoing the Damage of Label Shift for Cross-Domain Semantic Segmentation
CVPR 2022 · Table 2
Domain adaptation and generalization
653.6Ours
ResNet-101
Phase Consistent Ecological Domain Adaptation
CVPR 2020 · Synthia-to-Cityscapes results
Domain adaptation and generalization
753.1Ours
DeepLab-ResNet101
Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
ECCV 2020 · Table 2
Domain adaptation and generalization
850SSF-DAN (Ours)
DeepLab-v2
SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation
ICCV 2019 · Table 2
Domain adaptation and generalization
946.7PyCDA
PSP-Net ResNet-101
Constructing Self-Motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach
ICCV 2019 · Table 2
Domain adaptation and generalization
1044PIT
ResNet-101
Cross-Domain Semantic Segmentation via Domain-Invariant Interactive Relation Transfer
CVPR 2020 · Table 2
Open-set and few-shot detection

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.