CyCADA: Cycle-Consistent Adversarial Domain Adaptation

ICML 2018 Judy HoffmanEric TzengTaesung ParkJun-Yan ZhuPhillip IsolaKate SaenkoAlexei A. EfrosTrevor Darrell

Domain adaptation is critical for success in new, unseen environments. Adversarial adaptation models applied in feature spaces discover domain invariant representations, but are difficult to visualize and sometimes fail to capture pixel-level and low-level domain shifts... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels CyCADA pixel-only mIoU 34.8 # 21
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels CyCADA pixel+feat mIoU 39.5 # 18
fwIOU 72.4 # 1
Per-pixel Accuracy 82.3% # 1
Heart Segmentation Multi-Modality Whole Heart Segmentation Challenge 2017 CyCADA [[Hoffman et al.2018]] Average ASD 9.4 # 2
Average Dice 64.4 # 2
Domain Adaptation SVHN-to-MNIST CYCADA Accuracy 90.4 # 7
Unsupervised Image-To-Image Translation SVNH-to-MNIST CyCADA pixel+feat Classification Accuracy 90.4% # 1
Image-to-Image Translation SYNTHIA Fall-to-Winter CyCADA mIoU 63.3 # 1
Per-pixel Accuracy 92.1% # 1
fwIOU 85.7 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet