Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation

Benchmark Model Rank Results
unsupervised-domain-adaptation-on-cityscapes-to-oxfordcarUncertainty + Adaboost#1mIoU: 75.2
unsupervised-domain-adaptation-on-cityscapes-to-oxfordcarMRNet + Adaboost#4mIoU: 73.7
domain-adaptation-on-gta5-synscapes-to-cityscapesMRNet + Adaboost#2mIoU: 50.8
domain-adaptation-on-gtav-synscapes-to-cityscapesMRNet+Adaboost#3mIoU: 50.8
unsupervised-domain-adaptation-on-synthia-to-cityscapesUncertainty + Adaboost#16mIoU (13 classes): 57.5mIoU: 50.4
unsupervised-domain-adaptation-on-synthia-to-cityscapesMRNet + Adaboost#18mIoU (13 classes): 52.9mIoU: 45.9
semi-supervised-image-classification-on-cifar-10-4000-labelsAdaboost#19Percentage error: 6.05±0.12
unsupervised-domain-adaptation-on-gtav-to-cityscapes-labelsUncertainty + Adaboost#20mIoU: 50.9
synthetic-to-real-translation-on-synthia-to-cityscapesUncertainty + Adaboost (ResNet-101)#23MIoU (16 classes): 50.4MIoU (13 classes): 57.5
synthetic-to-real-translation-on-synthia-to-cityscapesMRNet + Adaboost (ResNet-101)#29MIoU (16 classes): 45.9MIoU (13 classes): 52.9
domain-adaptation-on-gta5-to-cityscapesMRNet + Adaboost#29mIoU: 49.0
synthetic-to-real-translation-on-gtav-to-cityscapes-labelsUncertainty + Adaboost#43mIoU: 50.9