Domain Separation Networks

NeurIPS 2016 Konstantinos BousmalisGeorge TrigeorgisNathan SilbermanDilip KrishnanDumitru Erhan

The cost of large scale data collection and annotation often makes the application of machine learning algorithms to new tasks or datasets prohibitively expensive. One approach circumventing this cost is training models on synthetic data where annotations are provided automatically... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Domain Adaptation MNIST-to-MNIST-M DSN (DANN) Accuracy 83.2 # 1
Domain Adaptation SVNH-to-MNIST DSN (DANN) Accuracy 82.7 # 5
Domain Adaptation Synth Digits-to-SVHN DSN (DANN) Accuracy 91.2 # 1
Domain Adaptation Synth Objects-to-LINEMOD DSN (DANN) Classification Accuracy 100 # 1
Mean Angle Error 53.27 # 1
Domain Adaptation Synth Signs-to-GTSRB DSN (DANN) Accuracy 93.1 # 1