Domain-Adversarial Training of Neural Networks

We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Domain Adaptation MNIST-to-MNIST-M DANN [ganin2016domain] Accuracy 77.4 # 3
Sentiment Analysis Multi-Domain Sentiment Dataset DANN DVD 75.40 # 5
Books 71.43 # 5
Electronics 77.67 # 4
Kitchen 80.53 # 5
Average 76.26 # 5
Unsupervised Domain Adaptation Office-Home DANN [cite:JMLR16RevGrad] Accuracy 76.8 # 1
Domain Adaptation SVNH-to-MNIST DANN [ganin2016domain] Accuracy 70.7 # 8

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Synthetic-to-Real Translation Syn2Real-C DANN Accuracy 57.4 # 5
Domain Adaptation Synth Digits-to-SVHN DANN [ganin2016domain] Accuracy 90.3 # 2

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