Deep Domain Confusion: Maximizing for Domain Invariance

10 Dec 2014  ·  Eric Tzeng, Judy Hoffman, Ning Zhang, Kate Saenko, Trevor Darrell ·

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an adaptation layer and an additional domain confusion loss, to learn a representation that is both semantically meaningful and domain invariant. We additionally show that a domain confusion metric can be used for model selection to determine the dimension of an adaptation layer and the best position for the layer in the CNN architecture. Our proposed adaptation method offers empirical performance which exceeds previously published results on a standard benchmark visual domain adaptation task.

PDF Abstract


Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Domain Adaptation Office-Caltech DDC[[Tzeng et al.2014]] Average Accuracy 88.2 # 6


No methods listed for this paper. Add relevant methods here