Deep Domain Confusion: Maximizing for Domain Invariance
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 3D Human Pose Estimation | MPI-INF-3DHP (test) | -- | 559 | |
| 3D Human Pose Estimation | 3DPW (test) | PA-MPJPE75.3 | 505 | |
| Image Classification | Office-31 | Average Accuracy86.9 | 261 | |
| Domain Adaptation | Office-31 unsupervised adaptation standard | Accuracy (A to W)75.8 | 162 | |
| Domain Adaptation | Office-31 | Accuracy (A -> W)61 | 156 | |
| Domain Adaptation | OFFICE | Average Accuracy78.3 | 96 | |
| Image Classification | Office-31 (test) | Avg Accuracy70.7 | 93 | |
| Unsupervised Domain Adaptation | Office-31 | A->W Accuracy75.6 | 83 | |
| Image Classification | Office-10 + Caltech-10 | Average Accuracy88.2 | 77 | |
| Image Classification | SVHN to MNIST (test) | Accuracy71.1 | 66 |