Unsupervised Domain Adaptation using Graph Transduction Games
This work addresses domain adaptation for object recognition, offering a principled method with theoretical guarantees, though it appears incremental as it builds on existing game-theoretic frameworks.
The paper tackles unsupervised domain adaptation by proposing a game-theoretic approach using graph transduction games, which achieves consistent labeling with guaranteed convergence to a Nash equilibrium and demonstrates performance on object recognition benchmarks.
Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a related source domain. In this paper, we propose to cast this problem in a game-theoretic setting as a non-cooperative game and introduce a fully automatized iterative algorithm for UDA based on graph transduction games (GTG). The main advantages of this approach are its principled foundation, guaranteed termination of the iterative algorithms to a Nash equilibrium (which corresponds to a consistent labeling condition) and soft labels quantifying the uncertainty of the label assignment process. We also investigate the beneficial effect of using pseudo-labels from linear classifiers to initialize the iterative process. The performance of the resulting methods is assessed on publicly available object recognition benchmark datasets involving both shallow and deep features. Results of experiments demonstrate the suitability of the proposed game-theoretic approach for solving UDA tasks.