Neighbor Class Consistency on Unsupervised Domain Adaptation

Chang Liu, Kai Li, Yun Fu

Keywords: Unsupervised domain adaptation, Consistency regularization, Neighbor

Abstract: Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data in a target domain with labeled data from source domain available. Recent advances exploit entropy minimization and self-training to align the feature of two domains. However, as decision boundary is largely biased towards source data, class-wise pseudo labels generated by target predictions are usually very noisy, and trusting those noisy supervisions might potentially deteriorate the intrinsic target discriminative feature. Motivated by agglomerative clustering which assumes that features in the near neighborhood should be clustered together, we observe that target features from source pre-trained model are highly intrinsic discriminative and have a high probability of sharing the same label with their neighbors. Based on those observations, we propose a simple but effective method to impose Neighbor Class Consistency on target features to preserve and further strengthen the intrinsic discriminative nature of target data while regularizing the unified classifier less biased towards source data. We also introduce an entropy-based weighting scheme to help our framework more robust to the potential noisy neighbor supervision. We conduct ablation studies and extensive experiments on three UDA image classification benchmarks. Our method outperforms all existing UDA state-of-the-art.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=crc6I6R8c