Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer

Abstract

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods require access to the source data, and thus are not applicable when the data are confidential and not shareable due to privacy concerns. This paper aims to tackle a realistic setting with only a classification model available trained over, instead of accessing to, the source data. To effectively utilize the source model for adaptation, we propose a novel approach called Source HypOthesis Transfer (SHOT), which learns the feature extraction module for the target domain by fitting the target data features to the frozen source classification module (representing classification hypothesis). Specifically, SHOT exploits both information maximization and self-supervised learning for the feature extraction module learning to ensure the target features are implicitly aligned with the features of unseen source data via the same hypothesis. Furthermore, we propose a new labeling transfer strategy, which separates the target data into two splits based on the confidence of predictions (labeling information), and then employ semi-supervised learning to improve the accuracy of less-confident predictions in the target domain. We denote labeling transfer as SHOT++ if the predictions are obtained by SHOT. Extensive experiments on both digit classification and object recognition tasks show that SHOT and SHOT++ achieve results surpassing or comparable to the state-of-the-arts, demonstrating the effectiveness of our approaches for various visual domain adaptation problems. Code will be available at https://github.com/tim-learn/SHOT-plus.

ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation

“…In recent years, pioneering works [12], [13] discover that the well-trained source model conceals sufficient source knowledge for the following target adaptation stage, and [12] provides a clear definition of this problem. The last two years have witnessed an increasing number of SFDA approaches [15], [16], [17], [18], most of which are generation based [13], [14], [15] or self-training [12], [44] based methods. Generation based methods [14], [15], [13], [45], [20] generate virtual highlevel features of the source domain to bridge the unseen source and target distribution.…”

“…However, generating source samples usually introduces additional modules such as generators or discriminators, while pseudo-labeling might lead to wrong labels due to domain shift, both of which cause negative effects on the adaptation procedure. Another practice [45], [20], [16] is selecting part of the target data as a pseudo source domain, to compensate for the unseen source domain. A typical method is entropy-criterion [16], which constructs the pseudo source domain by estimating a split ratio using the target dataset's mean and maximum entropy, and then uses the split ratio to choose samples with lower entropy for all pseudo-labeled target domains within each class.…”

“…Nevertheless, generative modules introduce additional parameters, and the recovered virtual source domain usually suffers from a mode collapse problem, which results in low-quality images or features. The pseudo label-based methods [15], [16], [17], [18] label the target samples based on the present model's prediction or feature structure. However, due to the extreme domain shift, the noises are inescapable, result in inaccurate decision boundary.…”

“…Specifically, we define the weights of the source classifier as the class prototypes [19], then select the nearest neighbors for each class prototype in angle space to construct the proxy source domain. Priors methods with proxy source domain primarily employ entropy-criterion [16], [20], which select samples with lower entropy for each class from pseudolabeled target data. In practice, as shown in Fig.…”

Reciprocal Normalization for Domain Adaptation

“…Unsupervised domain adaptation (UDA) [15], [37], [22], [31], [32], [73] aims to transfer the knowledge learned from the labeled source domain to the unlabeled target domain. It has been widely applied in classification [38], detection [64], and segmentation [71].…”