DINE: Domain Adaptation from Single and Multiple Black-box Predictors
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2022)
摘要
To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (target). Despite impressive progress, prior methods always need to access the raw source data and develop data-dependent alignment approaches to recognize the target samples in a transductive learning manner, which may raise privacy concerns from source individuals. Several recent studies resort to an alternative solution by exploiting the well-trained white-box model from the source domain, yet, it may still leak the raw data via generative adversarial learning. This paper studies a practical and interesting setting for UDA, where only black-box source models (i.e., only network predictions are available) are provided during adaptation in the target domain. To solve this problem, we propose a new two-step knowledge adaptation framework called DIstill and fine-tuNE (DINE). Taking into consideration the target data structure, DINE first distills the knowledge from the source predictor to a customized target model, then fine-tunes the distilled model to further fit the target domain. Besides, neural networks are not required to be identical across domains in DINE, even allowing effective adaptation on a low-resource device. Empirical results on three UDA scenarios (i.e., single-source, multisource, and partial-set) confirm that DINE achieves highly competitive performance compared to state-of-the-art data-dependent approaches. Code is available at https://github.com/tim-learn/DINE/.
更多查看译文
关键词
Transfer/low-shot/long-tail learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要