Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
arXiv:2106.15326
Abstract
We study a practical domain adaptation task, called source-free unsupervised domain adaptation (UDA) problem, in which we cannot access source domain data due to data privacy issues but only a pre-trained source model and unlabeled target data are available. This task, however, is very difficult due to one key challenge: the lack of source data and target domain labels makes model adaptation very challenging. To address this, we propose to mine the hidden knowledge in the source model and exploit it to generate source avatar prototypes (i.e., representative features for each source class) as well as target pseudo labels for domain alignment. To this end, we propose a Contrastive Prototype Generation and Adaptation (CPGA) method. Specifically, CPGA consists of two stages: (1) prototype generation: by exploring the classification boundary information of the source model, we train a prototype generator to generate avatar prototypes via contrastive learning. (2) prototype adaptation: based on the generated source prototypes and target pseudo labels, we develop a new robust contrastive prototype adaptation strategy to align each pseudo-labeled target data to the corresponding source prototypes. Extensive experiments on three UDA benchmark datasets demonstrate the effectiveness and superiority of the proposed method.
arXiv commentAccepted by IJCAI 2021
References in corpus (11)
- Prototypical Networks for Few-shot Learning
- Deep Domain Confusion: Maximizing for Domain Invariance
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Conditional Adversarial Domain Adaptation
- VisDA: The Visual Domain Adaptation Challenge
- Model Adaptation: Unsupervised Domain Adaptation without Source Data
- A Closer Look at Memorization in Deep Networks
- Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
- Transferrable Prototypical Networks for Unsupervised Domain Adaptation
- Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
- Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering