Unsupervised Domain Adaptation of Black-Box Source Models

Abstract

Unsupervised domain adaptation (UDA) aims to learn models for a target domain of unlabeled data by transferring knowledge from a labeled source domain. In the traditional UDA setting, labeled source data are assumed to be available for adaptation. Due to increasing concerns for data privacy, source-free UDA is highly appreciated as a new UDA setting, where only a trained source model is assumed to be available, while labeled source data remain private. However, trained source models may also be unavailable in practice since source models may have commercial values and exposing source models brings risks to the source domain, e.g., problems of model misuse and white-box attacks. In this work, we study a subtly different setting, named Black-Box Unsupervised Domain Adaptation (B${}^2$UDA), where only the application programming interface of source model is accessible to the target domain; in other words, the source model itself is kept as a black-box one. To tackle B${}^2$UDA, we propose a simple yet effective method, termed Iterative Learning with Noisy Labels (IterLNL). With black-box models as tools of noisy labeling, IterLNL conducts noisy labeling and learning with noisy labels (LNL), iteratively. To facilitate the implementation of LNL in B${}^2$UDA, we estimate the noise rate from model predictions of unlabeled target data and propose category-wise sampling to tackle the unbalanced label noise among categories. Experiments on benchmark datasets show the efficacy of IterLNL. Given neither source data nor source models, IterLNL performs comparably with traditional UDA methods that make full use of labeled source data.

References in corpus (17)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Learning Transferable Features with Deep Adaptation Networks
• On Calibration of Modern Neural Networks
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• Conditional Adversarial Domain Adaptation
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• VisDA: The Visual Domain Adaptation Challenge
• Model Adaptation: Unsupervised Domain Adaptation without Source Data
• A Closer Look at Memorization in Deep Networks
• Masking: A New Perspective of Noisy Supervision
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
• Deep Transfer Learning with Joint Adaptation Networks
• A Survey of Label-noise Representation Learning: Past, Present and Future
• SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
• Source Free Domain Adaptation with Image Translation
• Domain Adaptation without Source Data
• Searching to Exploit Memorization Effect in Learning from Corrupted Labels

Cited by in corpus (7)

• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• Privacy-Preserving Brain-Computer Interfaces: A Systematic Review
• RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
• On Universal Black-Box Domain Adaptation
• DINE: Domain Adaptation from Single and Multiple Black-box Predictors
• Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable Transfer from Black-Box to Lightweight Segmentation Model
• Domain Adaptation without Model Transferring