BiPC: Bidirectional Probability Calibration for Unsupervised Domain Adaption
This addresses domain adaptation challenges for researchers and practitioners using CNNs and hierarchical Transformers, though it appears incremental as it builds on existing pre-training and probability calibration ideas.
The paper tackles the limitation of Transformer-based methods in Unsupervised Domain Adaptation (UDA) by proposing Bidirectional Probability Calibration (BiPC), which leverages pre-trained heads to adjust probability distributions and improve model performance across various networks, achieving remarkable results on multiple UDA tasks.
Unsupervised Domain Adaptation (UDA) leverages a labeled source domain to solve tasks in an unlabeled target domain. While Transformer-based methods have shown promise in UDA, their application is limited to plain Transformers, excluding Convolutional Neural Networks (CNNs) and hierarchical Transformers. To address this issues, we propose Bidirectional Probability Calibration (BiPC) from a probability space perspective. We demonstrate that the probability outputs from a pre-trained head, after extensive pre-training, are robust against domain gaps and can adjust the probability distribution of the task head. Moreover, the task head can enhance the pre-trained head during adaptation training, improving model performance through bidirectional complementation. Technically, we introduce Calibrated Probability Alignment (CPA) to adjust the pre-trained head's probabilities, such as those from an ImageNet-1k pre-trained classifier. Additionally, we design a Calibrated Gini Impurity (CGI) loss to refine the task head, with calibrated coefficients learned from the pre-trained classifier. BiPC is a simple yet effective method applicable to various networks, including CNNs and Transformers. Experimental results demonstrate its remarkable performance across multiple UDA tasks. Our code will be available at: https://github.com/Wenlve-Zhou/BiPC.