Generalized Domain Conditioned Adaptation Network

Abstract

Domain Adaptation (DA) attempts to transfer knowledge learned in the labeled source domain to the unlabeled but related target domain without requiring large amounts of target supervision. Recent advances in DA mainly proceed by aligning the source and target distributions. Despite the significant success, the adaptation performance still degrades accordingly when the source and target domains encounter a large distribution discrepancy. We consider this limitation may attribute to the insufficient exploration of domain-specialized features because most studies merely concentrate on domain-general feature learning in task-specific layers and integrate totally-shared convolutional networks (convnets) to generate common features for both domains. In this paper, we relax the completely-shared convnets assumption adopted by previous DA methods and propose Domain Conditioned Adaptation Network (DCAN), which introduces domain conditioned channel attention module with a multi-path structure to separately excite channel activation for each domain. Such a partially-shared convnets module allows domain-specialized features in low-level to be explored appropriately. Further, given the knowledge transferability varying along with convolutional layers, we develop Generalized Domain Conditioned Adaptation Network (GDCAN) to automatically determine whether domain channel activations should be separately modeled in each attention module. Afterward, the critical domain-specialized knowledge could be adaptively extracted according to the domain statistic gaps. As far as we know, this is the first work to explore the domain-wise convolutional channel activations separately for deep DA networks. Additionally, to effectively match high-level feature distributions across domains, we consider deploying feature adaptation blocks after task-specific layers, which can explicitly mitigate the domain discrepancy.

Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI). Journal version of arXiv:2005.06717 (AAAI 2020). Code is available at https://github.com/BIT-DA/GDCAN

References in corpus (10)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Two-Stream Convolutional Networks for Action Recognition in Videos
• How transferable are features in deep neural networks?
• Fully Convolutional Networks for Semantic Segmentation
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Deep Domain Confusion: Maximizing for Domain Invariance
• Bridging Theory and Algorithm for Domain Adaptation
• Deep Residual Correction Network for Partial Domain Adaptation