Qiuxia Lin

Qiuxia Lin

Auto-generated profile, based on publicly available information

Qiuxia Lin

School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 December 2018 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
CLChi Harold Liu
Chi Harold Liu
QLQiuxia Lin
Qiuxia Lin
SWShilin Wen
Shilin Wen

7 January 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
Shuang LiShuang Li
Shuang Li
CLChi Harold Liu
Chi Harold Liu
QLQiuxia Lin
Qiuxia Lin
QWQi Wen
Qi Wen
LSLimin Su
Limin Su
Zhengming DingZhengming Ding
Zhengming Ding
Deep domain adaptation methods have achieved appealing performance by learning transferable representations from a well-labeled source domain to a different but related unlabeled target domain. Most existing works assume source and target data share the identical label space, which is often difficult to be satisfied in many real-world applications. There is a more practical scenario called partial domain adaptation, where the target label space is a subset of the source label space. In this case, reinforcing the positive effects of the most relevant source subclasses and reducing the negative impacts of irrelevant source subclasses are crucial. This paper proposes an efficiently-implemented Deep Residual Correction Network by plugging one residual block into the source network, which effectively enhances the adaptation from source to target and explicitly weakens the influence from the irrelevant source classes. Moreover, we design a weighted class-wise domain alignment loss to couple two domains by matching the feature distributions of shared classes between source and target. Comprehensive experiments on partial, traditional and fine-grained cross-domain visual recognition demonstrate that DRCN is superior to the competitive deep domain adaptation approaches.

1 March 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
Shuang LiShuang Li
Shuang Li
BXBinhui Xie
Binhui Xie
QLQiuxia Lin
Qiuxia Lin
CLChi Harold Liu
Chi Harold Liu
GHGao Huang
Gao Huang
GWGuoren Wang
Guoren Wang
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. Extensive experiments on four cross-domain benchmarks, including DomainNet, Office-Home, Office-31, and ImageCLEF, demonstrate the proposed approaches outperform the existing methods by a large margin, especially on the large-scale challenging dataset. The code and models are available at https://github.com/BIT-DA/GDCAN .