Prototype-Matching Graph Network for Heterogeneous Domain Adaptation

Wang, Zijian; Luo, Yadan; Huang, Zi; Baktashmotlagh, Mahsa

doi:10.1145/3394171.3413662

Cited by 29 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Domain adaptation [31,27] aims to learn a model for the unlabeled target domain by leveraging knowledge from a labeled source domain. A group of methods uses various metrics to mitigate the distribution difference caused by domain gap, such as maximum mean discrepancy (MMD) [5] and its variants [32,18].…”

Section: Domain Adaptationmentioning

confidence: 99%

Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

Jiao¹,

Wu²,

Lou³

et al. 2021

Preprint

View full text Add to dashboard Cite

Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time. Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database. In this way, when updating the deployed model, we can bypass the inflexible and time-consuming feature re-extraction process. However, the old feature space that needs to be compatible is not ideal and faces the distribution discrepancy problem with the new space caused by different supervision losses. In this work, we propose a global optimization Dual-Tuning method to obtain feature compatibility against different networks and losses. A feature-level prototype loss is proposed to explicitly align two types of embedding features, by transferring global prototype information. Furthermore, we design a component-level mutual structural regularization to implicitly optimize the feature intrinsic structure. Experimental results on million-scale datasets demonstrate that our Dual-Tuning is able to obtain feature compatibility without sacrificing performance. (Our code will be avaliable at https://github.com/yanbai1993/Dual-Tuning)

show abstract

Section: Domain Adaptationmentioning

confidence: 99%

Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

Jiao¹,

Wu²,

Lou³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…However, the conventional recommender systems are mainly developed using item IDs and textual information, which fail to leverage the important visual signals for recommendation. The rapid development of computer vision area has significantly promoted various visualbased applications, such as image retrieval [25,53,26,43,52,5,50,49], visual understanding [42,28,6], and visual domain adaptation [29,27,41]. This also has largely facilitated the studies in the fashion area.…”

Section: Related Workmentioning

confidence: 99%

Attribute-aware Explainable Complementary Clothing Recommendation

Chen

Huang

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Modelling mix-and-match relationships among fashion items has become increasingly demanding yet challenging for modern E-commerce recommender systems. When performing clothes matching, most existing approaches leverage the latent visual features extracted from fashion item images for compatibility modelling, which lacks explainability of generated matching results and can hardly convince users of the recommendations. Though recent methods start to incorporate pre-defined attribute information (e.g., colour, style, length, etc.) for learning item representations and improving the model interpretability, their utilisation of attribute information is still mainly reserved for enhancing the learned item representations and generating explanations via post-processing. As a result, this creates a severe bottleneck when we are trying to advance the recommendation accuracy and generating fine-grained explanations since the explicit attributes have only loose connections to the actual recommendation process. This work aims to tackle the explainability challenge in fashion recommendation tasks by proposing a novel Attribute-aware Fashion Recommender (AFRec). Specifically, AFRec recommender assesses the outfit compatibility by explicitly leveraging the extracted attribute-level representations from each item's visual feature. The attributes serve as the bridge between two fashion items, where we quantify the affinity of a pair of items through the learned compatibility between their attributes. Extensive experiments have demonstrated that, by making full use of the explicit attributes in

show abstract

“…In particular, the sample alignment focuses on mitigating the domain shifts by the importance-weighting of samples [15]- [17]. In contrast, the feature alignment attempts to learn a domain invariant feature or representation to alleviate the domain discrepancies by kernel matching [18], adversarial learning [19], prototype matching [5], optimal transport [20] and image reconstruction [21].…”

Section: Introductionmentioning

confidence: 99%

Jacobian Norm for Unsupervised Source-Free Domain Adaptation

Li¹,

Cao²,

Chen³

2022

Preprint

View full text Add to dashboard Cite

Unsupervised Source (data) Free domain adaptation (USFDA) aims to transfer knowledge from a well-trained source model to a related but unlabeled target domain. In such a scenario, all conventional adaptation methods that require source data fail. To combat this challenge, existing USFDAs turn to transfer knowledge by aligning the target feature to the latent distribution hidden in the source model. However, such information is naturally limited. Thus, the alignment in such a scenario is not only difficult but also insufficient, which degrades the target generalization performance. To relieve this dilemma in current USFDAs, we are motivated to explore a new perspective to boost their performance. For this purpose and gaining necessary insight, we look back upon the origin of the domain adaptation and first theoretically derive a new-brand target generalization error bound based on the model smoothness. Then, following the theoretical insight, a general and model-smoothness-guided Jacobian norm (JN) regularizer is designed and imposed on the target domain to mitigate this dilemma. Extensive experiments are conducted to validate its effectiveness. In its implementation, just with a few lines of codes added to the existing USFDAs, we achieve superior results on various benchmark datasets.

show abstract

Prototype-Matching Graph Network for Heterogeneous Domain Adaptation

Cited by 29 publications

References 30 publications

Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

Attribute-aware Explainable Complementary Clothing Recommendation

Jacobian Norm for Unsupervised Source-Free Domain Adaptation

Contact Info

Product

Resources

About