.png){kind=icon}
返回
D-BIN: A Generalized Disentangling Batch Instance Normalization for Domain Adaptation
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2021.3110128.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Pattern recognition is significantly challenging in real-world scenarios by the variability of visual statistics. Therefore, most existing algorithms relying on the independent identically distributed assumption of training and test data suffer from the poor generalization capability of inference on unseen testing datasets. Although numerous studies, including domain discriminator or domain-invariant feature learning, are proposed to alleviate this problem, the data-driven property and lack of interpretation of their principle throw researchers and developers off. Consequently, this dilemma incurs us to rethink the essence of networks' generalization. An observation that visual patterns cannot be discriminative after style transfer inspires us to take careful consideration of the importance of style features and content features. Does the style information related to the domain bias? How to effectively disentangle content and style features across domains? In this article, we first investigate the effect of feature normalization on domain adaptation. Based on it, we propose a novel normalization module to adaptively leverage the propagated information through each channel and batch of features called disentangling batch instance normalization (D-BIN). In this module, we explicitly explore domain-specific and domain-invariant feature disentanglement. We maneuver contrastive learning to encourage images with the same semantics from different domains to have similar content representations while having dissimilar style representations. Furthermore, we construct both self-form and dual-form regularizers for preserving the mutual information (MI) between feature representations of the normalization layer in order to compensate for the loss of discriminative information and effectively match the distributions across domains. D-BIN and the constrained term can be simply plugged into state-of-the-art (SOTA) networks to improve their performance. In the end, experiments, including domain adaptation and generalization, conducted on different datasets have proven their effectiveness.
Keyword:
Task analysis
Adaptation models
Training
Semantics
Neural networks
Measurement
Computational modeling
Domain adaptation
domain generalization (DG)
feature disentangling
normalization
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
引用论文
ARVino - outdoor augmented reality visualisation of viticulture GIS dataARVino-葡萄栽培GIS数据的户外增强现实可视化
OAAI
.png){kind=icon}
OAAI分享收藏The Cauchy-Schwarz divergence and Parzen windowing: Connections to graph theory and Mercer kernels
PREAI
分享收藏Surgical therapy and next-generation sequencing-based genetic alteration analysis of malignant solitary fibrous tumor of the pleura胸膜恶性孤立性纤维瘤的外科治疗和基于二代测序的遗传学改变分析OAAI
OAAI分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容