.png){kind=icon}
返回
Gradient-aware domain-invariant learning for domain generalization
.png){kind=icon}
PRE
AI
DOI：10.1007/s00530-024-01613-4.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In realistic scenarios, the effectiveness of Deep Neural Networks is hindered by domain shift, where discrepancies between training (source) and testing (target) domains lead to poor generalization on previously unseen data. The Domain Generalization (DG) paradigm addresses this challenge by developing a general model that relies solely on source domains, aiming for robust performance in unknown domains. Despite the progress of prior augmentation-based methods by introducing more diversity based on the known distribution, DG still suffers from overfitting due to limited domain-specific information. Therefore, unlike prior DG methods that treat all parameters equally, we propose a Gradient-Aware Domain-Invariant Learning mechanism that adaptively recognizes and emphasizes domain-invariant parameters. Specifically, two novel models named Domain Decoupling and Combination and Domain-Invariance-Guided Backpropagation (DIGB) are introduced to first generate contrastive samples with the same domain-invariant features and then selectively prioritize parameters with unified optimization directions across contrastive sample pairs to enhance domain robustness. Additionally, a sparse version of DIGB achieves a trade-off between performance and efficiency. Our extensive experiments on various domain generalization benchmarks demonstrate that our proposed method achieves state-of-the-art performance with strong generalization capabilities.
Keyword:
Domain shift
Domain generalization
Domain-invariant parameters
Sparse
期刊
IF:
3.1
论文数:
2.8K
被引数:
2.7K
机构
引用论文
分享收藏Determinants of quality of life in patients with fibromyalgia: A structural equation modeling approach纤维肌痛患者生活质量的决定因素: 结构方程建模方法.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏Improved proprioceptive function by application of subsensory electrical noise: Effects of aging and task-demandNeuroscienceOAAI
NeuroscienceIF0
OAAI分享收藏A cancer pharmacogenomic screen powering crowd-sourced advancement of drug combination prediction
OAAI
IF0
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