返回
Joint Variational Inference Network for domain generalization
DOI:10.1016/j.patcog.2024.110587.png)
摘要
En 中文
Domain generalization is a machine learning task that involves training a model on a set of domains with the goal of achieving high performance on unseen domains. While most domain generalization methods focus on extracting domain -invariant features, they may ignore domain -specific information beyond object styles which is label -relevant for classification. In this paper, we first propose a two-step data generation process in which the domain label and observed data are sampled from two distributions sequentially, and accordingly develop an end -to -end Joint Variational Inference Network (JVINet) for domain generalization. JVINet is a framework that admits a variational -based discriminative structure, which the domain -specific latent variable is learned and integrated to enhance the feature for classification. When testing on unseen target domains, the potential beneficial domain information is hence utilized to improve generalization ability. The overall objective is to optimize the variational lower bound of the conditional joint likelihood functions for both class and domain labels. We provide theoretical proof that JVINet can achieve an optimal lower bound using a variational -based discriminative approach. To evaluate the effectiveness of our method, we compare it with state-of-the-art methods on both simulated and real -world datasets.
Keyword:
Domain generalization
Deep learning
Variational Bayesian
Transfer learning
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
First-Principles Calculations of Acoustic and Anharmonic Properties of Ferromagnetic Cu2MnZ (Z = Al and In) Heusler Alloys铁磁Cu2MnZ (Z = Al和In) Heusler合金的声学和非谐特性的第一性原理计算
Acute myeloid and T‐cell acute lymphoblastic leukaemia with aberrant antigen expression exhibit similar TCRδ gene rearrangements抗原表达异常的急性髓性和t细胞急性淋巴细胞白血病表现出相似的tcr δ 基因重排
A novel pentaruthenium cluster containing three thiazole derived ligands; X-ray structure of [(Ru3(CO)9(μ-H)(μ5-η5-HCNCCHS)Ru2-(CO)4(μ-H) (η1-HC=NCH=CHS) (μ-2,3-η3-C=NCH=CHS)]含有三个噻唑衍生配体的新型五钌簇; [(Ru3(CO)9 (μ-h)(μ5-η5-HC nc chs) Ru2-(CO)4 (μ-h) (η1-HC = NCH = CHS) (μ-2,3-η3-C = NCH = CHS)] 的x射线结构
Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统

