Compound Domain Generalization via Meta-Knowledge Encoding
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7109-7119
Abstract
Domain generalization (DG) aims to improve the generalization performance for an unseen target domain by using the knowledge of multiple seen source domains. Mainstream DG methods typically assume that the domain label of each source sample is known a priori, which is challenged to be satisfied in many real-world applications. In this paper, we study a practical problem of compound DG, which relaxes the discrete domain assumption to the mixed source domains setting. On the other hand, current DG algorithms prioritize the focus on semantic invariance across domains (one-vs-one), while paying less attention to the holistic semantic structure (many-vs-many). Such holistic semantic structure, referred to as meta-knowledge here, is crucial for learning generalizable representations. To this end, we present COmpound domain generalization via Meta-knowledge ENcoding (COMEN), a general approach to automatically discover and model latent domains in two steps. Firstly, we introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions, thereby dividing the mixture of source domains into latent clusters. Secondly, we harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space with two parallel and complementary modules, which explicitly encode the semantic structure for the out-of-distribution generalization. Experiments on four standard DG benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2020YFC2003902)
This publication has 39 references indexed in Scilit:
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Deep Residual Learning for Image Recognition2016
- Domain Generalization for Object Recognition with Multi-task Autoencoders2015
- Unbiased Metric Learning: On the Utilization of Multiple Datasets and Web Images for Softening Bias2013
- Discovering Latent Domains for Multisource Domain Adaptation2012
- Unbiased look at dataset bias2011
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007
- Dimensionality Reduction by Learning an Invariant Mapping2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998