☆ 3.8 Proceedings Paper

Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice

Yabin Zhang et al.

Summary: This paper studies the formalism of unsupervised multi-class domain adaptation and proposes the concept of Multi-Class Scoring Disagreement (MCSD) to characterize the relations between multi-class scoring hypotheses. Based on this concept, the paper develops algorithms including Multi-class Domain-adversarial learning Networks (McDalNets) and Domain-Symmetric Networks (SymmNets). Empirical studies verify the theoretical analysis and demonstrate the efficacy of the proposed algorithms.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Compound Domain Generalization via Meta-Knowledge Encoding

Chaoqi Chen et al.

Summary: This paper studies the practical problem of compound domain generalization and proposes a general approach to automatically discover and model latent domains. Experimental results show that the proposed method outperforms existing techniques on four standard domain generalization benchmarks.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

CrossNorm and SelfNorm for Generalization under Distribution Shifts

Zhiqiang Tang et al.

Summary: The paper introduces two new normalization methods, CrossNorm and SelfNorm, to improve model generalization robustness under distribution shifts by exchanging mean and variance between feature maps and recalibrating statistics using attention. Experiments show the effectiveness of these methods in different tasks and fields.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence