☆ 3.8 Proceedings Paper

Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Maximum Density Divergence for Domain Adaptation

Jingjing Li et al.

Summary: This paper proposes a new domain adaptation method named ATM, which aims to reduce domain divergence by minimizing inter-domain divergence and maximizing intra-class density, combining adversarial training and metric learning. Experimental results show that the proposed ATM achieves state-of-the-art performance on multiple benchmark datasets.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep Residual Correction Network for Partial Domain Adaptation

Shuang Li et al.

Summary: Deep Residual Correction Network (DRCN) enhances adaptation from source to target by plugging a residual block and task-specific feature layer, while weakening the influence from irrelevant source classes. Weighted class-wise domain alignment loss is designed to couple two domains by matching shared class feature distributions. DRCN outperforms competitive deep domain adaptation approaches in partial, traditional, and fine-grained cross-domain visual recognition experiments.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Automation & Control Systems