Minimum Class Confusion for Versatile Domain Adaptation
By Ying Jin, Ximei Wang, Mingsheng Long, Jianmin Wang. European Conference on Computer Vision, 2019
478 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Infectious Diseases
View Paper: https://www.semanticscholar.org/paper/ee66b3c5dc6347b3cdfd3e7ef8dd4968163e93b4
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Luc Van Gool
- Dengxin Dai
- Lukas Hoyer
- Trevor Darrell
- Dequan Wang
- Sayna Ebrahimi
- Haoran Wang
- Dongrui Wu
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dengxin Dai
- Trevor Darrell
- Ming-Hsuan Yang
- Lukas Hoyer
- Dacheng Tao
- Jiashi Feng
- Xiaogang Wang
Citations in the corpus
- MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation (2022, methodology): “For UDA training, we follow SDAT [57], which utilizes CDAN [48] with MCC [36] and a smoothness enhancing loss [57].”
- A Survey on Negative Transfer (2020, methodology): “Clustering enhanced pseudo-labeling explores the unsupervised clustering information to enhance target prediction [123], [139]–[141].”
- Contrastive Test-Time Adaptation (2022, methodology): “AdaContrast achieves 62.6% accuracy averaged on 7 domain shifts in DomainNet-126, surpassing the UDA method MCC [21] (see Tab.”
- A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts (2023, unknown): “, inputlevel translation [28], [29], feature-level alignment [30], [31], [32]), output-level regularization [33], [34], [35], and prior estimation [17], [36], [37].”