no code implementations • 18 Jan 2024 • Guanglin Zhou, Zhongyi Han, Shiming Chen, Biwei Huang, Liming Zhu, Tongliang Liu, Lina Yao, Kun Zhang
Domain Generalization (DG) endeavors to create machine learning models that excel in unseen scenarios by learning invariant features.
1 code implementation • 12 Dec 2023 • Zhongyi Han, Guanglin Zhou, Rundong He, Jindong Wang, Tailin Wu, Yilong Yin, Salman Khan, Lina Yao, Tongliang Liu, Kun Zhang
We further investigate its adaptability to controlled data perturbations and examine the efficacy of in-context learning as a tool to enhance its adaptation.
no code implementations • CVPR 2023 • Fan Wang, Zhongyi Han, Zhiyan Zhang, Rundong He, Yilong Yin
Source free domain adaptation (SFDA) aims to transfer a trained source model to the unlabeled target domain without accessing the source data.
no code implementations • 16 Sep 2022 • Rundong He, Rongxue Li, Zhongyi Han, Yilong Yin
Based on limited ID labeled data and sufficient unlabeled data, we define a new setting called Weakly-Supervised Out-of-Distribution Detection (WSOOD).
no code implementations • 22 May 2022 • Fan Wang, Zhongyi Han, Zhiyan Zhang, Yilong Yin
We then propose minimum happy points learning (MHPL) to actively explore and exploit MH points.
no code implementations • CVPR 2022 • Fan Wang, Zhongyi Han, Yongshun Gong, Yilong Yin
In contrast, we provide a fascinating insight: rather than attempting to learn domain-invariant representations, it is better to explore the domain-invariant parameters of the source model.
no code implementations • CVPR 2022 • Rundong He, Zhongyi Han, Xiankai Lu, Yilong Yin
To take advantage of these unseen-class data and ensure performance, we propose a safe SSL method called SAFE-STUDENT from the teacher-student view.
1 code implementation • 8 Nov 2021 • Haoliang Sun, Chenhui Guo, Qi Wei, Zhongyi Han, Yilong Yin
In this paper, we propose warped probabilistic inference (WarPI) to achieve adaptively rectifying the training procedure for the classification network within the meta-learning scenario.
1 code implementation • 13 Aug 2021 • Zhongyi Han, Haoliang Sun, Yilong Yin
However, the learning processes of domain-invariant features and source hypothesis inevitably involve domain-specific information that would degrade the generalizability of UDA models on the target domain.
no code implementations • 28 Apr 2020 • Zhongyi Han, Benzheng Wei, Yilong Yin, Shuo Li
In this paper, we propose the neural-symbolic learning (NSL) framework that performs human-like learning by unifying deep neural learning and symbolic logical reasoning for the spinal medical report generation.
1 code implementation • 27 Apr 2020 • Zhongyi Han, Xian-Jin Gui, Chaoran Cui, Yilong Yin
In non-stationary environments, learning machines usually confront the domain adaptation scenario where the data distribution does change over time.
no code implementations • 27 Apr 2020 • Tianyang Li, Zhongyi Han, Benzheng Wei, Yuanjie Zheng, Yanfei Hong, Jinyu Cong
However, robust and accurate screening of COVID-19 from chest X-rays is still a globally recognized challenge because of two bottlenecks: 1) imaging features of COVID-19 share some similarities with other pneumonia on chest X-rays, and 2) the misdiagnosis rate of COVID-19 is very high, and the misdiagnosis cost is expensive.