Search Results for author: Zhongyi Han

Found 17 papers, 6 papers with code

Improving Representation of High-frequency Components for Medical Foundation Models

no code implementations19 Jul 2024 Yuetan Chu, Yilan Zhang, Zhongyi Han, Changchun Yang, Longxi Zhou, Gongning Luo, Xin Gao

Foundation models have recently attracted significant attention for their impressive generalizability across diverse downstream tasks.

SkinCAP: A Multi-modal Dermatology Dataset Annotated with Rich Medical Captions

no code implementations28 May 2024 Juexiao Zhou, Liyuan Sun, Yan Xu, wenbin liu, Shawn Afvari, Zhongyi Han, Jiaoyan Song, Yongzhi Ji, Xiaonan He, Xin Gao

To address this gap and provide a meticulously annotated dermatology dataset with comprehensive natural language descriptions, we introduce SkinCAP: a multi-modal dermatology dataset annotated with rich medical captions.

Can We Treat Noisy Labels as Accurate?

1 code implementation21 May 2024 Yuxiang Zheng, Zhongyi Han, Yilong Yin, Xin Gao, Tongliang Liu

Instead of focusing on label correction, EchoAlign treats noisy labels ($\tilde{Y}$) as accurate and modifies corresponding instance features ($X$) to achieve better alignment with $\tilde{Y}$.

Learning with noisy labels

Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learning

1 code implementation20 May 2024 Guanglin Zhou, Zhongyi Han, Shiming Chen, Biwei Huang, Liming Zhu, Salman Khan, Xin Gao, Lina Yao

We find that the success of ICL heavily relies on the choice of demonstration, mirroring challenges seen in large language models but introducing unique complexities for LMMs facing distribution shifts.

In-Context Learning

HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization

no code implementations18 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.

Contrastive Learning Domain Generalization

How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation

1 code implementation12 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.

Anomaly Detection Autonomous Driving +6

MHPL: Minimum Happy Points Learning for Active Source Free Domain 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.

Active Learning Source-Free Domain Adaptation

Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detection

no code implementations16 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).

Contrastive Learning Out-of-Distribution Detection +1

Active Source Free Domain Adaptation

no code implementations22 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.

Source-Free Domain Adaptation

Safe-Student for Safe Deep Semi-Supervised Learning With Unseen-Class Unlabeled Data

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.

Exploring Domain-Invariant Parameters for Source Free Domain Adaptation

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.

Privacy Preserving Source-Free Domain Adaptation

Learning to Rectify for Robust Learning with Noisy Labels

1 code implementation8 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.

Learning with noisy labels Meta-Learning

Learning Transferable Parameters for Unsupervised Domain Adaptation

1 code implementation13 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.

Image Classification Keypoint Detection +2

Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation

no code implementations28 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.

Decision Making Generative Adversarial Network +3

Towards Accurate and Robust Domain Adaptation under Noisy Environments

1 code implementation27 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.

Unsupervised Domain Adaptation

Robust Screening of COVID-19 from Chest X-ray via Discriminative Cost-Sensitive Learning

no code implementations27 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.