no code implementations • 4 May 2024 • Siyuan Yan, Cheng Luo, Zhen Yu, ZongYuan Ge
To address this, we propose a plug-and-play feature augmentation method called LDFS (Language-Guided Diverse Feature Synthesis) to synthesize new domain features and improve existing CLIP fine-tuning strategies.
no code implementations • 20 Mar 2024 • Zhen Yu, Yang Liu, Qingchao Chen
To solve these barriers, we propose to design a novel progressive trajectory matching strategy to improve the training stability for medical image dataset distillation.
2 code implementations • 5 Jan 2024 • Siyuan Yan, Chi Liu, Zhen Yu, Lie Ju, Dwarikanath Mahapatra, Brigid Betz-Stablein, Victoria Mar, Monika Janda, Peter Soyer, ZongYuan Ge
To address these challenges, we propose a novel DG framework for medical image classification without relying on domain labels, called Prompt-driven Latent Domain Generalization (PLDG).
no code implementations • 8 Apr 2023 • Lie Ju, Yicheng Wu, Wei Feng, Zhen Yu, Lin Wang, Zhuoting Zhu, ZongYuan Ge
Therefore, in this paper, we proposed a unified framework to leverage these unseen unlabeled data for open-scenario semi-supervised medical image classification.
1 code implementation • 4 Apr 2023 • Siyuan Yan, Chi Liu, Zhen Yu, Lie Ju, Dwarikanath Mahapatrainst, Victoria Mar, Monika Janda, Peter Soyer, ZongYuan Ge
Concretely, EPVT leverages a set of domain prompts, each of which plays as a domain expert, to capture domain-specific knowledge; and a shared prompt for general knowledge over the entire dataset.
no code implementations • CVPR 2023 • Siyuan Yan, Zhen Yu, Xuelin Zhang, Dwarikanath Mahapatra, Shekhar S. Chandra, Monika Janda, Peter Soyer, ZongYuan Ge
We introduce a human-in-the-loop framework in the model training process such that users can observe and correct the model's decision logic when confounding behaviors happen.
no code implementations • 13 Sep 2022 • Zhen Yu, Toan Nguyen, Yaniv Gal, Lie Ju, Shekhar S. Chandra, Lei Zhang, Paul Bonnington, Victoria Mar, Zhiyong Wang, ZongYuan Ge
Accordingly, the learned prototypes preserve the semantic class relations in the embedding space and we can predict the label of an image by assigning its feature to the nearest hyperbolic class prototype.
no code implementations • 7 Apr 2022 • Lie Ju, Yicheng Wu, Lin Wang, Zhen Yu, Xin Zhao, Xin Wang, Paul Bonnington, ZongYuan Ge
To address this, in this paper, we propose a curriculum learning-based framework called Flexible Sampling for the long-tailed skin lesion classification task.
1 code implementation • 20 Jan 2022 • Zhen Yu, Xiaosen Wang, Wanxiang Che, Kun He
Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications.
no code implementations • 17 Nov 2021 • Lie Ju, Zhen Yu, Lin Wang, Xin Zhao, Xin Wang, Paul Bonnington, ZongYuan Ge
From a modeling perspective, most deep learning models trained on these datasets may lack the ability to generalize to rare diseases where only a few available samples are presented for training.
no code implementations • 12 Oct 2021 • Zhen Yu, Jennifer Nguyen, Toan D Nguyen, John Kelly, Catriona Mclean, Paul Bonnington, Lei Zhang, Victoria Mar, ZongYuan Ge
In this study, we propose a framework for automated early melanoma diagnosis using sequential dermoscopic images.
no code implementations • 19 Jun 2020 • Zhen Yu, Jennifer Nguyen, Xiaojun Chang, John Kelly, Catriona Mclean, Lei Zhang, Victoria Mar, ZongYuan Ge
Existing studies for automated melanoma diagnosis are based on single-time point images of lesions.
no code implementations • 8 Apr 2020 • Youyi Song, Zhen Yu, Teng Zhou, Jeremy Yuen-Chun Teoh, Baiying Lei, Kup-Sze Choi, Jing Qin
Our insight is that feature maps of two CNNs trained respectively on GT and CT images should be similar on some metric space, because they both are used to describe the same objects for the same purpose.
no code implementations • 17 Jan 2020 • Ping Zhou, Zhen Yu, Jingyi Ma, Maozai Tian, Ye Fan
Distributed statistical inference has recently attracted immense attention.