arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.05780cs.CVcs.AI
收藏

TAKT:面向全切片图像分类的目标感知知识迁移

TAKT: Target-Aware Knowledge Transfer for Whole Slide Image Classification

The Chinese University of Hong Kong(香港中文大学);The Hong Kong University of Science and Technology (HKUST)(香港科技大学);Tencent YouTu Lab(腾讯优图实验室);Nanyang Technological University(南洋理工大学)

Conghao Xiong, Yi Lin, Hao Chen, Hao Zheng, Dong Wei, Yefeng Zheng, Joseph J. Y. Sung, Irwin King

AI总结:

针对全切片图像分类标注样本少、域偏移与任务差异阻碍知识迁移的问题,提出TAKT师生范式框架,结合目标感知特征对齐模块实现有效知识迁移,在多个数据集上达到SOTA性能。

摘要:

由于标注成本高昂,数据集的样本数量通常十分有限,因此将源域知识迁移到目标域对于全切片图像分类至关重要。然而,数据集之间的域偏移和任务差异会阻碍有效的知识迁移。本文提出了一种目标感知知识迁移(Target-Aware Knowledge Transfer)框架,采用师生范式。该框架通过主动将未标注的目标图像纳入教师模型的训练,使教师模型能够从源域和目标域中学习通用知识。随后对教师模型输出的包特征进行适配,以监督学生模型在目标域上的训练。尽管训练过程中融入了目标特征,但在固有的域偏移和任务差异下,教师模型往往会忽略这些特征。为缓解这一问题,我们引入了目标感知特征对齐模块,通过求解最优传输问题,在源特征与目标特征之间建立可迁移的潜在关联。实验结果表明,采用知识迁移的模型优于从头训练的模型,且我们的方法在TCGA-RCC、TCGA-NSCLC和Camelyon16等多个数据集上,在各类知识迁移方法中取得了当前最优性能。

英文摘要:

Transferring knowledge from a source domain to a target domain can be crucial for whole slide image classification, since the number of samples in a dataset is often limited due to high annotation costs. However, domain shift and task discrepancy between datasets can hinder effective knowledge transfer. In this paper, we propose a Target-Aware Knowledge Transfer framework, employing a teacher-student paradigm. Our framework enables the teacher model to learn common knowledge from the source and target domains by actively incorporating unlabelled target images into the training of the teacher model. The teacher bag features are subsequently adapted to supervise the training of the student model on the target domain. Despite incorporating the target features during training, the teacher model tends to overlook them under the inherent domain shift and task discrepancy. To alleviate this, we introduce a target-aware feature alignment module to establish a transferable latent relationship between the source and target features by solving the optimal transport problem. Experimental results show that models employing knowledge transfer outperform those trained from scratch, and our method achieves state-of-the-art performance among other knowledge transfer methods on various datasets, including TCGA-RCC, TCGA-NSCLC, and Camelyon16.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑