关注细节：跨分辨率知识蒸馏
Attention to detail: inter-resolution knowledge distillation
AI总结：
针对数字病理学中降低图像分辨率导致模型性能下降的问题，本文提出利用 grad-CAM 注意力图进行跨分辨率知识蒸馏，引导低分辨率学生模型匹配教师分布，并在前列腺组织分级中显著提升性能。
摘要：
数字病理学中针对十亿像素级图像的计算机视觉解决方案的发展，受到全切片图像尺寸过大所带来的显著计算限制的阻碍。特别是，以高分辨率数字化活检组织是一个耗时的过程，而这一过程又是必要的，因为图像细节的减少会导致结果恶化。为了缓解这一问题，近期文献提出利用知识蒸馏来增强模型在降低图像分辨率情况下的性能。具体而言，将在最高放大倍率下提取的软标签和特征蒸馏到一个以较低放大倍率图像为输入的模型中。然而，这种方法未能迁移分类过程中最具判别性的图像区域的相关知识，而这些知识在分辨率降低时可能会丢失。在本工作中，我们提出通过在训练过程中引入注意力图来蒸馏这些信息。具体来说，我们的方法利用通过 grad-CAM 获得的目标类别的显著性图，通过最小化它们之间的 l2 距离，引导低分辨率的 Student 模型去匹配 Teacher 分布。在前列腺组织学图像分级上的综合实验表明，与先前文献相比，所提出的方法在不同图像分辨率下均显著提升了模型性能。
英文摘要：
The development of computer vision solutions for gigapixel images in digital pathology is hampered by significant computational limitations due to the large size of whole slide images. In particular, digitizing biopsies at high resolutions is a time-consuming process, which is necessary due to the worsening results from the decrease in image detail. To alleviate this issue, recent literature has proposed using knowledge distillation to enhance the model performance at reduced image resolutions. In particular, soft labels and features extracted at the highest magnification level are distilled into a model that takes lower-magnification images as input. However, this approach fails to transfer knowledge about the most discriminative image regions in the classification process, which may be lost when the resolution is decreased. In this work, we propose to distill this information by incorporating attention maps during training. In particular, our formulation leverages saliency maps of the target class via grad-CAMs, which guides the lower-resolution Student model to match the Teacher distribution by minimizing the l2 distance between them. Comprehensive experiments on prostate histology image grading demonstrate that the proposed approach substantially improves the model performance across different image resolutions compared to previous literature.
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。
