CCSI: Continual Class-Specific Impression for data-free class incremental learning,Medical Image Analysis

当前位置： X-MOL 学术 › Med. Image Anal. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

CCSI: Continual Class-Specific Impression for data-free class incremental learning
Medical Image Analysis ( IF 10.7 ) Pub Date : 2024-06-15 , DOI: 10.1016/j.media.2024.103239
Sana Ayromlou ₁ , Teresa Tsang ₂ , Purang Abolmaesumi ₃ , Xiaoxiao Li ₁

Affiliation

In real-world clinical settings, traditional deep learning-based classification methods struggle with diagnosing newly introduced disease types because they require samples from all disease classes for offline training. Class incremental learning offers a promising solution by adapting a deep network trained on specific disease classes to handle new diseases. However, catastrophic forgetting occurs, decreasing the performance of earlier classes when adapting the model to new data. Prior proposed methodologies to overcome this require perpetual storage of previous samples, posing potential practical concerns regarding privacy and storage regulations in healthcare. To this end, we propose a novel data-free class incremental learning framework that utilizes data synthesis on learned classes instead of data storage from previous classes. Our key contributions include acquiring synthetic data known as Continual Class-Specific Impression (CCSI) for previously inaccessible trained classes and presenting a methodology to effectively utilize this data for updating networks when introducing new classes. We obtain CCSI by employing data inversion over gradients of the trained classification model on previous classes starting from the mean image of each class inspired by common landmarks shared among medical images and utilizing continual normalization layers statistics as a regularizer in this pixel-wise optimization process. Subsequently, we update the network by combining the synthesized data with new class data and incorporate several losses, including an intra-domain contrastive loss to generalize the deep network trained on the synthesized data to real data, a margin loss to increase separation among previous classes and new ones, and a cosine-normalized cross-entropy loss to alleviate the adverse effects of imbalanced distributions in training data. Extensive experiments show that the proposed framework achieves state-of-the-art performance on four of the public MedMNIST datasets and in-house echocardiography cine series, with an improvement in classification accuracy of up to 51% compared to baseline data-free methods. Our code is available at https://github.com/ubc-tea/Continual-Impression-CCSI.

中文翻译：

CCSI：无数据班级增量学习的持续班级特定印象

在现实世界的临床环境中，传统的基于深度学习的分类方法很难诊断新引入的疾病类型，因为它们需要所有疾病类别的样本进行离线训练。类别增量学习通过调整针对特定疾病类别训练的深度网络来处理新疾病，提供了一种有前景的解决方案。然而，当模型适应新数据时，会发生灾难性遗忘，从而降低早期类别的性能。先前提出的克服这一问题的方法需要永久存储以前的样本，这对医疗保健中的隐私和存储法规提出了潜在的实际问题。为此，我们提出了一种新颖的无数据类增量学习框架，该框架利用学习类的数据合成而不是先前类的数据存储。我们的主要贡献包括为以前无法访问的训练类获取称为持续类特定印象（CCSI）的合成数据，并提出一种在引入新类时有效利用这些数据来更新网络的方法。我们通过对先前类别的训练分类模型的梯度进行数据反转来获得 CCSI，该数据反转是从受医学图像之间共享的共同地标启发的每个类别的平均图像开始，并利用连续归一化层统计作为此像素优化过程中的正则化器。随后，我们通过将合成数据与新类数据相结合来更新网络，并合并一些损失，包括将在合成数据上训练的深度网络推广到真实数据的域内对比损失，以及增加先前类别之间分离的边际损失和新的，以及余弦归一化交叉熵损失，以减轻训练数据中不平衡分布的不利影响。大量实验表明，所提出的框架在四个公共 MedMNIST 数据集和内部超声心动图电影系列上实现了最先进的性能，与基线无数据方法相比，分类精度提高了高达 51%。我们的代码位于 https://github.com/ubc-tea/Continual-Impression-CCSI。

更新日期：2024-06-15

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南