APPLE：用于缓解不公平性的潜在嵌入对抗隐私感知扰动
APPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigation
AI总结：
针对医学图像分析中基础模型难以在保留实用性的同时从头训练公平模型的问题，提出无需更新原模型权重、通过添加潜在向量扰动提升分割模型公平性的APPLE方法，实验验证其有效性优于现有方法。
摘要：
确保基于深度学习的分割模型的公平性对健康公平至关重要。目前已有大量研究致力于缓解训练数据集或训练流程中的不公平问题。然而，随着基础模型在医学图像分析中日益普及，在保留实用性的前提下从头训练公平模型难度很大。本文提出一种新方法——潜在嵌入对抗隐私感知扰动（Adversarial Privacy-aware Perturbations on Latent Embedding，APPLE），该方法无需更新原始模型权重，仅通过引入一个小型潜在特征扰动器即可提升已部署分割模型的公平性。通过向潜在向量添加扰动，APPLE对分割模型的潜在向量进行修饰，使得与公平性相关的特征无法传递到分割模型的解码器，同时保留分割模型的架构和参数。在两个分割数据集、五个分割模型（三个类U-Net模型、两个类SAM模型）上开展的实验表明，与多种不公平性缓解方法相比，本文提出的方法更具有效性。
英文摘要：
Ensuring fairness in deep-learning-based segmentors is crucial for health equity. Much effort has been dedicated to mitigating unfairness in the training datasets or procedures. However, with the increasing prevalence of foundation models in medical image analysis, it is hard to train fair models from scratch while preserving utility. In this paper, we propose a novel method, Adversarial Privacy-aware Perturbations on Latent Embedding (APPLE), that can improve the fairness of deployed segmentors by introducing a small latent feature perturber without updating the weights of the original model. By adding perturbation to the latent vector, APPLE decorates the latent vector of segmentors such that no fairness-related features can be passed to the decoder of the segmentors while preserving the architecture and parameters of the segmentor. Experiments on two segmentation datasets and five segmentors (three U-Net-like and two SAM-like) illustrate the effectiveness of our proposed method compared to several unfairness mitigation methods.
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。
