CLIPErase：高效遗忘 CLIP 中视觉-文本关联的方法
CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP
AI总结：
本文提出 CLIPErase 方法，通过遗忘、保留和一致性三个模块解耦并选择性遗忘 CLIP 中的视觉-文本关联，在 CIFAR-100 和 Flickr30K 上验证了其在零样本任务中有效遗忘指定关联且不损害保留集性能。
摘要：
机器遗忘（MU）作为一种无需完整重新训练即可从已训练模型中移除特定数据的方法，已获得广泛关注。尽管在文本和图像分类等单模态领域已取得进展，多模态模型中的遗忘问题仍相对未被充分探索。本文针对 CLIP 这一对齐视觉与文本表示的著名多模态模型，解决其遗忘任务中的独特挑战。我们提出 CLIPErase，一种解耦并选择性遗忘视觉与文本关联的新方法，确保遗忘过程不会损害模型性能。CLIPErase 包含三个关键模块：遗忘模块（Forgetting Module），用于破坏遗忘集中的关联；保留模块（Retention Module），用于保持模型在保留集上的性能；一致性模块（Consistency Module），用于维持与原始模型的一致性。在 CIFAR-100 和 Flickr30K 数据集上，针对四个 CLIP 下游任务进行的大量实验表明，CLIPErase 能在多模态样本的零样本任务中有效遗忘指定关联，同时在遗忘后保持模型在保留集上的性能。
英文摘要：
Machine unlearning (MU) has gained significant attention as a means to remove specific data from trained models without requiring a full retraining process. While progress has been made in unimodal domains like text and image classification, unlearning in multimodal models remains relatively underexplored. In this work, we address the unique challenges of unlearning in CLIP, a prominent multimodal model that aligns visual and textual representations. We introduce CLIPErase, a novel approach that disentangles and selectively forgets both visual and textual associations, ensuring that unlearning does not compromise model performance. CLIPErase consists of three key modules: a Forgetting Module that disrupts the associations in the forget set, a Retention Module that preserves performance on the retain set, and a Consistency Module that maintains consistency with the original model. Extensive experiments on the CIFAR-100 and Flickr30K datasets across four CLIP downstream tasks demonstrate that CLIPErase effectively forgets designated associations in zero-shot tasks for multimodal samples, while preserving the model's performance on the retain set after unlearning.
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。
