选择性失忆：基于对比子网络擦除的视觉模型类别级遗忘
Selective Amnesia using Contrastive Subnet Erasure for Class Level Unlearning in Vision Models
提出一种免训练、无推理开销的通道级擦除方法，通过对比子网络定位类别相关通道并代数折叠到下一层，为视觉模型的概念级遗忘提供了可直接部署的编辑手段；其跨数据集评估协议也可用于检验遗忘的泛化性。
原文依据 We introduce Contrastive Subnet Erasure (CSE), a training-free, encoder-centric edit that targets a compact set of channels most responsible for the class and attenuates them in a calibrated manner.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们研究预训练视觉模型中的概念级遗忘：移除整个语义类别，使系统不再在未见图像和上下文中识别该物体，而非仅仅遗忘特定的训练样本。先前工作要么采用粗暴的全局投影，要么微调参数，这可能对无关特征造成附带损伤、增加计算量，并且随着遗忘强度增加而变得不稳定。我们引入对比子网络擦除（CSE），这是一种免训练、以编码器为中心的编辑方法，针对对类别最负责的一组紧凑通道，并以校准的方式衰减它们。该修改被代数折叠到后续层中，不产生推理时开销，且任务头保持不变。为了评估遗忘是否能泛化到用于指定类别的数据之外，我们引入跨数据集协议，其中类别在源数据集上定义，性能在来自不同分布且无共享图像的不相交目标数据集上测量。该设置测试模型在物体外观不同或出现在新场景中时是否仍无法识别它，并有助于避免对源数据集中的模式过拟合。在该协议下的CIFAR-10、CIFAR-100和ImageNet上，CSE在单类别和多类别设置中均比现有基线实现了对目标类别更强的遗忘，同时更好地保留了非目标效用。总体而言，CSE为视觉中的类别级遗忘提供了一种简单、稳定且可部署的机制。
英文原文摘要 1592 字符
We study concept-level forgetting in pretrained vision models: removing an entire semantic category so the system no longer recognizes that object in unseen images and contexts, rather than merely forgetting specific training examples. Prior work either applies blunt global projections or fine-tunes parameters, which can introduce collateral damage to unrelated features, add compute, and become unstable as forgetting strength increases. We introduce Contrastive Subnet Erasure (CSE), a training-free, encoder-centric edit that targets a compact set of channels most responsible for the class and attenuates them in a calibrated manner. The modification is algebraically folded into the subsequent layer, yielding no inference-time overhead and leaving task heads unchanged. To evaluate whether forgetting generalizes beyond the data used to specify the class, we introduce a cross dataset protocol in which the class is defined on a source dataset and performance is measured on a disjoint target dataset drawn from a different distribution with no shared images. This setup tests whether the model still fails to recognize the object when it looks different or appears in new scenes, and it helps avoid overfitting to patterns in the source dataset. Across CIFAR 10, CIFAR 100, and ImageNet under this protocol, CSE achieves stronger forgetting of the target class while better preserving non target utility than existing baselines in both single class and multi class settings. Overall, CSE provides a simple, stable, and deployment-ready mechanism for class-level unlearning in vision.