选择性、可控性和领域无关的预训练CLIP模型去学习：一种无需训练和数据的方法
Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach
AI总结：
本文提出了一种无需训练和数据的CLIP去学习方法，能够实现选择性、可控性和领域无关的模型遗忘，提升模型在不同任务上的适应性与效率。
摘要：
预训练模型如CLIP在跨多样视觉领域的零样本分类任务中展示了令人印象深刻的性能，涵盖自然图像、艺术渲染和抽象表示。然而，现实应用往往需要在不需额外数据或重新训练的情况下移除（或“去学习”）特定对象类别，或影响模型在无关任务上的性能。在本文中，我们提出了一种新颖的无需训练和数据的去学习框架，能够实现三种不同的遗忘范式：（1）在所有领域中全局移除所选对象，（2）领域特定的知识移除（例如消除草图表示同时保留照片识别），（3）在选择性领域中完全移除。通过利用多模态空域，通过协同整合文本提示和从CLIP联合嵌入空间中合成的视觉原型，我们的方法有效地移除了不需要的类别信息，同时保留了剩余知识。这种方法克服了现有重新训练方法的局限性，提供了一种灵活且计算高效的受控模型遗忘解决方案。
英文摘要：
Pretrained models like CLIP have demonstrated impressive zero-shot classification capabilities across diverse visual domains, spanning natural images, artistic renderings, and abstract representations. However, real-world applications often demand the removal (or "unlearning") of specific object classes without requiring additional data or retraining, or affecting the model's performance on unrelated tasks. In this paper, we propose a novel training- and data-free unlearning framework that enables three distinct forgetting paradigms: (1) global unlearning of selected objects across all domains, (2) domain-specific knowledge removal (e.g., eliminating sketch representations while preserving photo recognition), and (3) complete unlearning in selective domains. By leveraging a multimodal nullspace through synergistic integration of text prompts and synthesized visual prototypes derived from CLIP's joint embedding space, our method efficiently removes undesired class information while preserving the remaining knowledge. This approach overcomes the limitations of existing retraining-based methods and offers a flexible and computationally efficient solution for controlled model forgetting.
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。
