Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mishra, Ashish, Nayak, Gyanaranjan, Kumar, Tarun, Shah, Arpit, Bhattacharya, Suparna, Foltin, Martin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911322065600512
author Mishra, Ashish
Nayak, Gyanaranjan
Kumar, Tarun
Shah, Arpit
Bhattacharya, Suparna
Foltin, Martin
author_facet Mishra, Ashish
Nayak, Gyanaranjan
Kumar, Tarun
Shah, Arpit
Bhattacharya, Suparna
Foltin, Martin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14113
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach
Mishra, Ashish
Nayak, Gyanaranjan
Kumar, Tarun
Shah, Arpit
Bhattacharya, Suparna
Foltin, Martin
Computer Vision and Pattern Recognition
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.
title Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.14113