CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP

• URL: http://arxiv.org/abs/2410.23330v2
• Date: Thu, 05 Jun 2025 23:48:38 GMT
• Title: CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP
• Authors: Tianyu Yang, Lisen Dai, Xiangqi Wang, Minhao Cheng, Yapeng Tian, Xiangliang Zhang,
• Abstract summary: We introduce CLIPErase, a novel approach that disentangles and selectively forgets both visual and textual associations.<n>Experiments on the CIFAR-100 and Flickr30K datasets demonstrate that CLIPErase effectively forgets designated associations in zero-shot tasks for multimodal samples.
• Score: 57.49519639951552
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items [10.98931494075836]
  We introduce a novel self-supervised multi-modal relational item representation learning framework designed to infer substitutable and complementary items.<n>MMSC consists of three main components: (1) a multi-modal item representation learning module that leverages a multi-modal foundational model and learns from item metadata, (2) a self-supervised behavior-based representation learning module that denoises and learns from user behavior data, and (3) a hierarchical representation aggregation mechanism that integrates item representations at both the semantic and task levels.
  arXiv  Detail & Related papers  (2025-07-29T22:38:39Z)
• NOVO: Unlearning-Compliant Vision Transformers [17.810044173023474]
  pname can perform unlearning for future unlearning requests without any fine-tuning over the requested set.<n>Forgetting is achieved by withdrawing keys, making unlearning on-the-fly and avoiding performance degradation.
  arXiv  Detail & Related papers  (2025-07-04T04:12:34Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• Segment Concealed Objects with Incomplete Supervision [63.637733655439334]
  Incompletely-Supervised Concealed Object (ISCOS) involves segmenting objects that seamlessly blend into their surrounding environments.<n>This task remains highly challenging due to the limited supervision provided by the incompletely annotated training data.<n>In this paper, we introduce the first unified method for ISCOS to address these challenges.
  arXiv  Detail & Related papers  (2025-06-10T16:25:15Z)
• Unifying Multimodal Large Language Model Capabilities and Modalities via Model Merging [103.98582374569789]
  Model merging aims to combine multiple expert models into a single model, thereby reducing storage and serving costs.<n>Previous studies have primarily focused on merging visual classification models or Large Language Models (LLMs) for code and math tasks.<n>We introduce the model merging benchmark for MLLMs, which includes multiple tasks such as VQA, Geometry, Chart, OCR, and Grounding, providing both LoRA and full fine-tuning models.
  arXiv  Detail & Related papers  (2025-05-26T12:23:14Z)
• Partially Supervised Unpaired Multi-Modal Learning for Label-Efficient Medical Image Segmentation [53.723234136550055]
  We term the new learning paradigm as Partially Supervised Unpaired Multi-Modal Learning (PSUMML) We propose a novel Decomposed partial class adaptation with snapshot Ensembled Self-Training (DEST) framework for it. Our framework consists of a compact segmentation network with modality specific normalization layers for learning with partially labeled unpaired multi-modal data.
  arXiv  Detail & Related papers  (2025-03-07T07:22:42Z)
• SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection [73.49799596304418]
  This paper introduces a new task called Multi-Modal datasets and Multi-Task Object Detection (M2Det) for remote sensing. It is designed to accurately detect horizontal or oriented objects from any sensor modality. This task poses challenges due to 1) the trade-offs involved in managing multi-modal modelling and 2) the complexities of multi-task optimization.
  arXiv  Detail & Related papers  (2024-12-30T02:47:51Z)
• Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning [13.68867780184022]
  Few-shot learning aims to recognize new concepts using a limited number of visual samples. Our framework incorporates both the abstract class semantics and the concrete class entities extracted from Large Language Models (LLMs) For the challenging one-shot setting, our approach, utilizing the ResNet-12 backbone, achieves an average improvement of 1.95% over the second-best competitor.
  arXiv  Detail & Related papers  (2024-08-22T15:10:20Z)
• Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning [45.25602203155762]
  Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. A major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression. We propose a novel model-agnostic Multistage Contrastive Learning framework.
  arXiv  Detail & Related papers  (2024-02-19T04:13:33Z)
• SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models [71.78800549517298]
  Continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the selection module to pick out the corresponding one for the testing input. We propose a novel Shared Attention Framework (SAPT) to align the PET learning and selection via the Shared Attentive Learning & Selection module.
  arXiv  Detail & Related papers  (2024-01-16T11:45:03Z)
• CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts [11.752632557524969]
  We propose contrastive learning with data augmentation to disentangle content features from the original representations. Our experiments across diverse datasets demonstrate significant improvements in zero-shot and few-shot classification tasks.
  arXiv  Detail & Related papers  (2023-11-28T03:00:59Z)
• MultiDelete for Multimodal Machine Unlearning [14.755831733659699]
  MultiDelete is designed to decouple associations between unimodal data points during unlearning. It can maintain the multimodal and unimodal knowledge of the original model post unlearning. It can provide better protection to unlearned data against adversarial attacks.
  arXiv  Detail & Related papers  (2023-11-18T08:30:38Z)
• RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
  This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal. We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
  arXiv  Detail & Related papers  (2023-07-03T13:21:58Z)
• Multi-View Class Incremental Learning [57.14644913531313]
  Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance. This paper investigates a novel paradigm called multi-view class incremental learning (MVCIL), where a single model incrementally classifies new classes from a continual stream of views.
  arXiv  Detail & Related papers  (2023-06-16T08:13:41Z)
• Learning Customized Visual Models with Retrieval-Augmented Knowledge [104.05456849611895]
  We propose REACT, a framework to acquire the relevant web knowledge to build customized visual models for target domains. We retrieve the most relevant image-text pairs from the web-scale database as external knowledge, and propose to customize the model by only training new modualized blocks while freezing all the original weights. The effectiveness of REACT is demonstrated via extensive experiments on classification, retrieval, detection and segmentation tasks, including zero, few, and full-shot settings.
  arXiv  Detail & Related papers  (2023-01-17T18:59:06Z)
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
  Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
  arXiv  Detail & Related papers  (2023-01-17T12:42:58Z)
• Personalizing Pre-trained Models [23.145974171912414]
  We consider how upstream pretrained models can be leveraged for downstream few-shot, multilabel, and continual learning tasks. Our model CLIPPER (CLIP PERsonalized) uses image representations from CLIP, a large-scale image representation learning model trained using weak natural language supervision.
  arXiv  Detail & Related papers  (2021-06-02T22:58:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.