Saved in:
Bibliographic Details
Main Authors: Han, Feng, Chen, Kai, Gong, Chao, Wei, Zhipeng, Chen, Jingjing, Jiang, Yu-Gang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.01125
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913633021198336
author Han, Feng
Chen, Kai
Gong, Chao
Wei, Zhipeng
Chen, Jingjing
Jiang, Yu-Gang
author_facet Han, Feng
Chen, Kai
Gong, Chao
Wei, Zhipeng
Chen, Jingjing
Jiang, Yu-Gang
contents The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous methods safeguard the models by eliminating inappropriate concepts. Nonetheless, these models alter the parameters of the backbone network and exert considerable influences on the structural (low-frequency) components of the image, which undermines the model's ability to retain non-target concepts. In this work, we propose our Dual encoder Modulation network (DuMo), which achieves precise erasure of inappropriate target concepts with minimum impairment to non-target concepts. In contrast to previous methods, DuMo employs the Eraser with PRior Knowledge (EPR) module which modifies the skip connection features of the U-NET and primarily achieves concept erasure on details (high-frequency) components of the image. To minimize the damage to non-target concepts during erasure, the parameters of the backbone U-NET are frozen and the prior knowledge from the original skip connection features is introduced to the erasure process. Meanwhile, the phenomenon is observed that distinct erasing preferences for the image structure and details are demonstrated by the EPR at different timesteps and layers. Therefore, we adopt a novel Time-Layer MOdulation process (TLMO) that adjusts the erasure scale of EPR module's outputs across different layers and timesteps, automatically balancing the erasure effects and model's generative ability. Our method achieves state-of-the-art performance on Explicit Content Erasure, Cartoon Concept Removal and Artistic Style Erasure, clearly outperforming alternative methods. Code is available at https://github.com/Maplebb/DuMo
format Preprint
id arxiv_https___arxiv_org_abs_2501_01125
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DuMo: Dual Encoder Modulation Network for Precise Concept Erasure
Han, Feng
Chen, Kai
Gong, Chao
Wei, Zhipeng
Chen, Jingjing
Jiang, Yu-Gang
Computer Vision and Pattern Recognition
The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous methods safeguard the models by eliminating inappropriate concepts. Nonetheless, these models alter the parameters of the backbone network and exert considerable influences on the structural (low-frequency) components of the image, which undermines the model's ability to retain non-target concepts. In this work, we propose our Dual encoder Modulation network (DuMo), which achieves precise erasure of inappropriate target concepts with minimum impairment to non-target concepts. In contrast to previous methods, DuMo employs the Eraser with PRior Knowledge (EPR) module which modifies the skip connection features of the U-NET and primarily achieves concept erasure on details (high-frequency) components of the image. To minimize the damage to non-target concepts during erasure, the parameters of the backbone U-NET are frozen and the prior knowledge from the original skip connection features is introduced to the erasure process. Meanwhile, the phenomenon is observed that distinct erasing preferences for the image structure and details are demonstrated by the EPR at different timesteps and layers. Therefore, we adopt a novel Time-Layer MOdulation process (TLMO) that adjusts the erasure scale of EPR module's outputs across different layers and timesteps, automatically balancing the erasure effects and model's generative ability. Our method achieves state-of-the-art performance on Explicit Content Erasure, Cartoon Concept Removal and Artistic Style Erasure, clearly outperforming alternative methods. Code is available at https://github.com/Maplebb/DuMo
title DuMo: Dual Encoder Modulation Network for Precise Concept Erasure
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.01125