MACE: mass concept erasure in diffusion models

MACE: mass concept erasure in diffusion models

The rapid expansion of large-scale text-to-image diffusion models has raised growing concerns regarding their potential misuse in creating harmful or misleading content. In this paper, we introduce MACE, a finetuning framework for the task of MAss Concept Erasure. This task aims to prevent models fr...

Saved in:

書目詳細資料
Main Authors:	Lu, Shilin, Wang, Zilan, Li, Leyang, Liu, Yanzhu, Kong, Adams Wai Kin
其他作者:	School of Computer Science and Engineering
格式:	Conference or Workshop Item
語言:	English
出版:	2024
主題:	Computer and Information Science Computer vision Generative model Diffusion model Text-to-Image Concept removal Machine unlearning
在線閱讀:	https://hdl.handle.net/10356/180560 https://openaccess.thecvf.com/CVPR2024?day=all
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!

相似書籍

TF-ICON: diffusion-based training-free cross-domain image composition
由: Lu, Shilin, et al.
出版: (2023)

LaVie: high-quality video generation with cascaded latent diffusion models
由: Wang, Yaohui, et al.
出版: (2025)

Coherent visual story generation using diffusion models
由: Jiang, Jiaxi
出版: (2024)

Evolving storytelling: benchmarks and methods for new character customization with diffusion models
由: Wang, Xiyu, et al.
出版: (2024)

Exemplar based image colourization using diffusion models
由: Rahul, George
出版: (2024)

MosaicFusion: diffusion models as data augmenters for large vocabulary instance segmentation
由: Xie, Jiahao, et al.
出版: (2025)

Beyond textual constraints : Learning novel diffusion conditions with fewer examples
由: YU, Yuyang, et al.
出版: (2024)

From noise to information: discriminative tasks based on randomized neural networks and generative tasks based on diffusion models
由: Hu, Minghui
出版: (2024)

A comparative review of latent spaces in latent diffusion model with other generative models
由: Sun Jiaxin
出版: (2024)

In-the-wild image quality assessment with diffusion priors
由: Fu, Honghao
出版: (2024)

Customized image synthesis using diffusion models
由: Fu, Guanqiao
出版: (2024)

FedCIO: efficient exact federated unlearning with clustering, isolation, and one-shot aggregation
由: Qiu, Hongyu, et al.
出版: (2024)

Unlearnable example with face images
由: Peng, Haohang
出版: (2025)

A survey on federated unlearning: challenges, methods, and future directions
由: Liu, Ziyao, et al.
出版: (2025)

Document concept lattice for text understanding and summarization
由: Ye, S., et al.
出版: (2013)

DEEP FACIAL EXPRESSION REPRESENTATION LEARNING: ENHANCING RECOGNITION ACCURACY, PRIVACY PRESERVATION, AND TEXT-TO-3D GENERATION
由: LI MING
出版: (2024)

Decomposing generation networks with structure prediction for recipe generation
由: Wang, Hao, et al.
出版: (2022)

Learning structural representations for recipe generation and food retrieval
由: Wang, Hao, et al.
出版: (2022)

Unsupervised modality adaptation with text-to-Image diffusion models for semantic segmentation
由: XIA, Ruihao, et al.
出版: (2024)

Semantic deep hiding for robust unlearnable examples
由: Meng, Ruohan, et al.
出版: (2024)

Exploiting diffusion prior for real-world image super-resolution
由: Wang, Jianyi, et al.
出版: (2024)

Domain concept handling in automated text categorization
由: Liu, Y., et al.
出版: (2014)

Hi3D: Pursuing high-resolution image-to-3D generation with video diffusion models
由: YANG, Haibo, et al.
出版: (2024)

BRAIN-SCIENCE INSPIRED COMPUTATIONAL MODELS FOR VISION TASKS
由: DUAN JUANYONG
出版: (2019)

Geometric diffusion model for molecular generation
由: Mou, Bingyan
出版: (2024)

Effects of erasures on gossiping algorithms
由: Lee, Qiu Xiang.
出版: (2011)

Diffuse3D: Wide-angle 3D photography via bilateral diffusion
由: JIANG, Yutao, et al.
出版: (2023)

Panoramic image outpainting
由: Teo, Sydney Wen Xuen
出版: (2024)

Data protection with unlearnable examples
由: Ma, Xiaoyu
出版: (2024)

Modeling of diffusion in mechanical alloying
由: YANG CHENG
出版: (2010)

UniD3: unified discrete diffusion for simultaneous vision-language generation
由: Hu, Minghui, et al.
出版: (2023)

Decomposing generation networks with structure prediction for recipe generation
由: WANG, Hao, et al.
出版: (2022)

How words mean: Lexical concepts, cognitive models, and meaning construction
由: Do, Tian Long
出版: (2018)

Spatial and temporal variability of black carbon concentrations during the Metro Manila Aerosol Characterization Experiment, Philippines (MACE)
由: HONEY DAWN, ALAS
出版: (2016)

VR Safari park: A concept-based world building interface using blocks and world tree
由: ICHIKAWA, Shotaro, et al.
出版: (2018)

Image restoration and representation with deep generative models
由: Wang, Yufei
出版: (2025)

CrackDiffusion: a two-stage semantic segmentation framework for pavement crack combining unsupervised and supervised processes
由: Han, Chengjia, et al.
出版: (2024)

Fast semantic diffusion for large-scale context-based image and video annotation
由: JIANG, Yu-Gang, et al.
出版: (2012)

Text extraction from name card images
由: LIN LIN
出版: (2010)

Cocktail: mixing multi-modality controls for text-conditional image generation
由: Hu, Minghui, et al.
出版: (2023)