English
Related papers

Related papers: Sparse Autoencoder as a Zero-Shot Classifier for C…

200 papers

Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Jie Ren , Kangrui Chen , Yingqian Cui , Shenglai Zeng , Hui Liu , Yue Xing , Jiliang Tang , Lingjuan Lyu

Concept-based Explainable Artificial Intelligence (XAI) interprets deep learning models using human-understandable visual features (e.g., textures or object parts) by linking internal representations to class predictions, thereby bridging…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Giacomo Astolfi , Matteo Bianchi , Riccardo Campi , Antonio De Santis , Marco Brambilla

Text-to-Image models such as Stable Diffusion have shown impressive image generation synthesis, thanks to the utilization of large-scale datasets. However, these datasets may contain sexually explicit, copyrighted, or undesirable content,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Seunghoo Hong , Juhun Lee , Simon S. Woo

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su

Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to implicit biases embedded in large-scale training datasets. Existing concept erasure methods,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Jun Li , Lizhi Xiong , Ziqiang Li , Weiwei Jiang , Zhangjie Fu , Yong Li , Guo-Sen Xie

Diffusion models have become the go-to method for text-to-image generation, producing high-quality images from pure noise. However, the inner workings of diffusion models is still largely a mystery due to their black-box nature and complex,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Berk Tinaz , Zalan Fabian , Mahdi Soltanolkotabi

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to…

Machine Learning · Computer Science 2026-05-13 Hyeonjin Kim , Hangyeol Jung , Heechan Yun , Sungjun Yun , Dong-Jun Han

Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. To perform reliable concept erasure, the properties of robustness and locality are desirable.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Chi-Pin Huang , Kai-Po Chang , Chung-Ting Tsai , Yung-Hsuan Lai , Fu-En Yang , Yu-Chiang Frank Wang

Reliable evaluation of modern zero-shot text-to-speech (TTS) models remains challenging. Subjective tests are costly and hard to reproduce, while objective metrics often saturate, failing to distinguish SOTA systems. To address this, we…

Sound · Computer Science 2026-03-26 Shengfan Shen , Di Wu , Xingchen Song , Dinghao Zhou , Liumeng Xue , Meng Meng , Jian Luan , Shuai Wang

Removing unwanted concepts from large-scale text-to-image (T2I) diffusion models while maintaining their overall generative quality remains an open challenge. This difficulty is especially pronounced in emerging paradigms, such as Stable…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Daiheng Gao , Shilin Lu , Shaw Walters , Wenbo Zhou , Jiaming Chu , Jie Zhang , Bang Zhang , Mengxi Jia , Jian Zhao , Zhaoxin Fan , Weiming Zhang

Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images. To mitigate risk, concept erasure methods are studied to facilitate the model to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Ruidong Chen , Honglin Guo , Lanjun Wang , Chenyu Zhang , Weizhi Nie , An-An Liu

The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable proficiency in generating high-definition images matching textual…

Computer Vision and Pattern Recognition · Computer Science 2023-12-25 Qiang Wan , Zilong Huang , Bingyi Kang , Jiashi Feng , Li Zhang

The inherent ambiguity in defining visual concepts poses significant challenges for modern generative models, such as the diffusion-based Text-to-Image (T2I) models, in accurately learning concepts from a single image. Existing methods lack…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Fernando Julio Cendra , Kai Han

Recent text-to-image (T2I) diffusion and flow-matching models can produce highly realistic images from natural language prompts. In practical scenarios, T2I systems are often run in a ``generate--then--select'' mode: many seeds are sampled…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Huanlei Guo , Hongxin Wei , Bingyi Jing

Recent advances in text-to-video (T2V) diffusion models have significantly enhanced the quality of generated videos. However, their capability to produce explicit or harmful content introduces new challenges related to misuse and potential…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Xiaoyu Ye , Songjie Cheng , Yongtao Wang , Yajiao Xiong , Yishen Li

Sparse Autoencoders (SAEs) are an interpretability technique aimed at decomposing neural network activations into interpretable units. However, a major bottleneck for SAE development has been the lack of high-quality performance metrics,…

Machine Learning · Computer Science 2024-12-02 Adam Karvonen , Can Rager , Samuel Marks , Neel Nanda

Text-to-image diffusion models suffer from the risk of generating outdated, copyrighted, incorrect, and biased content. While previous methods have mitigated the issues on a small scale, it is essential to handle them simultaneously in…

Computer Vision and Pattern Recognition · Computer Science 2024-10-14 Tianwei Xiong , Yue Wu , Enze Xie , Yue Wu , Zhenguo Li , Xihui Liu

Concept erasure techniques for text-to-video (T2V) diffusion models report substantial suppression of sensitive content, yet current evaluation is limited to checking whether the target concept is absent from generated frames, treating…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yiwei Xie , Zheng Zhang , Ping Liu

Text-guided diffusion models have revolutionized generative tasks by producing high-fidelity content from text descriptions. They have also enabled an editing paradigm where concepts can be replaced through text conditioning (e.g., a dog to…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Chao Huang , Susan Liang , Yunlong Tang , Yapeng Tian , Anurag Kumar , Chenliang Xu

Recent success of text-to-image (T2I) generation and its increasing practical applications, enabled by diffusion models, require urgent consideration of erasing unwanted concepts, e.g., copyrighted, offensive, and unsafe ones, from the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Yuan Wang , Ouxiang Li , Tingting Mu , Yanbin Hao , Kuien Liu , Xiang Wang , Xiangnan He