English
Related papers

Related papers: Preserving Task-Relevant Information Under Linear …

200 papers

Natural language processing models tend to learn and encode social biases present in the data. One popular approach for addressing such biases is to eliminate encoded information from the model's representations. However, current methods…

Computation and Language · Computer Science 2023-05-18 Shadi Iskander , Kira Radinsky , Yonatan Belinkov

Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Haiyang Huang , Zhi Chen , Cynthia Rudin

Text-to-image diffusion models have shown unprecedented generative capability, but their ability to produce undesirable concepts (e.g.~pornographic content, sensitive identities, copyrighted styles) poses serious concerns for privacy,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Finn Carter

Text-to-image models exhibit remarkable capabilities in image generation. However, they also pose safety risks of generating harmful content. A key challenge of existing concept erasure methods is the precise removal of target concepts…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Qinqin He , Jiaqi Weng , Jialing Tao , Hui Xue

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

Weakly supervised semantic segmentation has been a subject of increased interest due to the scarcity of fully annotated images. We introduce a new approach for solving weakly supervised semantic segmentation with deep Convolutional Neural…

Computer Vision and Pattern Recognition · Computer Science 2018-07-25 Rania Briq , Michael Moeller , Juergen Gall

Concept erasure in text-to-image diffusion models seeks to remove undesired concepts while preserving overall generative capability. Localized erasure methods aim to restrict edits to the spatial region occupied by the target concept.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Zhuan Shi , Alireza Dehghanpour Farashah , Rik de Vries , Golnoosh Farnadi

While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Ruchika Chavhan , Da Li , Timothy Hospedales

Large-scale diffusion models, known for their impressive image generation capabilities, have raised concerns among researchers regarding social impacts, such as the imitation of copyrighted artistic styles. In response, existing approaches…

Machine Learning · Computer Science 2024-02-12 Mengnan Zhao , Lihe Zhang , Tianhang Zheng , Yuqiu Kong , Baocai Yin

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

We address the problem of concept removal in deep neural networks, aiming to learn representations that do not encode certain specified concepts (e.g., gender etc.) We propose a novel method based on adversarial linear classifiers trained…

Machine Learning · Computer Science 2023-10-10 Yegor Klochkov , Jean-Francois Ton , Ruocheng Guo , Yang Liu , Hang Li

While modern generative models such as diffusion-based architectures have enabled impressive creative capabilities, they also raise important safety and ethical risks. These concerns have led to growing interest in concept erasure, the…

Machine Learning · Computer Science 2026-04-14 Chi Zhang , Jingpu Cheng , Zhixian Wang , Ping Liu

Interpreting individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods often limit the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Vladimir Zaigrajew , Michał Piechota , Gaspar Sekula , Paweł Gelar , Przemysław Biecek

As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preserving model utility has become paramount. Recent work has explored sparse autoencoders (SAEs)…

Computation and Language · Computer Science 2026-04-28 Tomer Ashuach , Dana Arad , Aaron Mueller , Martin Tutek , Yonatan Belinkov

The representation space of neural models for textual data emerges in an unsupervised manner during training. Understanding how those representations encode human-interpretable concepts is a fundamental problem. One prominent approach for…

Machine Learning · Computer Science 2024-09-17 Shauli Ravfogel , Francisco Vargas , Yoav Goldberg , Ryan Cotterell

Delineation of curvilinear structures is an important problem in Computer Vision with multiple practical applications. With the advent of Deep Learning, many current approaches on automatic delineation have focused on finding more powerful…

Computer Vision and Pattern Recognition · Computer Science 2017-12-07 Agata Mosinska , Pablo Marquez-Neila , Mateusz Kozinski , Pascal Fua

Prior work suggests that neural networks tend to learn low-order moments of the data distribution first, before moving on to higher-order correlations. In this work, we derive a novel closed-form concept erasure method, QLEACE, which…

Machine Learning · Computer Science 2025-02-06 Lucia Quirke , Nora Belrose

An important line of research attempts to explain CNN image classifier predictions and intermediate layer representations in terms of human-understandable concepts. Previous work supports that deep representations are linearly separable…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Alexandros Doumanoglou , Stylianos Asteriadis , Dimitrios Zarpalas

Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Saemi Moon , Suhyeon Jun , Seoyeon Lee , Dongwoo Kim

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Machine Learning · Computer Science 2020-12-08 Isaac Lage , Finale Doshi-Velez