Related papers: ICE: Intrinsic Concept Extraction from a Single Im…

Unsupervised Concept Extraction aims to extract concepts from a single image; however, existing methods suffer from the inability to extract composable intrinsic concepts. To address this, this paper introduces a new task called…

Robust concept removal for text-to-image (T2I) and text-to-video (T2V) models is essential for their safe deployment. Existing methods, however, suffer from costly retraining, inference overhead, or vulnerability to adversarial attacks.…

Inner interpretability is a promising field aiming to uncover the internal mechanisms of AI systems through scalable, automated methods. While significant research has been conducted on large language models, limited attention has been paid…

While personalized text-to-image generation has enabled the learning of a single concept from multiple images, a more practical yet challenging scenario involves learning multiple concepts within a single image. However, existing works…

Enabling generative models to decompose visual concepts from a single image is a complex and challenging problem. In this paper, we study a new and challenging task, customized concept decomposition, wherein the objective is to leverage…

A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for…

Text-to-image models encounter safety issues, including concerns related to copyright and Not-Safe-For-Work (NSFW) content. Despite several methods have been proposed for erasing inappropriate concepts from diffusion models, they often…

Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. These concepts, termed as the "implicit concepts", could be unintentionally learned during training and then be…

Text-to-image diffusion models have made significant advancements in generating high-quality, diverse images from text prompts. However, the inherent limitations of textual signals often prevent these models from fully capturing specific…

Text-to-image (TTI) diffusion models have demonstrated impressive results in generating high-resolution images of complex and imaginative scenes. Recent approaches have further extended these methods with personalization techniques that…

In the evolving landscape of text-to-image (T2I) diffusion models, the remarkable capability to generate high-quality images from textual descriptions faces challenges with the potential misuse of reproducing sensitive content. To address…

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,…

Deep convolutional networks have been quite successful at various image classification tasks. The current methods to explain the predictions of a pre-trained model rely on gradient information, often resulting in saliency maps that focus on…

Text-to-image diffusion models (T2I) use a latent representation of a text prompt to guide the image generation process. However, the process by which the encoder produces the text representation is unknown. We propose the Diffusion Lens, a…

Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learned by these models remain an enigma. In this work, we…

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,…

Large text-to-image diffusion models have demonstrated remarkable image synthesis capabilities, but their indiscriminate training on Internet-scale data has led to learned concepts that enable harmful, copyrighted, or otherwise undesirable…

Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications,…

Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts. However, current methods primarily focus on the case of learning a single concept from multiple images…

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…