相关论文: Espresso: Robust Concept Filtering in Text-to-Imag…

We observe that the mapping between an image's representation in one model to its representation in another can be learned surprisingly well with just a linear layer, even across diverse models. Building on this observation, we propose…

Measuring perceptual similarity is a key tool in computer vision. In recent years perceptual metrics based on features extracted from neural networks with large and diverse training sets, e.g. CLIP, have become popular. At the same time,…

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,…

Studies have been conducted to prevent specific concepts from being generated from pretrained text-to-image generative models, achieving concept erasure in various ways. However, the performance evaluation of these studies is still largely…

Large-scale vision-and-language models, such as CLIP, are typically trained on web-scale data, which can introduce inappropriate content and lead to the development of unsafe and biased behavior. This, in turn, hampers their applicability…

Large-scale text-to-image diffusion models can generate high-fidelity images with powerful compositional ability. However, these models are typically trained on an enormous amount of Internet data, often containing copyrighted material,…

Adversarial robustness has been conventionally believed as a challenging property to encode for neural networks, requiring plenty of training data. In the recent paradigm of adopting off-the-shelf models, however, access to their training…

Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models while preserving non-target semantics. However, existing methods either rely on costly fine-tuning or apply coarse semantic…

Recent advancements in text-to-image diffusion models have brought them to the public spotlight, becoming widely accessible and embraced by everyday users. However, these models have been shown to generate harmful content such as…

Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content. To mitigate this, concept erasure…

In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet…

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,…

This study investigates the robustness of image classifiers to text-guided corruptions. We utilize diffusion models to edit images to different domains. Unlike other works that use synthetic or hand-picked data for benchmarking, we use…

Motivated by recent advancements in text-to-image diffusion, we study erasure of specific concepts from the model's weights. While Stable Diffusion has shown promise in producing explicit or realistic artwork, it has raised concerns…

Large text-to-image diffusion models have impressive capabilities in generating photorealistic images from text prompts. How to effectively guide or control these powerful models to perform different downstream tasks becomes an important…

Recent advances in vision-language models (VLMs) have shown great promise in connecting images and text, but extending these models to long videos remains challenging due to the rapid growth in token counts. Models that compress videos by…

Automated captioning of photos is a mission that incorporates the difficulties of photo analysis and text generation. One essential feature of captioning is the concept of attention: how to determine what to specify and in which sequence.…

The Stable Diffusion model is a prominent text-to-image generation model that relies on a text prompt as its input, which is encoded using the Contrastive Language-Image Pre-Training (CLIP). However, text prompts have limitations when it…

Text-to-image diffusion models sometimes depict blended concepts in the generated images. One promising use case of this effect would be the nonword-to-image generation task which attempts to generate images intuitively imaginable from a…

We propose a text-to-image generation algorithm based on deep neural networks when text captions for images are unavailable during training. In this work, instead of simply generating pseudo-ground-truth sentences of training images using…