Related papers: Assessing Open-world Forgetting in Generative Imag…
The notion of concept drift refers to the phenomenon that the distribution generating the observed data changes over time. If drift is present, machine learning models can become inaccurate and need adjustment. While there do exist methods…
Lifelong few-shot customization for text-to-image diffusion aims to continually generalize existing models for new tasks with minimal data while preserving old knowledge. Current customization diffusion models excel in few-shot tasks but…
We offer a novel approach to image composition, which integrates multiple input images into a single, coherent image. Rather than concentrating on specific use cases such as appearance editing (image harmonization) or semantic editing…
The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time; as a consequence machine learning models may become inaccurate and need adjustment. While there do exist…
Diffusion models have shown great promise in text-guided image style transfer, but there is a trade-off between style transformation and content preservation due to their stochastic nature. Existing methods require computationally expensive…
Diffusion customization methods have achieved impressive results with only a minimal number of user-provided images. However, existing approaches customize concepts collectively, whereas real-world applications often require sequential…
Generative foundation models like Stable Diffusion comprise a diverse spectrum of knowledge in computer vision with the potential for transfer learning, e.g., via generating data to train student models for downstream tasks. This could…
Image restoration aims to enhance low quality images, producing high quality images that exhibit natural visual characteristics and fine semantic attributes. Recently, the diffusion model has emerged as a powerful technique for image…
Recent advances in generative models have demonstrated remarkable capabilities in producing high-quality images, but their reliance on large-scale unlabeled data has raised significant safety and copyright concerns. Efforts to address these…
Personalizing text-to-image diffusion models involves integrating novel visual concepts from a small set of reference images while retaining the model's original generative capabilities. However, this process often leads to overfitting,…
Data in the real world often has an evolving distribution. Thus, machine learning models trained on such data get outdated over time. This phenomenon is called model drift. Knowledge of this drift serves two purposes: (i) Retain an accurate…
There is strong empirical evidence that the state-of-the-art diffusion modeling paradigm leads to models that memorize the training set, especially when the training set is small. Prior methods to mitigate the memorization problem often…
Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery, a novel training-free, zero-shot framework for concept…
Recent text-to-image customization works have proven successful in generating images of given concepts by fine-tuning diffusion models on a few examples. However, tuning-based methods inherently tend to overfit the concepts, resulting in…
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,…
In concept erasure, a model is modified to selectively prevent it from generating a target concept. Despite the rapid development of new methods, it remains unclear how thoroughly these approaches remove the target concept from the model.…
To what extent does concept erasure eliminate generative capacity in diffusion models? While prior evaluations have primarily focused on measuring concept suppression under specific textual prompts, we explore a complementary and…
Large multimodal models such as Stable Diffusion can generate, detect, and classify new visual concepts after fine-tuning just a single word embedding. Do models learn similar words for the same concepts (i.e. <orange-cat> = orange + cat)?…
Text-to-image (T2I) diffusion models have achieved remarkable success in generating high-quality images from textual prompts. However, their ability to store vast amounts of knowledge raises concerns in scenarios where selective forgetting…
Data stream processing has become a landmark in modern machine learning applications, with concept drifts and novel class appearances posing the primary challenges faced by sophisticated recognition methods. This work proposes an…