Related papers: CleanStyle: Plug-and-Play Style Conditioning Purif…

Due to the development of deep learning-based denoisers, the plug-and-play strategy has achieved great success in image restoration problems. However, existing plug-and-play image restoration methods are designed for non-blind Gaussian…

In this paper, we introduce UnFuSeD, a novel approach to leverage self-supervised learning and reduce the need for large amounts of labeled data for audio classification. Unlike prior works, which directly fine-tune a self-supervised…

Few-shot Chinese font generation aims to synthesize new characters in a target style using only a handful of reference images. Achieving accurate content rendering and faithful style transfer requires effective disentanglement between…

Representing artistic style is challenging due to its deep entanglement with semantic content. We propose StyleDecoupler, an information-theoretic framework that leverages a key insight: multi-modal vision models encode both style and…

Large-scale text-to-image generative models have been a revolutionary breakthrough in the evolution of generative AI, allowing us to synthesize diverse images that convey highly complex visual concepts. However, a pivotal challenge in…

Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale. Detoxification is therefore important for safety and user trust, particularly when we want to reduce harmful…

Artistic image stylization aims to render the content provided by text or image with the target style, where content and style decoupling is the key to achieve satisfactory results. However, current methods for content and style…

Diffusion models can unintentionally reproduce training examples, raising privacy and copyright concerns as these systems are increasingly deployed at scale. Existing inference-time mitigation methods typically manipulate classifier-free…

The widespread deployment of text-to-image models is challenged by their potential to generate harmful content. While existing safety methods, such as prompt rewriting or model fine-tuning, provide valuable interventions, they often…

The performance of deep learning models for music source separation heavily depends on training data quality. However, datasets are often corrupted by difficult-to-detect artifacts such as audio bleeding and label noise. Since the type and…

Addressing the challenge of data scarcity in industrial domains, transfer learning emerges as a pivotal paradigm. This work introduces Style Filter, a tailored methodology for industrial contexts. By selectively filtering source domain data…

Text-to-image diffusion models have revolutionized image synthesis and editing, but precise control over stylistic attributes remains a challenge, often causing unintended content modifications. We propose an approach for fine-grained…

The rise of text-to-video generation models has raised growing concerns over content authenticity, copyright protection, and malicious misuse. Watermarking serves as an effective mechanism for regulating such AI-generated content, where…

Text-to-image (T2I) models have recently gained widespread adoption. This has spurred concerns about safeguarding intellectual property rights and an increasing demand for mechanisms that prevent the generation of specific artistic styles.…

Deep learning has achieved remarkable progress for visual recognition on large-scale balanced datasets but still performs poorly on real-world long-tailed data. Previous methods often adopt class re-balanced training strategies to…

Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…

We build on the Visual Autoregressive Modeling (VAR) framework and formulate style transfer as conditional discrete sequence modeling in a learned latent space. Images are decomposed into multi-scale representations and tokenized into…

Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…

Diffusion models have shown tremendous results in image generation. However, due to the iterative nature of the diffusion process and its reliance on classifier-free guidance, inference times are slow. In this paper, we propose a new…

Learning with noisy labels (LNL) has been extensively studied, with existing approaches typically following a framework that alternates between clean sample selection and semi-supervised learning (SSL). However, this approach has a…