Related papers: Content-Style Decoupling for Unsupervised Makeup T…

Narrowly finetuned language models memorize implanted content verbatim, but auditing what a deployed model has been taught, without access to its weights or training data, remains an open challenge. Recent work shows that activation…

Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain performance. We argue this forgetting arises because fine-tuning…

High quality facial image editing is a challenging problem in the movie post-production industry, requiring a high degree of control and identity preservation. Previous works that attempt to tackle this problem may suffer from the…

Recent advances in tuning-free personalized image generation based on diffusion models are impressive. However, to improve subject fidelity, existing methods either retrain the diffusion model or infuse it with dense visual embeddings, both…

Medical Image-to-image translation is a key task in computer vision and generative artificial intelligence, and it is highly applicable to medical image analysis. GAN-based methods are the mainstream image translation methods, but they…

Regional facial image synthesis conditioned on semantic mask has achieved great success using generative adversarial networks. However, the appearance of different regions may be inconsistent with each other when conducting regional image…

Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning. It has reached the…

We present a method to generate speech from input text and a style vector that is extracted from a reference speech signal in an unsupervised manner, i.e., no style annotation, such as speaker information, is required. Existing unsupervised…

Traditional data masking techniques such as anonymization cannot achieve the expected privacy protection while ensuring data utility for privacy-preserving machine learning. Synthetic data plays an increasingly important role as it…

This paper proposes a training data augmentation pipeline that combines synthetic image data with neural style transfer in order to address the vulnerability of deep vision models to common corruptions. We show that although applying style…

Photorealistic style transfer aims to transfer the artistic style of an image onto an input image or video while keeping photorealism. In this paper, we think it's the summary statistics matching scheme in existing algorithms that leads to…

In this paper, we propose a novel and efficient CNN-based framework that leverages local and global context information for image denoising. Due to the limitations of convolution itself, the CNN-based method is generally unable to construct…

Recent rapid advancement of generative models has significantly improved the fidelity and accessibility of AI-generated synthetic images. While enabling various innovative applications, the unprecedented realism of these synthetics makes…

Style transfer methods have achieved significant success in recent years with the use of convolutional neural networks. However, many of these methods concentrate on artistic style transfer with few constraints on the output image…

Effective cross-lingual transfer remains a critical challenge in scaling the benefits of large language models from high-resource to low-resource languages. Towards this goal, prior studies have explored many approaches to combine task…

Synthesizing high-quality images from low-field MRI holds significant potential. Low-field MRI is cheaper, more accessible, and safer, but suffers from low resolution and poor signal-to-noise ratio. This synthesis process can reduce…

One major impediment in rapidly deploying object detection models for industrial applications is the lack of large annotated datasets. We currently have presented the Sacked Carton Dataset(SCD) that contains carton images from three…

Diffusion models have demonstrated significant potential in producing high-quality images in medical image translation to aid disease diagnosis, localization, and treatment. Nevertheless, current diffusion models have limited success in…

Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face significant…

Implicit degradation modeling-based blind super-resolution (SR) has attracted more increasing attention in the community due to its excellent generalization to complex degradation scenarios and wide application range. How to extract more…