Výsledky vyhledávání - "Chen, Zhuowei"

Report

CustomContrast: A Multilevel Contrastive Perspective For Subject-Driven Text-to-Image Customization

Autor: Chen, Nan, Huang, Mengqi, Chen, Zhuowei, Zheng, Yang, Zhang, Lei, Mao, Zhendong

Subject-driven text-to-image (T2I) customization has drawn significant interest in academia and industry. This task enables pre-trained models to generate novel images based on unique subjects. Existing studies adopt a self-reconstructive perspective

Externí odkaz: http://arxiv.org/abs/2409.05606

Zobrazit plný text záznamu

Report

An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification

Autor: Chen, Zhuowei, Wang, Lianxi, Wu, Yuben, Liao, Xinfeng, Tian, Yujia, Zhong, Junyang

Sentiment classification (SC) often suffers from low-resource challenges such as domain-specific contexts, imbalanced label distributions, and few-shot scenarios. The potential of the diffusion language model (LM) for textual data augmentation (DA) r

Externí odkaz: http://arxiv.org/abs/2409.03203

Zobrazit plný text záznamu

Report

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Autor: Guo, Zinan, Wu, Yanze, Chen, Zhuowei, Chen, Lang, He, Qian

We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation. By incorporating a Lightning T2I branch with a standard diffusion one, PuLID introduces both contrastive alignment loss

Externí odkaz: http://arxiv.org/abs/2404.16022

Zobrazit plný text záznamu

Report

DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation

Autor: Chen, Zhuowei, Fang, Shancheng, Liu, Wei, He, Qian, Huang, Mengqi, Zhang, Yongdong, Mao, Zhendong

While large-scale pre-trained text-to-image models can synthesize diverse and high-quality human-centric images, an intractable problem is how to preserve the face identity for conditioned face images. Existing methods either require time-consuming o

Externí odkaz: http://arxiv.org/abs/2307.00300

Zobrazit plný text záznamu

Report

Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization

Autor: Huang, Mengqi, Mao, Zhendong, Chen, Zhuowei, Zhang, Yongdong

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they encode fi

Externí odkaz: http://arxiv.org/abs/2305.11718

Zobrazit plný text záznamu