Výsledky vyhledávání

Report

Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning

Autor: Xu, Huali, Liu, Yongxiang, Liu, Li, Zhi, Shuaifeng, Sun, Shuzhou, Liu, Tianpeng, Cheng, MingMing

Existing cross-domain few-shot learning (CDFSL) methods, which develop source-domain training strategies to enhance model transferability, face challenges with large-scale pre-trained models (LMs) due to inaccessible source data and training strategi

Externí odkaz: http://arxiv.org/abs/2411.10070

Zobrazit plný text záznamu

Report

Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning

Autor: Xu, Huali, Liu, Li, Zhi, Shuaifeng, Fu, Shaojing, Su, Zhuo, Cheng, Ming-Ming, Liu, Yongxiang

Existing Cross-Domain Few-Shot Learning (CDFSL) methods require access to source domain data to train a model in the pre-training phase. However, due to increasing concerns about data privacy and the desire to reduce data transmission and training co

Externí odkaz: http://arxiv.org/abs/2403.01966

Zobrazit plný text záznamu

Report

Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey

Autor: Xu, Huali, Zhi, Shuaifeng, Sun, Shuzhou, Patel, Vishal M., Liu, Li

While deep learning excels in computer vision tasks with abundant labeled data, its performance diminishes significantly in scenarios with limited labeled samples. To address this, Few-shot learning (FSL) enables models to perform the target tasks wi

Externí odkaz: http://arxiv.org/abs/2303.08557

Zobrazit plný text záznamu

Report

Cross-Domain Few-Shot Classification via Inter-Source Stylization

Autor: Xu, Huali, Zhi, Shuaifeng, Liu, Li

Publikováno v: Published at ICIP 2023

The goal of Cross-Domain Few-Shot Classification (CDFSC) is to accurately classify a target dataset with limited labelled data by exploiting the knowledge of a richly labelled auxiliary dataset, despite the differences between the domains of the two

Externí odkaz: http://arxiv.org/abs/2208.08015

Zobrazit plný text záznamu

Report

An Edge Information and Mask Shrinking Based Image Inpainting Approach

Autor: Xu, Huali, Su, Xiangdong, Wang, Meng, Hao, Xiang, Gao, Guanglai

In the image inpainting task, the ability to repair both high-frequency and low-frequency information in the missing regions has a substantial influence on the quality of the restored image. However, existing inpainting methods usually fail to consid

Externí odkaz: http://arxiv.org/abs/2006.06196

Zobrazit plný text záznamu

Report

SNR-Based Teachers-Student Technique for Speech Enhancement

Autor: Hao, Xiang, Su, Xiangdong, Wang, Zhiyu, Zhang, Qiang, Xu, Huali, Gao, Guanglai

It is very challenging for speech enhancement methods to achieves robust performance under both high signal-to-noise ratio (SNR) and low SNR simultaneously. In this paper, we propose a method that integrates an SNR-based teachers-student technique an

Externí odkaz: http://arxiv.org/abs/2005.14441

Zobrazit plný text záznamu