Zobrazeno 1 - 10
of 531
pro vyhledávání: '"Zhou, Joey"'
Autor:
Zhang, Qingyang, Feng, Qiuxuan, Zhou, Joey Tianyi, Bian, Yatao, Hu, Qinghua, Zhang, Changqing
Out-of-distribution (OOD) detection is essential for model trustworthiness which aims to sensitively identify semantic OOD samples and robustly generalize for covariate-shifted OOD samples. However, we discover that the superior OOD detection perform
Externí odkaz:
http://arxiv.org/abs/2410.11576
The sharp increase in data-related expenses has motivated research into condensing datasets while retaining the most informative features. Dataset distillation has thus recently come to the fore. This paradigm generates synthetic dataset that are rep
Externí odkaz:
http://arxiv.org/abs/2409.17612
Dataset distillation has emerged as a technique aiming to condense informative features from large, natural datasets into a compact and synthetic form. While recent advancements have refined this technique, its performance is bottlenecked by the prev
Externí odkaz:
http://arxiv.org/abs/2408.06927
Generating fair and accurate predictions plays a pivotal role in deploying large language models (LLMs) in the real world. However, existing debiasing methods inevitably generate unfair or incorrect predictions as they are designed and evaluated to a
Externí odkaz:
http://arxiv.org/abs/2408.11843
This survey addresses the critical challenge of deepfake detection amidst the rapid advancements in artificial intelligence. As AI-generated media, including video, audio and text, become more realistic, the risk of misuse to spread misinformation an
Externí odkaz:
http://arxiv.org/abs/2406.06965
In the medical field, managing high-dimensional massive medical imaging data and performing reliable medical analysis from it is a critical challenge, especially in resource-limited environments such as remote medical facilities and mobile devices. T
Externí odkaz:
http://arxiv.org/abs/2406.05677
Autor:
He, Yang, Zhou, Joey Tianyi
Hierarchical vision transformers (ViTs) have two advantages over conventional ViTs. First, hierarchical ViTs achieve linear computational complexity with respect to image size by local self-attention. Second, hierarchical ViTs create hierarchical fea
Externí odkaz:
http://arxiv.org/abs/2404.13648
Autor:
Xie, Xiaopeng, Yan, Ming, Zhou, Xiwen, Zhao, Chenlong, Wang, Suli, Zhang, Yong, Zhou, Joey Tianyi
Prompt-based learning paradigm has demonstrated remarkable efficacy in enhancing the adaptability of pretrained language models (PLMs), particularly in few-shot scenarios. However, this learning paradigm has been shown to be vulnerable to backdoor at
Externí odkaz:
http://arxiv.org/abs/2404.00461
Stance detection is the view towards a specific target by a given context (\textit{e.g.} tweets, commercial reviews). Target-related knowledge is often needed to assist stance detection models in understanding the target well and making detection cor
Externí odkaz:
http://arxiv.org/abs/2403.19219
Autor:
Yan, Tingbing, Zeng, Wenzheng, Xiao, Yang, Tong, Xingyu, Tan, Bo, Fang, Zhiwen, Cao, Zhiguo, Zhou, Joey Tianyi
Most existing one-shot skeleton-based action recognition focuses on raw low-level information (e.g., joint location), and may suffer from local information loss and low generalization ability. To alleviate these, we propose to leverage text descripti
Externí odkaz:
http://arxiv.org/abs/2403.10082