Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Ye, Wenqian"'
Autor:
Cao, Xu, Liang, Kaizhao, Liao, Kuei-Da, Gao, Tianren, Ye, Wenqian, Chen, Jintai, Ding, Zhiguang, Cao, Jianguo, Rehg, James M., Sun, Jimeng
Modeling disease progression is crucial for improving the quality and efficacy of clinical diagnosis and prognosis, but it is often hindered by a lack of longitudinal medical image monitoring for individual patients. To address this challenge, we pro
Externí odkaz:
http://arxiv.org/abs/2411.11943
Autor:
Cui, Can, Yang, Zichong, Zhou, Yupeng, Peng, Juntong, Park, Sung-Yeon, Zhang, Cong, Ma, Yunsheng, Cao, Xu, Ye, Wenqian, Feng, Yiheng, Panchal, Jitesh, Li, Lingxi, Chen, Yaobin, Wang, Ziran
Personalized driving refers to an autonomous vehicle's ability to adapt its driving behavior or control strategies to match individual users' preferences and driving styles while maintaining safety and comfort standards. However, existing works eithe
Externí odkaz:
http://arxiv.org/abs/2411.11913
In the aftermath of the COVID-19 pandemic and amid accelerating climate change, emerging infectious diseases, particularly those arising from zoonotic spillover, remain a global threat. Mpox (caused by the monkeypox virus) is a notable example of a z
Externí odkaz:
http://arxiv.org/abs/2411.10888
Few-shot image classifiers are designed to recognize and classify new data with minimal supervision and limited data but often show reliance on spurious correlations between classes and spurious attributes, known as spurious bias. Spurious correlatio
Externí odkaz:
http://arxiv.org/abs/2409.02882
Autor:
Ye, Wenqian, Zheng, Guangtao, Ma, Yunsheng, Cao, Xu, Lai, Bolin, Rehg, James M., Zhang, Aidong
Spurious bias, a tendency to use spurious correlations between non-essential input attributes and target variables for predictions, has revealed a severe robustness pitfall in deep learning models trained on single modality data. Multimodal Large Lan
Externí odkaz:
http://arxiv.org/abs/2406.17126
Spurious correlations are brittle associations between certain attributes of inputs and target variables, such as the correlation between an image background and an object class. Deep image classifiers often leverage them for predictions, leading to
Externí odkaz:
http://arxiv.org/abs/2406.10742
Autor:
Cao, Xu, Lai, Bolin, Ye, Wenqian, Ma, Yunsheng, Heintz, Joerg, Chen, Jintai, Cao, Jianguo, Rehg, James M.
Recently, Multimodal Large Language Models (MLLMs) have shown great promise in language-guided perceptual tasks such as recognition, segmentation, and object detection. However, their effectiveness in addressing visual cognition problems that require
Externí odkaz:
http://arxiv.org/abs/2406.10424
Autor:
Fallahpour, Adibvafa, Alinoori, Mahshid, Ye, Wenqian, Cao, Xu, Afkanpour, Arash, Krishnan, Amrit
Transformers have significantly advanced the modeling of Electronic Health Records (EHR), yet their deployment in real-world healthcare is limited by several key challenges. Firstly, the quadratic computational cost and insufficient context length of
Externí odkaz:
http://arxiv.org/abs/2405.14567
Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious correlations typicall
Externí odkaz:
http://arxiv.org/abs/2405.03649
Machine learning systems are known to be sensitive to spurious correlations between non-essential features of the inputs (e.g., background, texture, and secondary objects) and the corresponding labels. These features and their correlations with the l
Externí odkaz:
http://arxiv.org/abs/2402.12715