Zobrazeno 1 - 10
of 3 376
pro vyhledávání: '"Xia, PENG"'
The advancement of Large Vision-Language Models (LVLMs) has propelled their application in the medical field. However, Medical LVLMs (Med-LVLMs) encounter factuality challenges due to modality misalignment, where the models prioritize textual knowled
Externí odkaz:
http://arxiv.org/abs/2412.06141
Autor:
Xia, Peng, Zhu, Kangyu, Li, Haoran, Wang, Tianze, Shi, Weijia, Wang, Sheng, Zhang, Linjun, Zou, James, Yao, Huaxiu
Artificial Intelligence (AI) has demonstrated significant potential in healthcare, particularly in disease diagnosis and treatment planning. Recent progress in Medical Large Vision-Language Models (Med-LVLMs) has opened up new possibilities for inter
Externí odkaz:
http://arxiv.org/abs/2410.13085
Autor:
Xia, Peng, Han, Siwei, Qiu, Shi, Zhou, Yiyang, Wang, Zhaoyang, Zheng, Wenhao, Chen, Zhaorun, Cui, Chenhang, Ding, Mingyu, Li, Linjie, Wang, Lijuan, Yao, Huaxiu
Interleaved multimodal comprehension and generation, enabling models to produce and interpret both images and text in arbitrary sequences, have become a pivotal area in multimodal learning. Despite significant advancements, the evaluation of this cap
Externí odkaz:
http://arxiv.org/abs/2410.10139
Autor:
Xia, Peng, Zhu, Kangyu, Li, Haoran, Zhu, Hongtu, Li, Yun, Li, Gang, Zhang, Linjun, Yao, Huaxiu
The recent emergence of Medical Large Vision Language Models (Med-LVLMs) has enhanced medical diagnosis. However, current Med-LVLMs frequently encounter factual issues, often generating responses that do not align with established medical facts. Retr
Externí odkaz:
http://arxiv.org/abs/2407.05131
TP-DRSeg: Improving Diabetic Retinopathy Lesion Segmentation with Explicit Text-Prompts Assisted SAM
Recent advances in large foundation models, such as the Segment Anything Model (SAM), have demonstrated considerable promise across various tasks. Despite their progress, these models still encounter challenges in specialized medical image analysis,
Externí odkaz:
http://arxiv.org/abs/2406.15764
Autor:
Hu, Ming, Xia, Peng, Wang, Lin, Yan, Siyuan, Tang, Feilong, Xu, Zhongxing, Luo, Yimin, Song, Kaimin, Leitner, Jurgen, Cheng, Xuelian, Cheng, Jun, Liu, Chi, Zhou, Kaijing, Ge, Zongyuan
Surgical scene perception via videos is critical for advancing robotic surgery, telesurgery, and AI-assisted surgery, particularly in ophthalmology. However, the scarcity of diverse and richly annotated video datasets has hindered the development of
Externí odkaz:
http://arxiv.org/abs/2406.07471
Autor:
Xia, Peng, Hu, Ming, Tang, Feilong, Li, Wenxue, Zheng, Wenhao, Ju, Lie, Duan, Peibo, Yao, Huaxiu, Ge, Zongyuan
Diabetic Retinopathy (DR), induced by diabetes, poses a significant risk of visual impairment. Accurate and effective grading of DR aids in the treatment of this condition. Yet existing models experience notable performance degradation on unseen doma
Externí odkaz:
http://arxiv.org/abs/2406.06384
Autor:
Xia, Peng, Chen, Ze, Tian, Juanxi, Gong, Yangrui, Hou, Ruibo, Xu, Yue, Wu, Zhenbang, Fan, Zhiyuan, Zhou, Yiyang, Zhu, Kangyu, Zheng, Wenhao, Wang, Zhaoyang, Wang, Xiao, Zhang, Xuchao, Bansal, Chetan, Niethammer, Marc, Huang, Junzhou, Zhu, Hongtu, Li, Yun, Sun, Jimeng, Ge, Zongyuan, Li, Gang, Zou, James, Yao, Huaxiu
Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustwo
Externí odkaz:
http://arxiv.org/abs/2406.06007
Autor:
Hu, Ming, Yan, Siyuan, Xia, Peng, Tang, Feilong, Li, Wenxue, Duan, Peibo, Zhang, Lin, Ge, Zongyuan
Deep learning-based diagnostic systems have demonstrated potential in skin disease diagnosis. However, their performance can easily degrade on test domains due to distribution shifts caused by input-level corruptions, such as imaging equipment variab
Externí odkaz:
http://arxiv.org/abs/2405.11289
Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in complex sc
Externí odkaz:
http://arxiv.org/abs/2311.14064