Zobrazeno 1 - 10
of 202
pro vyhledávání: '"Meng, Gaofeng"'
The advent of pre-trained vision-language foundation models has revolutionized the field of zero/few-shot (i.e., low-shot) image recognition. The key challenge to address under the condition of limited training data is how to fine-tune pre-trained vi
Externí odkaz:
http://arxiv.org/abs/2410.11686
Cache-based approaches stand out as both effective and efficient for adapting vision-language models (VLMs). Nonetheless, the existing cache model overlooks three crucial aspects. 1) Pre-trained VLMs are mainly optimized for image-text similarity, ne
Externí odkaz:
http://arxiv.org/abs/2410.08895
Autor:
Geng, Yimeng, Meng, Gaofeng, Chen, Mingcong, Cao, Guanglin, Zhao, Mingyang, Zhao, Jianbo, Liu, Hongbin
Accurate identification of arteries and veins in ultrasound images is crucial for vascular examinations and interventions in robotics-assisted surgeries. However, current methods for ultrasound vessel segmentation face challenges in distinguishing be
Externí odkaz:
http://arxiv.org/abs/2407.21394
In this study, we introduce a new problem raised by social media and photojournalism, named Image Address Localization (IAL), which aims to predict the readable textual address where an image was taken. Existing two-stage approaches involve predictin
Externí odkaz:
http://arxiv.org/abs/2407.08156
This paper presents a novel non-rigid point set registration method that is inspired by unsupervised clustering analysis. Unlike previous approaches that treat the source and target point sets as separate entities, we develop a holistic framework whe
Externí odkaz:
http://arxiv.org/abs/2406.18817
Recently, live streaming platforms have gained immense popularity. Traditional video highlight detection mainly focuses on visual features and utilizes both past and future content for prediction. However, live streaming requires models to infer with
Externí odkaz:
http://arxiv.org/abs/2407.12002
Autor:
Deng, Jiaxin, Wang, Shiyao, Wang, Yuchen, Qi, Jiansong, Zhao, Liqin, Zhou, Guorui, Meng, Gaofeng
Live streaming services are becoming increasingly popular due to real-time interactions and entertainment. Viewers can chat and send comments or virtual gifts to express their preferences for the streamers. Accurately modeling the gifting interaction
Externí odkaz:
http://arxiv.org/abs/2407.00056
In this work, we present Xwin-LM, a comprehensive suite of alignment methodologies for large language models (LLMs). This suite encompasses several key techniques, including supervised finetuning (SFT), reward modeling (RM), rejection sampling finetu
Externí odkaz:
http://arxiv.org/abs/2405.20335
Autor:
Zhang, Chenghao, Meng, Gaofeng, Fan, Bin, Tian, Kun, Zhang, Zhaoxiang, Xiang, Shiming, Pan, Chunhong
The remarkable performance of recent stereo depth estimation models benefits from the successful use of convolutional neural networks to regress dense disparity. Akin to most tasks, this needs gathering training data that covers a number of heterogen
Externí odkaz:
http://arxiv.org/abs/2404.00360
Autor:
Ni, Bolin, Zhao, Hongbo, Zhang, Chenghao, Hu, Ke, Meng, Gaofeng, Zhang, Zhaoxiang, Xiang, Shiming
Continual learning (CL) aims to empower models to learn new tasks without forgetting previously acquired knowledge. Most prior works concentrate on the techniques of architectures, replay data, regularization, \etc. However, the category name of each
Externí odkaz:
http://arxiv.org/abs/2403.16124