Zobrazeno 1 - 10
of 4 033
pro vyhledávání: '"YE, Mao"'
Few-shot Semantic Segmentation(FSS)aim to adapt a pre-trained model to new classes with as few as a single labeled training sample per class. The existing prototypical work used in natural image scenarios biasedly focus on capturing foreground's disc
Externí odkaz:
http://arxiv.org/abs/2412.02983
Autor:
Su, Wenxin, Tang, Song, Liu, Xiaofeng, Yi, Xiaojing, Ye, Mao, Zu, Chunxiao, Li, Jiahao, Zhu, Xiatian
Domain shift (the difference between source and target domains) poses a significant challenge in clinical applications, e.g., Diabetic Retinopathy (DR) grading. Despite considering certain clinical requirements, like source data privacy, conventional
Externí odkaz:
http://arxiv.org/abs/2412.01203
Autor:
Li, Hui, Xu, Mingwang, Zhan, Yun, Mu, Shan, Li, Jiaye, Cheng, Kaihui, Chen, Yuxuan, Chen, Tan, Ye, Mao, Wang, Jingdong, Zhu, Siyu
Recent advancements in visual generation technologies have markedly increased the scale and availability of video datasets, which are crucial for training effective video generation models. However, a significant lack of high-quality, human-centric v
Externí odkaz:
http://arxiv.org/abs/2412.00115
Autor:
Zhang, Hongyun, Li, Qian, Scheer, Michael G., Wang, Renqi, Tuo, Chuyi, Zou, Nianlong, Chen, Wanying, Li, Jiaheng, Cai, Xuanxi, Bao, Changhua, Li, Ming-Rui, Deng, Ke, Watanabe, Kenji, Taniguchi, Takashi, Ye, Mao, Tang, Peizhe, Xu, Yong, Yu, Pu, Avila, Jose, Dudin, Pavel, Denlinger, Jonathan D., Yao, Hong, Lian, Biao, Duan, Wenhui, Zhou, Shuyun
Publikováno v:
PNAS 121, (43) e2410714121 (2024)
Flat bands and nontrivial topological physics are two important topics of condensed matter physics. With a unique stacking configuration analogous to the Su-Schrieffer-Heeger (SSH) model, rhombohedral graphite (RG) is a potential candidate for realiz
Externí odkaz:
http://arxiv.org/abs/2411.07906
We propose a novel hybrid calibration-free method FreeCap to accurately capture global multi-person motions in open environments. Our system combines a single LiDAR with expandable moving cameras, allowing for flexible and precise motion estimation i
Externí odkaz:
http://arxiv.org/abs/2411.04469
Deep visual Simultaneous Localization and Mapping (SLAM) techniques, e.g., DROID, have made significant advancements by leveraging deep visual odometry on dense flow fields. In general, they heavily rely on global visual similarity matching. However,
Externí odkaz:
http://arxiv.org/abs/2410.23231
Whole Slide Image (WSI) classification has very significant applications in clinical pathology, e.g., tumor identification and cancer diagnosis. Currently, most research attention is focused on Multiple Instance Learning (MIL) using static datasets.
Externí odkaz:
http://arxiv.org/abs/2410.10573
Autor:
Yang, Jiuzheng, Tang, Song, Zhang, Yangkuiyi, Li, Shuaifeng, Ye, Mao, Zhang, Jianwei, Zhu, Xiatian
Source-Free domain adaptive Object Detection (SFOD) aims to transfer a detector (pre-trained on source domain) to new unlabelled target domains. Current SFOD methods typically follow the Mean Teacher framework, where weak-to-strong augmentation provi
Externí odkaz:
http://arxiv.org/abs/2410.05557
Autor:
Yang, Yunhao, Hu, Yuxin, Ye, Mao, Zhang, Zaiwei, Lu, Zhichao, Xu, Yi, Topcu, Ufuk, Snyder, Ben
Multimodal foundation models offer promising advancements for enhancing driving perception systems, but their high computational and financial costs pose challenges. We develop a method that leverages foundation models to refine predictions from exis
Externí odkaz:
http://arxiv.org/abs/2410.01144
A fundamental challenge in continual learning is to balance the trade-off between learning new tasks and remembering the previously acquired knowledge. Gradient Episodic Memory (GEM) achieves this balance by utilizing a subset of past training sample
Externí odkaz:
http://arxiv.org/abs/2410.00868