Zobrazeno 1 - 10
of 226
pro vyhledávání: '"Xing, Yifan"'
Autor:
Kim, Youngeun, Fang, Jun, Zhang, Qin, Cai, Zhaowei, Shen, Yantao, Duggal, Rahul, Raychaudhuri, Dripta S., Tu, Zhuowen, Xing, Yifan, Dabeer, Onkar
The open world is inherently dynamic, characterized by ever-evolving concepts and distributions. Continual learning (CL) in this dynamic open-world environment presents a significant challenge in effectively generalizing to unseen test-time classes.
Externí odkaz:
http://arxiv.org/abs/2409.05312
Autor:
Ming, Yuhang, Yang, Xingrui, Wang, Weihan, Chen, Zheng, Feng, Jinglun, Xing, Yifan, Zhang, Guofeng
Neural Radiance Fields (NeRF) have emerged as a powerful paradigm for 3D scene representation, offering high-fidelity renderings and reconstructions from a set of sparse and unstructured sensor data. In the context of autonomous robotics, where perce
Externí odkaz:
http://arxiv.org/abs/2405.05526
Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures across test classes and data distributions. When combined with the common practice of using
Externí odkaz:
http://arxiv.org/abs/2307.04047
Autor:
Zhang, Qin, An, Dongsheng, Xiao, Tianjun, He, Tong, Tang, Qingming, Wu, Ying Nian, Tighe, Joseph, Xing, Yifan, Soatto, Stefano
In deep metric learning for visual recognition, the calibration of distance thresholds is crucial for achieving desired model performance in the true positive rates (TPR) or true negative rates (TNR). However, calibrating this threshold presents chal
Externí odkaz:
http://arxiv.org/abs/2305.12039
Tactile pose estimation and tactile servoing are fundamental capabilities of robot touch. Reliable and precise pose estimation can be provided by applying deep learning models to high-resolution optical tactile sensors. Given the recent successes of
Externí odkaz:
http://arxiv.org/abs/2303.02708
This paper proposed a fully-simulated environment by integrating an on-sensor visual computing device, SCAMP, and CoppeliaSim robot simulator via interface and remote API. Within this platform, a mobile robot obstacle avoidance and target navigation
Externí odkaz:
http://arxiv.org/abs/2110.06386
Publikováno v:
In Journal of Water Process Engineering August 2024 65
Publikováno v:
In Process Safety and Environmental Protection August 2024 188:480-491
Autor:
Xing, Yifan, He, Tong, Xiao, Tianjun, Wang, Yongxin, Xiong, Yuanjun, Xia, Wei, Wipf, David, Zhang, Zheng, Soatto, Stefano
We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities using a training set of images annotated with labels belonging to a disjoint set of identities. Our hierarchica
Externí odkaz:
http://arxiv.org/abs/2107.01319
Data augmentation has been highly effective in narrowing the data gap and reducing the cost for human annotation, especially for tasks where ground truth labels are difficult and expensive to acquire. In face recognition, large pose and illumination
Externí odkaz:
http://arxiv.org/abs/2010.01246