Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Li, Kaican"'
Autor:
Li, Kaican, Xie, Weiyan, Huang, Yongxiang, Deng, Didan, Hong, Lanqing, Li, Zhenguo, Silva, Ricardo, Zhang, Nevin L.
Fine-tuning foundation models often compromises their robustness to distribution shifts. To remedy this, most robust fine-tuning methods aim to preserve the pre-trained features. However, not all pre-trained features are robust and those methods are
Externí odkaz:
http://arxiv.org/abs/2411.19757
Out-of-distribution (OOD) generalization is a complicated problem due to the idiosyncrasies of possible distribution shifts between training and test domains. Most benchmarks employ diverse datasets to address this issue; however, the degree of the d
Externí odkaz:
http://arxiv.org/abs/2310.06622
Autor:
Zhang, Nevin L., Li, Kaican, Gao, Han, Xie, Weiyan, Lin, Zhi, Li, Zhenguo, Wang, Luning, Huang, Yongxiang
Domain generalization (DG) is about learning models that generalize well to new domains that are related to, but different from, the training domain(s). It is a fundamental problem in machine learning and has attracted much attention in recent years.
Externí odkaz:
http://arxiv.org/abs/2307.06825
Autor:
Gao, Han, Li, Kaican, Xie, Weiyan, Lin, Zhi, Huang, Yongxiang, Wang, Luning, Cao, Caleb Chen, Zhang, Nevin L.
Domain generalization (DG) is about training models that generalize well under domain shift. Previous research on DG has been conducted mostly in single-source or multi-source settings. In this paper, we consider a third, lesser-known setting where a
Externí odkaz:
http://arxiv.org/abs/2305.07888
Autor:
Yu, Runpeng, Zhu, Hong, Li, Kaican, Hong, Lanqing, Zhang, Rui, Ye, Nanyang, Huang, Shao-Lun, He, Xiuqiang
Due to the poor generalization performance of traditional empirical risk minimization (ERM) in the case of distributional shift, Out-of-Distribution (OoD) generalization algorithms receive increasing attention. However, OoD generalization algorithms
Externí odkaz:
http://arxiv.org/abs/2206.05749
Autor:
Li, Kaican, Chen, Kai, Wang, Haoyu, Hong, Lanqing, Ye, Chaoqiang, Han, Jianhua, Chen, Yukuai, Zhang, Wei, Xu, Chunjing, Yeung, Dit-Yan, Liang, Xiaodan, Li, Zhenguo, Xu, Hang
Contemporary deep-learning object detection methods for autonomous driving usually assume prefixed categories of common traffic participants, such as pedestrians and cars. Most existing detectors are unable to detect uncommon objects and corner cases
Externí odkaz:
http://arxiv.org/abs/2203.07724
Autor:
Ye, Nanyang, Li, Kaican, Bai, Haoyue, Yu, Runpeng, Hong, Lanqing, Zhou, Fengwei, Li, Zhenguo, Zhu, Jun
Deep learning has achieved tremendous success with independent and identically distributed (i.i.d.) data. However, the performance of neural networks often degenerates drastically when encountering out-of-distribution (OoD) data, i.e., when training
Externí odkaz:
http://arxiv.org/abs/2106.03721
Existing portrait matting methods either require auxiliary inputs that are costly to obtain or involve multiple stages that are computationally expensive, making them less suitable for real-time applications. In this work, we present a light-weight m
Externí odkaz:
http://arxiv.org/abs/2011.11961
We investigate the generalization of semi-supervised learning (SSL) to diverse pixel-wise tasks. Although SSL methods have achieved impressive results in image classification, the performances of applying them to pixel-wise tasks are unsatisfactory d
Externí odkaz:
http://arxiv.org/abs/2008.05258
Publikováno v:
Journal of Physics: Conference Series; 2024, Vol. 2771 Issue 1, p1-10, 10p
