Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Zou, Yingtian"'
Domain generalization aims to develop models that are robust to distribution shifts. Existing methods focus on learning invariance across domains to enhance model robustness, and data augmentation has been widely used to learn invariant predictors, w
Externí odkaz:
http://arxiv.org/abs/2405.08586
Generalizing to out-of-distribution (OOD) data or unseen domain, termed OOD generalization, still lacks appropriate theoretical guarantees. Canonical OOD bounds focus on different distance measurements between source and target domains but fail to co
Externí odkaz:
http://arxiv.org/abs/2403.06392
Autor:
Zou, Yingtian, Verma, Vikas, Mittal, Sarthak, Tang, Wai Hoh, Pham, Hieu, Kannala, Juho, Bengio, Yoshua, Solin, Arno, Kawaguchi, Kenji
Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels. This technique is known to improve the generalization performance in m
Externí odkaz:
http://arxiv.org/abs/2212.13381
Autor:
Tu, Xiaoguang, Zou, Yingtian, Zhao, Jian, Ai, Wenjie, Dong, Jian, Yao, Yuan, Wang, Zhikang, Guo, Guodong, Li, Zhifeng, Liu, Wei, Feng, Jiashi
We present a versatile model, FaceAnime, for various video generation tasks from still images. Video generation from a single face image is an interesting problem and usually tackled by utilizing Generative Adversarial Networks (GANs) to integrate in
Externí odkaz:
http://arxiv.org/abs/2105.14678
Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few-shot segmentation has thus be
Externí odkaz:
http://arxiv.org/abs/1908.06391
Pursuing more complete and coherent scene understanding towards realistic vision applications drives edge detection from category-agnostic to category-aware semantic level. However, finer delineation of instance-level boundaries still remains unexcav
Externí odkaz:
http://arxiv.org/abs/1906.00590
Autor:
Zou, Yingtian, Feng, Jiashi
Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks share the same out-put structure. To obtain a meta model applicable to t
Externí odkaz:
http://arxiv.org/abs/1904.09081
Predicting the future is a fantasy but practicality work. It is the key component to intelligent agents, such as self-driving vehicles, medical monitoring devices and robotics. In this work, we consider generating unseen future frames from previous o
Externí odkaz:
http://arxiv.org/abs/1901.01649
We tackle the problem of person re-identification in video setting in this paper, which has been viewed as a crucial task in many applications. Meanwhile, it is very challenging since the task requires learning effective representations from video se
Externí odkaz:
http://arxiv.org/abs/1807.05799
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.