no code implementations • 15 Mar 2021 • Wei Bao, Meiyu Huang, Yaqin Zhang, Yao Xu, Xuejiao Liu, Xueshuang Xiang
In this paper, to resolve the problem of inconsistent imaging perspective between ImageNet and earth observations, we propose an optical ship detector (OSD) pretraining technique, which transfers the characteristics of ships in earth observations to SAR images from a large-scale aerial image dataset.
1 code implementation • 15 Mar 2021 • Meiyu Huang, Yao Xu, Lixin Qian, Weili Shi, Yaqin Zhang, Wei Bao, Nan Wang, Xuejiao Liu, Xueshuang Xiang
We obtain the SAR patches from SAR satellite GaoFen-3 images and the optical patches from Google Earth images.
no code implementations • 10 Apr 2020 • Meiyu Huang, Xueshuang Xiang, Yao Xu
Few-shot classification is a challenging task which aims to formulate the ability of humans to learn concepts from limited prior data and has drawn considerable attention in machine learning.
no code implementations • 18 Sep 2019 • Chaohui Yu, Jindong Wang, Yiqiang Chen, Meiyu Huang
In this paper, we propose a novel Dynamic Adversarial Adaptation Network (DAAN) to dynamically learn domain-invariant representations while quantitatively evaluate the relative importance of global and local domain distributions.
1 code implementation • 17 Sep 2019 • Jindong Wang, Yiqiang Chen, Wenjie Feng, Han Yu, Meiyu Huang, Qiang Yang
Since the source and the target domains are usually from different distributions, existing methods mainly focus on adapting the cross-domain marginal or conditional distributions.
Ranked #7 on Domain Adaptation on ImageCLEF-DA
no code implementations • 26 Jun 2019 • Yao Xu, Xueshuang Xiang, Meiyu Huang
The experiments on the tasks, including pair matching, canonical correlation analysis, transfer learning, and reconstruction demonstrate the state-of-the-art performance of BNN, which may provide new insights into the aspect of common representation learning.
1 code implementation • 2 Apr 2019 • Jindong Wang, Yiqiang Chen, Han Yu, Meiyu Huang, Qiang Yang
In this paper, we propose a practically Easy Transfer Learning (EasyTL) approach which requires no model selection and hyperparameter tuning, while achieving competitive performance.
Ranked #4 on Transfer Learning on Office-Home
no code implementations • 5 Dec 2018 • Haipeng Jia, Xueshuang Xiang, Da Fan, Meiyu Huang, Changhao Sun, Yang He
Addressing these two issues, this paper proposes the Drop Pruning approach, which leverages stochastic optimization in the pruning process by introducing a drop strategy at each pruning step, namely, drop away, which stochastically deletes some unimportant weights, and drop back, which stochastically recovers some pruned weights.
no code implementations • 20 Jul 2018 • Jindong Wang, Vincent W. Zheng, Yiqiang Chen, Meiyu Huang
In this paper, we propose an effective Unsupervised Source Selection algorithm for Activity Recognition (USSAR).
Cross-Domain Activity Recognition Human Activity Recognition +1
1 code implementation • 19 Jul 2018 • Jindong Wang, Wenjie Feng, Yiqiang Chen, Han Yu, Meiyu Huang, Philip S. Yu
Existing methods either attempt to align the cross-domain distributions, or perform manifold subspace learning.
Ranked #1 on Domain Adaptation on Office-Caltech-10
no code implementations • 26 Jun 2018 • Yiqiang Chen, Jindong Wang, Meiyu Huang, Han Yu
STL consists of two components: Stratified Domain Selection (STL-SDS) can select the most similar source domain to the target domain; Stratified Activity Transfer (STL-SAT) is able to perform accurate knowledge transfer.