Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Zhaoshui He

Domain Confusion with Self Ensembling for Unsupervised Adaptation

Oct 10, 2018
Jiawei Wang, Zhaoshui He, Chengjian Feng, Zhouping Zhu, Qinzhuang Lin, Jun Lv, Shengli Xie

Figure 1 for Domain Confusion with Self Ensembling for Unsupervised Adaptation

Figure 2 for Domain Confusion with Self Ensembling for Unsupervised Adaptation

Figure 3 for Domain Confusion with Self Ensembling for Unsupervised Adaptation

Figure 4 for Domain Confusion with Self Ensembling for Unsupervised Adaptation

Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There are two popular ways to achieve this goal: adversarial learning and self training. In this article, we first analyze the training unstablity problem and the mistaken confusion issue in adversarial learning process. Then, inspired by domain confusion and self-ensembling methods, we propose a combined model to learn feature and class jointly invariant representation, namely Domain Confusion with Self Ensembling (DCSE). The experiments verified that our proposed approach can offer better performance than empirical art in a variety of unsupervised domain adaptation benchmarks.

Via

Access Paper or Ask Questions

Kernel Sparse Subspace Clustering on Symmetric Positive Definite Manifolds

Jan 04, 2016
Ming Yin, Yi Guo, Junbin Gao, Zhaoshui He, Shengli Xie

Figure 1 for Kernel Sparse Subspace Clustering on Symmetric Positive Definite Manifolds

Figure 2 for Kernel Sparse Subspace Clustering on Symmetric Positive Definite Manifolds

Figure 3 for Kernel Sparse Subspace Clustering on Symmetric Positive Definite Manifolds

Figure 4 for Kernel Sparse Subspace Clustering on Symmetric Positive Definite Manifolds

Sparse subspace clustering (SSC), as one of the most successful subspace clustering methods, has achieved notable clustering accuracy in computer vision tasks. However, SSC applies only to vector data in Euclidean space. As such, there is still no satisfactory approach to solve subspace clustering by ${\it self-expressive}$ principle for symmetric positive definite (SPD) matrices which is very useful in computer vision. In this paper, by embedding the SPD matrices into a Reproducing Kernel Hilbert Space (RKHS), a kernel subspace clustering method is constructed on the SPD manifold through an appropriate Log-Euclidean kernel, termed as kernel sparse subspace clustering on the SPD Riemannian manifold (KSSCR). By exploiting the intrinsic Riemannian geometry within data, KSSCR can effectively characterize the geodesic distance between SPD matrices to uncover the underlying subspace structure. Experimental results on two famous database demonstrate that the proposed method achieves better clustering results than the state-of-the-art approaches.

Via

Access Paper or Ask Questions