[name]

Machine Vision, Image Recognition and Machine Learning

[LSDT for Heterogeneous Image Recognition]

Paper:

Lei Zhang*, Wangmeng Zuo, and David Zhang, LSDT: Latent Sparse Domain Transfer Learning for Visual Adaptation, IEEE Transactions on Image Processing (T-IP), vol. 25, no. 3, pp. 1177-1191, 2016. [paper]

Abstract:

We propose a novel reconstruction-based transfer learning method called latent sparse domain transfer (LSDT) for domain adaptation and visual categorization of heterogeneous data. For handling cross-domain distribution mismatch, we advocate reconstructing the target domain data with the combined source and target domain data points based on L1-norm sparse coding. Furthermore, we propose a joint learning model for simultaneous optimization of the sparse coding and the optimal subspace representation. In addition, we generalize the proposed LSDT model into a kernel-based linear/nonlinear basis transformation learning framework for tackling nonlinear subspace shifts in reproduced kernel Hilbert space. The proposed methods have three advantages: 1) the latent space and the reconstruction are jointly learned for pursuit of an optimal subspace transfer; 2) with the theory of sparse subspace clustering, a few valuable source and target data points are formulated to reconstruct the target data with noise (outliers) from source domain removed during domain adaptation, such that the robustness is guaranteed; and 3) a nonlinear projection of some latent space with kernel is easily generalized for dealing with highly nonlinear domain shift (e.g., face poses). Extensive experiments on several benchmark vision data sets demonstrate that the proposed approaches outperform other state-of-the-art representation-based domain adaptation methods.

Overview of the existing reconstruction guided knowledge transfer methods and our method. (a) Idea of RDALR. (b) Idea of LTSL. (c) Idea of our method.

[name]

Approach:

Flowchart of the training and testing phase of the proposed LSDT method for visual categorization.

[name]

Experiments:

The 3D illustration of synthetic data (left) and 2D illustration after subspace alignment (right).

[name]

Recognition Accuracy

[name] [name]

Visualization

[name]