Abstract
Dictionary Learning has produced state-of-the-art results in various classification tasks. However, when the training data has a different distribution than the testing data, the learned sparse representation may not be optimal. Recently, several domain adaptive dictionary learning (DADL) methods and its kernelized have been proposed and achieved impressive performance. However, the performance of these single kernel based methods heavily depend on the choice of the kernel, and how to combine multiple kernel learning (MKL) with DADL framework has not been well studied. Motivated by these concerns, in this paper, we propose a multi-kernel domain adaptive sparse representation based classification (MK-DASRC), and then we use it as a criterion to design a multi-kernel sparse representation based domain adaptive discriminative projections method (MK-DADP), in which the discriminative features of data in the two domains are simultaneously learned with the dictionary. The purpose of this method is to maximize the between-class sparse reconstruction residuals of data from both domains, and minimize the within-class sparse reconstruction residuals of data in the low dimensional subspace. Thus, the resulting representations can well fit MK-DASRC and simultaneously have discriminability. Extensive experimental results on a series of benchmark databases show that our method performs better than state-of-the-art methods.
Funding Information
  • National Natural Science Foundation of China (61806099, 61672293)
  • Natural Science Foundation of Jiangsu Province (BK20180790)
  • Nanjing University of Information Science and Technology (2243141701077)
  • PAPD

This publication has 45 references indexed in Scilit: