Fig. 6From: Classification methods of a small sample target object in the sky based on the higher layer visualizing feature and transfer learning deep networksThe visualizing displays of the higher layer local eigenvectors extracted by the SAE model. The left side of the figure shows the higher layer local eigenvectors extracted by the SAE model from (a) The target-domain object images, and the right side of the figure shows the higher layer local eigenvectors extracted by the SAE model from (b) The cross-domain database of STL-10Back to article page