Note: Below were experiments done at the early stage of this project. See THIS PAGE for more recent experiments where local shift leads to cleaner templates.

Learning Active Basis Models from Aligned Images

Note: The parameters in the following experiments are slightly different from those in IJCV reproducibility page

Code for deer example





Code for synthesis
The first row displays the training images (displayed in color for visual clarity, although the algorithm works on grey level images). The second and third rows display the learned templates at two different scales, with the scale in the third row about twice the scale in the second row. In each of the second and third rows, the first template is the common template, and the rest are the deformed templates to match the training images. The number of elements in the templates of the second row is 50. The number of elements in the templates of the third row is 14. The fourth row displays the reconstructed images by linearly combining 100 wavelet elements at different scales.

Code for showing learning sequence


The learned templates with 5, 10, 15, 20, 25, 30, 40, 50 basis elements.

The learned templates with 1, 2, 4, 6, 8, 10, 12, 14 basis elements, at a larger scale. code

Detecting and sketching the objects in the testing images using the template learned at the smaller scale.

Code for crane example



Code for pigeon example




Code for cow example





Code for bike example








Code for horse example

Flatness features by local average of filter responses after local normalization and sigmoid transformation. code for flatness features


The window for local average is 1x1, 9x9, 17x17, 25x25 respectively. eps0 4 8 12








































































Code for butterfly example













































Code for cat example























Code for bear example


























Old code for reproducing results in paper: deer
Back to active basis homepage