Predicting on multiple transformations of original picture

[haoyu09]

Hi, in the predicting process, I found that the input picture has to be transformed into various version, the final result is the sum of the predicting result for each, is this a method to increase the accuracy?

[dpressel]

This is actually optional, if you set --single_look it will only look at the image, not oversample it.

Here is the section of the Levi/Hassner paper which explains the approach:

Prediction. We experimented with two methods of using the network in order to produce age and gender predictions for novel faces:

• Center Crop: Feeding the network with the face image, cropped to 227 × 227 around the face center.
• Over-sampling: We extract five 227 × 227 pixel crop regions, four from the corners of the 256 × 256 face image, and an additional crop region from the center of the face. The network is presented with all five images, along with their horizontal reflections. Its final prediction is taken to be the average prediction value across all these variations.

We have found that small misalignments in the Adience images, caused by the many challenges of these images (occlusions, motion blur, etc.) can have a noticeable impact on the quality of our results. This second, over-sampling method, is designed to compensate for these small misalignments, bypassing the need for improving alignment quality, but rather directly feeding the network with multiple translated
versions of the same face