1 code implementation • 16 Oct 2016 • Sandipan Banerjee, Joel Brogan, Janez Krizaj, Aparna Bharati, Brandon RichardWebster, Vitomir Struc, Patrick Flynn, Walter Scheirer
If a CNN is intended to tolerate facial pose, then we face an important question: should this training data be diverse in its pose distribution, or should face images be normalized to a single pose in a pre-processing step?