Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations. (arXiv:2111.00131v2 [cs.CV] UPDATED)

The training data distribution is often biased towards objects in certain
orientations and illumination conditions. While humans have a remarkable
capability of recognizing objects in out-of-distribution (OoD) orientations and
illuminations, Deep Neural Networks (DNNs) severely suffer in this case, even
when large amounts of training examples are available. In this paper, we
investigate three different approaches to improve DNNs in recognizing objects
in OoD orientations and illuminations. Namely, these are (i) training much
longer after convergence of the in-distribution (InD) …

arxiv cv distribution