Abstract
—Existing studies in facial age estimation have mostly
focused on intra-dataset protocols that assume training and
test images captured under similar conditions. However, this is
rarely valid in practical applications, where training and test sets
usually have different characteristics. In this paper, we advocate
a cross-dataset protocol for age estimation benchmarking. In
order to improve the cross-dataset age estimation performance,
we mitigate the inherent bias caused by the learning algorithm
itself. To this end, we propose a novel loss function that is more
effective for neural network training. The relative smoothness
of the proposed loss function is its advantage with regards
to the optimisation process performed by stochastic gradient
descent. Its lower gradient, compared with existing loss functions, facilitates the discovery of and convergence to a better
optimum, and consequently a better generalisation. The crossdataset experimental results demonstrate the superiority of the
proposed method over the state-of-the-art algorithms in terms of
accuracy and generalisation capability.