Learning with Ambiguous Label Distribution for Apparent Age Estimation

Annotating age classes for humans’ facial images according to their appearance is very challenging because of dynamic person-specific ageing pattern, and thus leads to a set of unreliable apparent age labels for each image. For utilising ambiguous label annotations, an intuitive strategy is to generate a pseudo age for each image, typically the average value of manually-annotated age annotations, which is thus fed into standard supervised learning frameworks designed for chronological age estimation. Alternatively, inspired by the recent success of label distribution learning, this paper introduces a novel concept of ambiguous label distribution for apparent age estimation, which is developed under the following observations that (1) soft labelling is beneficial for alleviating the suffering of inaccurate annotations and (2) more reliable annotations should contribute more. To achieve the goal, label distributions of sparse age annotations for each image are weighted according to their reliableness and then combined to construct an ambiguous label distribution. In the light, the proposed learning framework not only inherits the advantages from conventional learning with label distribution to capture latent label correlation but also exploits annotation reliableness to improve the robustness against inconsistent age annotations. Experimental evaluation on the FG-NET age estimation benchmark verifies its effectiveness and superior performance over the state-of-the-art frameworks for apparent age estimation.