Estimation of 3D Body Shape and Clothing Measurements From Frontal- and Side-View Images

This paper demonstrates a novel approach to improve face-recognition pose-invariance using semantic-segmentation features. The proposed Seg-Distilled-ID network jointly learns identification and semantic-segmentation tasks, where the segmentation task is then ?distilled? (MobileNet encoder). Performance is benchmarked against three state-of-the-art encoders on a publicly available data-set emphasizing head-pose variations. Experimental evaluations show the Seg-Distilled-ID network shows notable robustness benefits, achieving 99.9% test-accuracy in comparison to 81.6% on ResNet-101, 96.1% on VGG-19 and 96.3% on inceptionV3. This is achieved using approximately one-tenth of the top competitor?s inference parameters. These results indicate encoding semantic-segmentation features can efficiently improve face-recognition pose-invariance.