Browse/search for people

Publication - Dr Tilo Burghardt

    Semantically Selective Augmentation for Deep Compact Person Re-Identification

    Citation

    Ponce-López, V, Burghardt, T, Hannunna, S, Damen, D, Masullo, A & Mirmehdi, M, 2019, ‘Semantically Selective Augmentation for Deep Compact Person Re-Identification’. in: Stefan Roth, Laura Leal-Taixé (eds) Computer Vision – ECCV 2018 Workshops, Proceedings. Springer Verlag, pp. 551-561

    Abstract

    We present a deep person re-identification approach that combines semantically selective, deep data augmentation with clustering-based network compression to generate high performance, light and fast inference networks. In particular, we propose to augment limited training data via sampling from a deep convolutional generative adversarial network (DCGAN), whose discriminator is constrained by a semantic classifier to explicitly control the domain specificity of the generation process. Thereby, we encode information in the classifier network which can be utilized to steer adversarial synthesis, and which fuels our CondenseNet ID-network training. We provide a quantitative and qualitative analysis of the approach and its variants on a number of datasets, obtaining results that outperform the state-of-the-art on the LIMA dataset for long-term monitoring in indoor living spaces.

    Full details in the University publications repository