Transferring learning from multi-person tracking to person re-identification

Learning to discriminate, whether two person-images correspond to the same person or not, is a daunting challenge when only two images per person are available. This task is called single-shot person re-identification (re-id) and it assumes that each one of the two available images was captured from a different camera view entailing variations in pose, resolution, scale, illumination and background. Addressing this task through supervised training of a deep convolutional neural network is susceptible to model overfitting due to the critical lack of enough labelled data. This paper proposes to exploit the transference of learning previously acquired from a multi-object-tracking (MOT) domain. In this context, a unique deep triplet architecture has been trained on both domains. Six different levels of transfer learning have been implemented and evaluated, proving that the transference of leaning from a different domain remarkably increases the re-id performance. Experimental results validate accuracy and robustness of the proposed method as comparable to other state-of-the-art techniques. These results also confirm that, despite the data problem, deep learning is also applicable to the single-shot re-id task.This work was supported by the Spanish Govern-ment through the CICYT projects (TRA2015-63708-R and TRA2016-78886-C3-1-R), and Ministerio de Educación, Cultura y Deporte para la Formación de Profesorado Universitario (FPU14/02143), Ayudas a la movilidad para estancias breves y traslados tempo-rales (2018) of Programa Estatal de promoción del ta-lento y su empleabilidad, , and Comunidad de Madrid through SEGVAUTO-TRIES (S2013/MIT- 2713). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the GPUs used for this research