Residual Transfer Learning for Multiple Object Tracking - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Residual Transfer Learning for Multiple Object Tracking


To address the Multiple Object Tracking (MOT) challenge , we propose to enhance the tracklet appearance features , given by a Convolutional Neural Network (CNN), based on the Residual Transfer Learning (RTL) method. Considering that object classification and tracking are significantly different tasks at high level. And that traditional fine-tuning limits the possible variations in all the layers of the network since it changes the last convolutional layers. Beyond that, our proposed method provides more flexibility in terms of modelling the difference between these two tasks with a four-stage training. This transfer approach increases the feature performance compared to traditional CNN fine-tuning. Experiments on the MOT17 challenge show competitive results with the current state-of-the-art methods.
Fichier principal
Vignette du fichier
PID5568623.pdf (264.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01928612 , version 1 (20-11-2018)


  • HAL Id : hal-01928612 , version 1


Juan Diego Gonzales Zuniga, Thi-Lan-Anh Nguyen, Francois Bremond. Residual Transfer Learning for Multiple Object Tracking. International Conference on Advanced Video and Signal-based Surveillance (AVSS), IEEE, Nov 2018, Auckland, New Zealand. ⟨hal-01928612⟩
97 View
162 Download


Gmail Facebook Twitter LinkedIn More