Residual Transfer Learning for Multiple Object Tracking

Abstract : 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.
Complete list of metadatas

https://hal.inria.fr/hal-01928612
Contributor : Juan Diego Gonzales Zuniga <>
Submitted on : Tuesday, November 20, 2018 - 4:14:24 PM
Last modification on : Thursday, November 22, 2018 - 1:20:17 AM

File

PID5568623.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01928612, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

70

Files downloads

106