Residual Transfer Learning for Multiple Object Tracking

Juan Diego Gonzales Zuniga 1 Thi-Lan-Anh Nguyen 1 Francois Bremond 1
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
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.
Keywords : Computer vision algorithm Object tracking
Document type :
Conference papers
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download
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

INRIA | UNIV-COTEDAZUR

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⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

86

Files downloads

150

Contact


archive-ouverte@inria.fr