A Dual-Path Model With Adaptive Attention for Vehicle Re-Identification

In recent years, attention models have been extensively used for person and vehicle re-identification. Most re-identification methods are designed to focus attention on key-point locations. However, depending on the orientation, the contribution of each key-point varies. In this paper, we present a...

Full description

Saved in:
Bibliographic Details
Main Authors: Khorramshahi, Pirazh, Kumar, Amit, Peri, Neehar, Rambhatla, Sai Saketh, Chen, Jun-Cheng, Chellappa, Rama
Format: Conference Proceeding
Language:English
Subjects:
Adaptation models
Automobiles
Estimation
Feature extraction
Heating systems
Task analysis
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, attention models have been extensively used for person and vehicle re-identification. Most re-identification methods are designed to focus attention on key-point locations. However, depending on the orientation, the contribution of each key-point varies. In this paper, we present a novel dual-path adaptive attention model for vehicle re-identification (AAVER). The global appearance path captures macroscopic vehicle features while the orientation conditioned part appearance path learns to capture localized discriminative features by focusing attention on the most informative key-points. Through extensive experimentation, we show that the proposed AAVER method is able to accurately re-identify vehicles in unconstrained scenarios, yielding state of the art results on the challenging dataset VeRi-776. As a byproduct, the proposed system is also able to accurately predict vehicle key-points and shows an improvement of more than 7% over state of the art. The code for key-point estimation model is available at https://github.com/Pirazh/Vehicle_Key_ Point_Orientation_Estimation.
ISSN:2380-7504
DOI:10.1109/ICCV.2019.00623