PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data

05/02/2020
by   Zheng Tang, et al.
1

In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention. Vehicle ReID is challenging due to 1) high intra-class variability (caused by the dependency of shape and appearance on viewpoint), and 2) small inter-class variability (caused by the similarity in shape and appearance between vehicles produced by different manufacturers). To address these challenges, we propose a Pose-Aware Multi-Task Re-Identification (PAMTRI) framework. This approach includes two innovations compared with previous methods. First, it overcomes viewpoint-dependency by explicitly reasoning about vehicle pose and shape via keypoints, heatmaps and segments from pose estimation. Second, it jointly classifies semantic vehicle attributes (colors and types) while performing ReID, through multi-task learning with the embedded pose representations. Since manually labeling images with detailed pose and attribute information is prohibitive, we create a large-scale highly randomized synthetic dataset with automatically annotated vehicle attributes for training. Extensive experiments validate the effectiveness of each proposed component, showing that PAMTRI achieves significant improvement over state-of-the-art on two mainstream vehicle ReID benchmarks: VeRi and CityFlow-ReID. Code and models are available at https://github.com/NVlabs/PAMTRI.

READ FULL TEXT

page 3

page 4

page 7

page 8

research
05/08/2019

Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation

While many individual tasks in the domain of human analysis have recentl...
research
06/17/2022

Cross-task Attention Mechanism for Dense Multi-task Learning

Multi-task learning has recently become a promising solution for a compr...
research
04/12/2018

Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling

We study 3D shape modeling from a single image and make contributions to...
research
04/20/2020

VOC-ReID: Vehicle Re-identification based on Vehicle-Orientation-Camera

Vehicle re-identification is a challenging task due to high intra-class ...
research
07/26/2020

GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision

We present a novel end-to-end framework named as GSNet (Geometric and Sc...
research
06/07/2019

Visual Person Understanding through Multi-Task and Multi-Dataset Learning

We address the problem of learning a single model for person re-identifi...
research
10/12/2020

Viewpoint-Aware Channel-Wise Attentive Network for Vehicle Re-Identification

Vehicle re-identification (re-ID) matches images of the same vehicle acr...

Please sign up or login with your details

Forgot password? Click here to reset