Published on Sat Jun 20 2020

Unsupervised Vehicle Re-identification with Progressive Adaptation

Jinjia Peng, Yang Wang, Huibing Wang, Zhao Zhang, Xianping Fu, Meng Wang

Vehicle re-identification (reID) aims at identifying vehicles across non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance. We propose a novel progressive adaptation learning method for vehicle reID.

0
0
0
Abstract

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to the severe domain bias between the training domain and the real-world scenes; worse still, these approaches required full annotations, which is labor-consuming. To tackle these challenges, we propose a novel progressive adaptation learning method for vehicle reID, named PAL, which infers from the abundant data without annotations. For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''. These pseudo samples are combined with the unlabeled samples that are selected by a dynamic sampling strategy to make training faster. We further proposed a weighted label smoothing (WLS) loss, which considers the similarity between samples with different clusters to balance the confidence of pseudo labels. Comprehensive experimental results validate the advantages of PAL on both VehicleID and VeRi-776 dataset.

Tue Apr 14 2020
Computer Vision
VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
Vehicle re-identification (re-id) is to learn robust and discriminative visual representation. The existing large-scale vehicle datasets are limited in terms of training images and viewpoints. We propose a two-stage progressive approach to learning more robust visual representation from VehicleNet.
0
0
0
Thu May 20 2021
Computer Vision
An Empirical Study of Vehicle Re-Identification on the AI City Challenge
This paper introduces our solution for the Track2 in AI City Challenge 2021. The Track2 is a vehicle re-identification task with both the real-world data and synthetic data. We mainly focus on four points, i.e. training data, unsupervised domain-adaptive (
1
0
1
Tue Apr 02 2019
Computer Vision
Vehicle Re-identification in Aerial Imagery: Dataset and Approach
The dataset contains 137k images of 13k vehicle instances captured by UAV-mounted cameras. To increase intra-class variation, each vehicle is captured by at least two UAVs at different locations. We manually label a variety of vehicle attributes, including vehicle type, color,
0
0
0
Sat May 09 2020
Computer Vision
Vehicle Re-Identification Based on Complementary Features
We present our solution to the vehicle re-identification(vehicle Re-ID) track in AI City Challenge 2020 (AIC2020) The purpose of vehicle Re- ID is to retrieve the same vehicle appeared across multiple cameras.
0
0
0
Sat May 02 2020
Machine Learning
PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data
Pose-Aware Multi-Task Re-Identification (PAMTRI) is a framework for vehicle ReID. It overcomes viewpoint-dependency by explicitly reasoning about vehicle pose and shape via keypoints, heatmaps and segments from pose estimation.
0
0
0
Wed Nov 18 2020
Computer Vision
Viewpoint-aware Progressive Clustering for Unsupervised Vehicle Re-identification
Vehicle re-identification (Re-ID) is an active task due to its importance in large-scale intelligent monitoring in smart cities. Most existing methods handle vehicle Re-ID task in asupervised manner, which is both time and labor-consuming. To handle this problem,
0
0
0