Disassembling the Dataset: A Camera Alignment Mechanism for Multiple Tasks in Person Re-identification

01/23/2020
by   Zijie Zhuang, et al.
0

In person re-identification (ReID), one of the main challenges is the distribution inconsistency among different datasets. Previous researchers have defined several seemingly individual topics, such as fully supervised learning, direct transfer, domain adaptation, and incremental learning, each with different settings of training and testing scenarios. These topics are designed in a dataset-wise manner, i.e., images from the same dataset, even from disjoint cameras, are presumed to follow the same distribution. However, such distribution is coarse and training-set-specific, and the ReID knowledge learned in such manner works well only on the corresponding scenarios. To address this issue, we propose a fine-grained distribution alignment formulation, which disassembles the dataset and aligns all training and testing cameras. It connects all topics above and guarantees that ReID knowledge is always learned, accumulated, and verified in the aligned distributions. In practice, we devise the Camera-based Batch Normalization, which is easy for integration and nearly cost-free for existing ReID methods. Extensive experiments on the above four ReID tasks demonstrate the superiority of our approach. The code will be publicly available.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/22/2020

Camera On-boarding for Person Re-identification using Hypothesis Transfer Learning

Most of the existing approaches for person re-identification consider a ...
research
08/02/2019

Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification

In person re-identification (Re-ID), supervised methods usually need a l...
research
08/15/2020

Cluster-level Feature Alignment for Person Re-identification

Instance-level alignment is widely exploited for person re-identificatio...
research
10/17/2022

Joint Plasticity Learning for Camera Incremental Person Re-Identification

Recently, incremental learning for person re-identification receives inc...
research
03/18/2020

Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification

Part-level representations are important for robust person re-identifica...
research
11/06/2020

Domain Adaptive Person Re-Identification via Coupling Optimization

Domain adaptive person Re-Identification (ReID) is challenging owing to ...
research
07/25/2018

Person re-identification across different datasets with multi-task learning

This paper presents an approach to tackle the re-identification problem....

Please sign up or login with your details

Forgot password? Click here to reset