An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification

05/16/2018
by   Paul Marchwica, et al.
0

In recent years, a variety of proposed methods based on deep convolutional neural networks (CNNs) have improved the state of the art for large-scale person re-identification (ReID). While a large number of optimizations and network improvements have been proposed, there has been relatively little evaluation of the influence of training data and baseline network architecture. In particular, it is usually assumed either that networks are trained on labeled data from the deployment location (scene-dependent), or else adapted with unlabeled data, both of which complicate system deployment. In this paper, we investigate the feasibility of achieving scene-independent person ReID by forming a large composite dataset for training. We present an in-depth comparison of several CNN baseline architectures for both scene-dependent and scene-independent ReID, across a range of training dataset sizes. We show that scene-independent ReID can produce leading-edge results, competitive with unsupervised domain adaption techniques. Finally, we introduce a new dataset for comparing within-camera and across-camera person ReID.

READ FULL TEXT

page 1

page 3

page 7

research
11/25/2020

Multi-Domain Adversarial Feature Generalization for Person Re-Identification

With the assistance of sophisticated training methods applied to single ...
research
02/09/2018

Triplet-based Deep Similarity Learning for Person Re-Identification

In recent years, person re-identification (re-id) catches great attentio...
research
07/24/2021

Going Deeper into Semi-supervised Person Re-identification

Person re-identification is the challenging task of identifying a person...
research
02/13/2019

Multi-views Embedding for Cattle Re-identification

People re-identification task has seen enormous improvements in the late...
research
05/09/2017

Deep Person Re-Identification with Improved Embedding and Efficient Training

Person re-identification task has been greatly boosted by deep convoluti...
research
10/21/2021

DEX: Domain Embedding Expansion for Generalized Person Re-identification

In recent years, supervised Person Re-identification (Person ReID) appro...
research
04/01/2016

A Semisupervised Approach for Language Identification based on Ladder Networks

In this study we address the problem of training a neuralnetwork for lan...

Please sign up or login with your details

Forgot password? Click here to reset