Bag of Tricks and a Strong Baseline for Deep Person Re-Identification
Hao Luo,Youzhi Gu,Xingyu Liao,Shenqi Lai,Wei Jiang +4 more
- pp 1487-1495
Reads0
Chats0
TLDR
A simple and efficient baseline for person re-identification with deep neural networks by combining effective training tricks together, which achieves 94.5% rank-1 and 85.9% mAP on Market1501 with only using global features.Abstract:
This paper explores a simple and efficient baseline for person re-identification (ReID). Person re-identification (ReID) with deep neural networks has made progress and achieved high performance in recent years. However, many state-of-the-arts methods design complex network structure and concatenate multi-branch features. In the literature, some effective training tricks are briefly appeared in several papers or source codes. This paper will collect and evaluate these effective training tricks in person ReID. By combining these tricks together, the model achieves 94.5% rank-1 and 85.9% mAP on Market1501 with only using global features. Our codes and models are available at https://github.com/michuanhaohao/reid-strong-baseline.read more
Citations
More filters
Journal ArticleDOI
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
TL;DR: A simple approach which consists of two homogeneous branches to predict pixel-wise objectness scores and re-ID features allows \emph{FairMOT} to obtain high levels of detection and tracking accuracy and outperform previous state-of-the-arts by a large margin on several public datasets.
Journal ArticleDOI
A Strong Baseline and Batch Normalization Neck for Deep Person Re-Identification
TL;DR: Extended experiments show that BNNeck can boost the baseline, and the baseline can improve the performance of existing state-of-the-art methods.
Journal ArticleDOI
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking
TL;DR: FairMOT as discussed by the authors proposes a simple yet effective approach based on the anchor-free object detection architecture CenterNet, which achieves high accuracy for both detection and tracking, and outperforms the state-of-the-art methods by a large margin.
Proceedings ArticleDOI
Style Normalization and Restitution for Generalizable Person Re-Identification
TL;DR: The aim of this paper is to design a generalizable person ReID framework which trains a model on source domains yet is able to generalize/perform well on target domains, and to enforce a dual causal loss constraint in SNR to encourage the separation of identity-relevant features and identity-irrelevant features.
Proceedings ArticleDOI
RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
TL;DR: A novel and end-to-end Alignment Generative Adversarial Network (AlignGAN) for the RGB-IR RE-ID task, which consists of a pixel generator, a feature generator and a joint discriminator that is able to not only alleviate the cross-modality and intra- modality variations, but also learn identity-consistent features.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings ArticleDOI
Rethinking the Inception Architecture for Computer Vision
TL;DR: In this article, the authors explore ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.
Posted Content
Rethinking the Inception Architecture for Computer Vision
TL;DR: This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.
Posted Content
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TL;DR: This work proposes a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit and derives a robust initialization method that particularly considers the rectifier nonlinearities.
Proceedings ArticleDOI
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TL;DR: In this paper, a Parametric Rectified Linear Unit (PReLU) was proposed to improve model fitting with nearly zero extra computational cost and little overfitting risk, which achieved a 4.94% top-5 test error on ImageNet 2012 classification dataset.