Person Re-Identification
268 papers with code • 15 benchmarks • 33 datasets
Person re-identification is the task of associating images of the same person taken from different cameras or from the same camera in different occasions.
( Image credit: PRID2011 dataset )
Benchmarks
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Market-1501
CUHK03
DukeMTMC-reID
MARS
VIPeR
CUHK-SYSU
ETH
PRW
CityFlow
Subtasks
Greatest papers with code
MobileNetV2: Inverted Residuals and Linear Bottlenecks
tensorflow/models
•
•
CVPR 2018
In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.
Ranked #4 on
Retinal OCT Disease Classification
on OCT2017
Deep Residual Learning for Image Recognition
tensorflow/models
•
•
CVPR 2016
Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
Ranked #2 on
Semantic Object Interaction Classification
on VLOG
Random Erasing Data Augmentation
rwightman/pytorch-image-models
•
•
In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).
Ranked #4 on
Image Classification
on Fashion-MNIST
Densely Connected Convolutional Networks
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output.
Ranked #1 on
Pedestrian Attribute Recognition
on UAV-Human
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
tensorpack/tensorpack
•
•
CVPR 2018
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e. g., 10-150 MFLOPs).
Ranked #61 on
Person Re-Identification
on DukeMTMC-reID
Simple Online and Realtime Tracking with a Deep Association Metric
nwojke/deep_sort
•
•
Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms.
Ranked #13 on
Video Instance Segmentation
on YouTube-VIS validation
(AR1 metric)
Large-Scale Person Re-Identification
Multiple Object Tracking
+1
Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
KaiyangZhou/deep-person-reid
•
•
Person re-identification (re-ID), which aims to re-identify people across different camera views, has been significantly advanced by deep learning in recent years, particularly with convolutional neural networks (CNNs).
Learning Generalisable Omni-Scale Representations for Person Re-Identification
KaiyangZhou/deep-person-reid
•
•
An effective person re-identification (re-ID) model should learn feature representations that are both discriminative, for distinguishing similar-looking people, and generalisable, for deployment across datasets without any adaptation.
Unsupervised Domain Adaptation
Unsupervised Person Re-Identification
Omni-Scale Feature Learning for Person Re-Identification
KaiyangZhou/deep-person-reid
•
•
ICCV 2019
As an instance-level recognition problem, person re-identification (ReID) relies on discriminative features, which not only capture different spatial scales but also encapsulate an arbitrary combination of multiple scales.
Ranked #7 on
Person Re-Identification
on CUHK03
Deep Transfer Learning for Person Re-identification
KaiyangZhou/deep-person-reid
•
•
Second, a two-stepped fine-tuning strategy is developed to transfer knowledge from auxiliary datasets.