Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch

Abstract

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). In this paper, we present Torchreid, a software library built on PyTorch that allows fast development and end-to-end training and evaluation of deep re-ID models. As a general-purpose framework for person re-ID research, Torchreid provides (1) unified data loaders that support 15 commonly used re-ID benchmark datasets covering both image and video domains, (2) streamlined pipelines for quick development and benchmarking of deep re-ID models, and (3) implementations of the latest re-ID CNN architectures along with their pre-trained models to facilitate reproducibility as well as future research. With a high-level modularity in its design, Torchreid offers a great flexibility to allow easy extension to new datasets, CNN models and loss functions.

Tech report

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• On the Convergence of Adam and Beyond
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Deep Transfer Learning for Person Re-identification
• SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition

Cited by in corpus (10)

• DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
• Domain Generalization with MixStyle
• Simple Unsupervised Multi-Object Tracking
• Person Re-ID through Unsupervised Hypergraph Rank Selection and Fusion
• Going Deeper into Semi-supervised Person Re-identification
• 3D Human Texture Estimation from a Single Image with Transformers
• Symbiotic Adversarial Learning for Attribute-based Person Search
• Visualizing Color-wise Saliency of Black-Box Image Classification Models
• Multi-granularity for knowledge distillation
• PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data