FastReID: A Pytorch Toolbox for General Instance Re-identification

By Lingxiao He, Xingyu Liao, Wu Liu, Xinchen Liu, Peng Cheng, Tao Mei. ACM Multimedia, 2020

438 citations recorded by the source corpus.

General Instance Re-identification is a very important task in computer vision, which can be widely used in many practical applications, such as person/vehicle re-identification, face recognition, wildlife protection, commodity tracing, snapshots, and so on. To meet the increasing application demand for general instance re-identification, we present FastReID as a widely used software system. In FastReID, the highly modular and extensible design makes it easy for the researcher to achieve new research ideas. Friendly manageable system configuration and engineering deployment functions allow practitioners to quickly deploy models into productions. We have implemented some state-of-the-art projects, including person re-id, partial re-id, cross-domain re-id, and vehicle re-id. Moreover, we plan to release these pre-trained models on multiple benchmark datasets. FastReID is by far the most general and high-performance toolbox that supports single and multiple GPU servers, it can reproduce our project results very easily. The source codes and models have been released at https://github.com/JDAI-CV/fast-reid.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/abf929395c3d9d40b0b499400b94095908a3356a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chunhua Shen
2. Xinggang Wang
3. Xinlong Wang
4. Ping Luo
5. Wenyu Liu
6. Pei Sun
7. Kris M. Kitani
8. Yifu Zhang

In Computer Vision and Pattern Recognition

1. Chunhua Shen
2. Xinggang Wang
3. Ping Luo
4. Kris M. Kitani
5. Luc Van Gool
6. Xiaogang Wang
7. Dacheng Tao
8. Wenyu Liu

Citations in the corpus

• Diverse Knowledge Distillation for End-to-End Person Search (2020, methodology): “…(3) In this way, the head H can capture the similar sample relationships as the model M. Motivated by recent contrastive learning algorithms (Chen et al. 2020b; He et al. 2020a; Tian, Krishnan, and Isola 2020), there exists a self supervision between differently generated views of the same data.”
• BoT-SORT: Robust Associations Multi-Pedestrian Tracking (2022, methodology): “For the feature extractor, we trained FastReID’s [19] SBS-50 model for MOT17 and MOT20 with their default training strategy, for 60 epochs.”
• ByteTrack: Multi-Object Tracking by Associating Every Detection Box (2021, methodology): “In ablation study, we use FastReID [27] to extract Re-ID features for MOT17.”
• Deep OC-Sort: Multi-Pedestrian Tracking by Adaptive Re-Identification (2023, methodology): “For Re-ID, we use SBS50 from the fast-reid [29] library.”