Lightweight Multi-Branch Network For Person Re-Identification

  title={Lightweight Multi-Branch Network For Person Re-Identification},
  author={Fabian Herzog and Xunbo Ji and Torben Teepe and Stefan H{\"o}rmann and Johannes Gilg and Gerhard Rigoll},
  journal={2021 IEEE International Conference on Image Processing (ICIP)},
Person Re-Identification aims to retrieve person identities from images captured by multiple cameras or the same cameras in different time instances and locations. Because of its importance in many vision applications from surveillance to human-machine interaction, person re-identification methods need to be reliable and fast. While more and more deep architectures are proposed for increasing performance, those methods also increase overall model complexity. This paper proposes a lightweight… 

Figures and Tables from this paper

Person Re-Identification with a Locally Aware Transformer
A novel Locally Aware Transformer (LA-Transformer) that employs a Parts-based Convolution Baseline (PCB)-inspired strategy for aggregating globally enhanced local classification tokens into an ensemble of √ N classifiers, where N is the number of patches.
Benchmarks for Corruption Invariant Person Re-identification
This work comprehensively establishes five ReID benchmarks for learning corruption invariant representation in singleand cross-modality datasets, including Market-1501, CUHK03, MSMT17, RegDB, SYSU-MM01, and proposes a strong baseline on both single and cross- modality ReID datasets which achieves improved robustness against diverse corruptions.
Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification
A model without trainable parameters is presented which shows great potential for high generalization and combines a fully analytical feature extraction and similarity ranking scheme with DL-based human parsing used to obtain the initial subregion classification and is shown to be higher than previously reported 30-50% transfer accuracy.
Building Unmanned Store Identification Systems Using YOLOv4 and Siamese Network
This paper uses multiple deep learning models to solve the problems often encountered in unmanned stores, and proposes a method for calculating stacked goods, so that the space can be effectively used.


Deep Learning for Person Re-Identification: A Survey and Outlook
A powerful AGW baseline is designed, achieving state-of-the-art or at least comparable performance on twelve datasets for four different Re-ID tasks, and a new evaluation metric (mINP) is introduced, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re- ID system for real applications.
Person Re-identification: Past, Present and Future
The history of person re-identification and its relationship with image classification and instance retrieval is introduced and two new re-ID tasks which are much closer to real-world applications are described and discussed.
Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
A novel coarse-to-fine pyramid model is proposed to relax the need of bounding boxes and learn discriminative identity representation, which not only incorporates local and global information, but also integrates the gradual cues between them.
Batch DropBlock Network for Person Re-Identification and Beyond
The Batch DropBlock (BDB) Network is a two branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch that achieves state-of-the-art on person re-identification and it is also applicable to general metric learning tasks.
Learning Diverse Features with Part-Level Resolution for Person Re-Identification
Empirical evidence demonstrates that the proposed PLR-OSNet achieves state-of-the-art performance on popular person Re-ID datasets, including Market1501, DukeMTMC-reID and CUHK03, despite its small model size.
Omni-Scale Feature Learning for Person Re-Identification
A novel deep ReID CNN is designed, termed Omni-Scale Network (OSNet), for omni-scale feature learning by designing a residual block composed of multiple convolutional feature streams, each detecting features at a certain scale.
Bag of Tricks and a Strong Baseline for Deep Person Re-Identification
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.
Learning Discriminative and Generalizable Representations by Spatial-Channel Partition for Person Re-Identification
This study proposes an end-to-end Spatial and Channel partition Representation network (SCR) in order to better exploit both spatial and channel information in Person Re-Identification task.
Scalable Person Re-identification: A Benchmark
A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset.
Compact Network Training for Person ReID
This study focuses on a small-sized randomly initialized model that enables us to easily introduce architecture and training modifications suitable for person ReID and shows the robustness of the network by outperforming the SotA on both Market1501 and DukeMTMC.