The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
개인 재식별은 지난 몇 년간 광범위한 연구를 거쳐 인상적인 진전을 이루었습니다. 최근 뛰어난 방법들은 심층 신경망의 특징 맵을 여러 개의 줄무늬로 분할하여 구별되는 특징을 추출합니다. 여전히 슬라이스 기반 방법을 촉진하는 데 도움이 될 수 있는 기능 융합 및 메트릭 학습 전략이 개선되었습니다. 본 논문에서는 다양한 수준과 신체 부위 모두의 특징을 포착하기 위해 MSN(Multi-level Slice-based Network)이라는 종단 간 훈련이 가능한 새로운 프레임워크를 제안합니다. 우리 모델은 이중 분기 네트워크 아키텍처로 구성됩니다. 하나는 전역 기능 추출을 위한 분기이고 다른 하나는 로컬 특징 추출을 위한 분기입니다. 두 가지 모두 피라미드 기능 유사 모듈을 사용하여 다중 레벨 기능을 처리합니다. 글로벌 기능과 로컬 기능을 연결함으로써 고유한 기능을 활용하고 적절하게 비교합니다. 또한 제안된 방법은 정교한 결합 손실 함수에 삼중항 중심 손실을 창의적으로 도입하여 공동 학습 네트워크를 훈련하는 데 도움이 됩니다. Market-1501, DukeMTMC, CUHK03을 포함한 주류 평가 데이터 세트에 대한 포괄적인 실험을 통해 우리가 제안한 모델이 강력하게 뛰어난 성능을 달성하고 기존 접근 방식보다 성능이 뛰어남을 나타냅니다. 예를 들어, 단일 쿼리 모드의 DukeMTMC 데이터세트에서 Rank-1/mAP =85.9%(+1.0%)/74.2%(+4.7%)라는 훌륭한 결과를 얻습니다.
Yusheng ZHANG
South China University of Technology
Zhiheng ZHOU
South China University of Technology
Bo LI
South China University of Technology
Yu HUANG
South China University of Technology
Junchu HUANG
South China University of Technology
Zengqun CHEN
South China University of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Yusheng ZHANG, Zhiheng ZHOU, Bo LI, Yu HUANG, Junchu HUANG, Zengqun CHEN, "Improving Slice-Based Model for Person Re-ID with Multi-Level Representation and Triplet-Center Loss" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 11, pp. 2230-2237, November 2019, doi: 10.1587/transinf.2019EDP7067.
Abstract: Person Re-Identification has received extensive study in the past few years and achieves impressive progress. Recent outstanding methods extract discriminative features by slicing feature maps of deep neural network into several stripes. Still there have improvement on feature fusion and metric learning strategy which can help promote slice-based methods. In this paper, we propose a novel framework that is end-to-end trainable, called Multi-level Slice-based Network (MSN), to capture features both in different levels and body parts. Our model consists of a dual-branch network architecture, one branch for global feature extraction and the other branch for local ones. Both branches process multi-level features using pyramid feature alike module. By concatenating the global and local features, distinctive features are exploited and properly compared. Also, our proposed method creatively introduces a triplet-center loss to elaborate combined loss function, which helps train the joint-learning network. By demonstrating the comprehensive experiments on the mainstream evaluation datasets including Market-1501, DukeMTMC, CUHK03, it indicates that our proposed model robustly achieves excellent performance and outperforms many of existing approaches. For example, on DukeMTMC dataset in single-query mode, we obtain a great result of Rank-1/mAP =85.9%(+1.0%)/74.2%(+4.7%).
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7067/_p
부
@ARTICLE{e102-d_11_2230,
author={Yusheng ZHANG, Zhiheng ZHOU, Bo LI, Yu HUANG, Junchu HUANG, Zengqun CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Improving Slice-Based Model for Person Re-ID with Multi-Level Representation and Triplet-Center Loss},
year={2019},
volume={E102-D},
number={11},
pages={2230-2237},
abstract={Person Re-Identification has received extensive study in the past few years and achieves impressive progress. Recent outstanding methods extract discriminative features by slicing feature maps of deep neural network into several stripes. Still there have improvement on feature fusion and metric learning strategy which can help promote slice-based methods. In this paper, we propose a novel framework that is end-to-end trainable, called Multi-level Slice-based Network (MSN), to capture features both in different levels and body parts. Our model consists of a dual-branch network architecture, one branch for global feature extraction and the other branch for local ones. Both branches process multi-level features using pyramid feature alike module. By concatenating the global and local features, distinctive features are exploited and properly compared. Also, our proposed method creatively introduces a triplet-center loss to elaborate combined loss function, which helps train the joint-learning network. By demonstrating the comprehensive experiments on the mainstream evaluation datasets including Market-1501, DukeMTMC, CUHK03, it indicates that our proposed model robustly achieves excellent performance and outperforms many of existing approaches. For example, on DukeMTMC dataset in single-query mode, we obtain a great result of Rank-1/mAP =85.9%(+1.0%)/74.2%(+4.7%).},
keywords={},
doi={10.1587/transinf.2019EDP7067},
ISSN={1745-1361},
month={November},}
부
TY - JOUR
TI - Improving Slice-Based Model for Person Re-ID with Multi-Level Representation and Triplet-Center Loss
T2 - IEICE TRANSACTIONS on Information
SP - 2230
EP - 2237
AU - Yusheng ZHANG
AU - Zhiheng ZHOU
AU - Bo LI
AU - Yu HUANG
AU - Junchu HUANG
AU - Zengqun CHEN
PY - 2019
DO - 10.1587/transinf.2019EDP7067
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2019
AB - Person Re-Identification has received extensive study in the past few years and achieves impressive progress. Recent outstanding methods extract discriminative features by slicing feature maps of deep neural network into several stripes. Still there have improvement on feature fusion and metric learning strategy which can help promote slice-based methods. In this paper, we propose a novel framework that is end-to-end trainable, called Multi-level Slice-based Network (MSN), to capture features both in different levels and body parts. Our model consists of a dual-branch network architecture, one branch for global feature extraction and the other branch for local ones. Both branches process multi-level features using pyramid feature alike module. By concatenating the global and local features, distinctive features are exploited and properly compared. Also, our proposed method creatively introduces a triplet-center loss to elaborate combined loss function, which helps train the joint-learning network. By demonstrating the comprehensive experiments on the mainstream evaluation datasets including Market-1501, DukeMTMC, CUHK03, it indicates that our proposed model robustly achieves excellent performance and outperforms many of existing approaches. For example, on DukeMTMC dataset in single-query mode, we obtain a great result of Rank-1/mAP =85.9%(+1.0%)/74.2%(+4.7%).
ER -