NDLI: Multi-scale feature fusion network for person re-identification

Content Provider	IET Digital Library
Author	Wang, Yongjie Zhang, Wei Liu, Yanyan
Abstract	Recently, it is becoming a challenging work for person re-identification due to the problems of occlusion, blurring and posture. The key of effective person re-identification is to capture sufficient detailed features of a person's appearance in images. Different from previous methods, our method mainly focuses on fusing different visual clues only depending on the features of different levels and scales without additional assistance. The major contributions of our paper are the mixed pooling strategy with different kernels and the mixed loss function. Firstly, we adopt ResNet50 as our backbone. We have slightly modified the backbone, which does not use the down-sampling operation at the beginning of stage 4. Inspired by pyramid pooling structure, we pass the outputs of Res4 and Res5 through the average pooling layer and max pooling layer with different kernels and strides separately. Secondly, we combine the averaged triplet losses and the averaged softmax losses as the final loss of the whole network. Extensive experiments on three datasets (CUHK3, Market1501, DukeMTMC-reID) show that compared with many state-of-the-art methods in recent years, our model achieve higher accuracy.
Starting Page	4614
Ending Page	4620
Page Count	7
ISSN	17519659
Volume Number	14
e-ISSN	17519667
Issue Number	Issue 17, Dec (2020)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-ipr/14/17
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-ipr.2020.0008
Journal	IET Image Processing
Publisher Date	2021-01-18
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Average Pooling Layer Averaged Softmax Loss Averaged Triplet Loss Body Analysis Computer Vision And Image Processing Technique Convolutional Neural Nets Convolutional Neural Network Effective Person Re-identification Feature Extraction Image Classification Image Fusion Image Recognition Learning in AI Max-pooling Layer Mixed Loss Function Mixed Pooling Strategy Multiscale Feature Fusion Network Object Recognition Pose Estimation Pyramid Pooling Structure Res4 Res5 Sensor Fusion Softmax Loss Function Stride Pooling Layer Triplet Loss Function Visual Clues
Content Type	Text
Resource Type	Article
Subject	Signal Processing Electrical and Electronic Engineering Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Ear verification under uncontrolled conditions with convolutional neural networks

Improved deep face identification with multi-class pairwise discriminant loss

Fully convolutional networks for action recognition

Adaptive learning feature pyramid for object detection

Enhanced pooling method for convolutional neural networks based on optimal search theory

Deep Image Similarity Measurement Based on the Improved Triplet Network with Spatial Pyramid Pooling

Mask-guided class activation mapping network for person re-identification

Edge gradient feature and long distance dependency for image semantic segmentation

Person Re-Identification across Data Distributions Based on General Purpose DNN Object Detector

Multi-scale feature fusion network for person re-identification

Similar Documents

Ear verification under uncontrolled conditions with convolutional neural networks

Improved deep face identification with multi-class pairwise discriminant loss

Fully convolutional networks for action recognition

Adaptive learning feature pyramid for object detection

Enhanced pooling method for convolutional neural networks based on optimal search theory

Deep Image Similarity Measurement Based on the Improved Triplet Network with Spatial Pyramid Pooling

Mask-guided class activation mapping network for person re-identification

Edge gradient feature and long distance dependency for image semantic segmentation

Person Re-Identification across Data Distributions Based on General Purpose DNN Object Detector

Multi-scale feature fusion network for person re-identification