Multi-level Feature Aggregation Network for Person Re-identification
Authors:
- 25 August 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 168-171
Abstract
Current person re-identification works focus on the deep features, ignoring the loss of detailed features due to downsampling operations. We propose a parallel structured Multi-level Feature Aggregation network (MFA-Net), which not only aggregates the information of local features within the same level as that of global features but also aggregates the features between different levels in an orderly manner as a way to mine the overlooked features. Furthermore, experiments on three datasets Market1501, DukeMTMC-RelD and MSMT17, show that our MFA-Net can further mine the detailed features, enhance the feature representation, and achieve state-of-the-art results on three benchmark datasets.Keywords
This publication has 23 references indexed in Scilit:
- Leader-Based Multi-Scale Attention Deep Architecture for Person Re-IdentificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification2019
- Unsupervised Embedding Learning via Invariant and Spreading Instance Feature2019
- Person Re-identification with Deep Similarity-Guided Graph Neural Network2018
- Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)2018
- Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro2017
- Deeply-Learned Part-Aligned Representations for Person Re-identification2017
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization2017
- Scalable Person Re-identification on Supervised Smoothed Manifold2017
- Deep Residual Learning for Image Recognition2016