Exploiting multigranular salient features with hierarchical multi-mode attention network for pedestrian re-IDentification

Yanbing GENG, Yongjian LIAN, Mingliang ZHOU*, Yixue KONG, Yinong ZHU

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

3 Citations (Scopus)

Abstract

In this paper, we propose an end-to-end hierarchical-based multi-mode attention network and adaptive fusion (HMAN-HAF) strategy to learn different-level salient features for re-ID tasks. First, according to each layer's characteristics, a hierarchical multi-mode attention network (HMAN) is designed to adopt different attention models for different-level salient feature learning. Specifically, refined channel-wise attention (CA) is adopted to capture high-level valuable semantic information, an attentive region model (AR) is used to detect salient regions in the low layer, and fused attention (FA) is designed to capture the salient regions of valuable channels in the middle layer. Second, a hierarchical adaptive fusion (HAF) is constructed to fulfill the complementary strengths of different-level salient features. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods on the following challenging benchmarks: Market-1501, DukeMTMC-reID and CUHK03.

Original languageEnglish
Article number102914
Number of pages12
JournalJournal of Visual Communication and Image Representation
Volume73
Early online date3 Oct 2020
DOIs
Publication statusPublished - Nov 2020
Externally publishedYes

Bibliographical note

Acknowledgement:
This work was supported in part by the General Program of National Natural Science Foundation of Chongqing under Grant cstc2020jcyjmsxmX0790, in part by the Fundamental Research Funds for the Central Universities under Grant 2020CDJ-LHZZ-052, in part by the Guangxi Key Laboratory of Cryptography and Information Security under Grant GCIS201906, and in part by the National Natural Science Fund of Shanxi Province under grant number 201901D111154.

Keywords

  • Fused attention
  • Hierarchical
  • Hierarchical adaptive fusion
  • Multi-mode attention network
  • Pedestrian re-identification

Fingerprint

Dive into the research topics of 'Exploiting multigranular salient features with hierarchical multi-mode attention network for pedestrian re-IDentification'. Together they form a unique fingerprint.

Cite this