Hierarchical Transfer Multi-task Learning Approach for Scene Classification

Reza Khoshkangini*, Mohsen Tajgardan, Mahtab Jamali, Martin Georg Ljungqvist, Radu-Casian Mihailescu, Paul Davidsson

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a novel Hierarchical Transfer and Multi-task Learning (HTMTL) approach designed to substantially improve the performance of scene classification networks by leveraging the collective influence of diverse scene types. HTMTL is distinguished by its ability to capture the interaction between various scene types, recognizing how context information from one scene category can enhance the classification performance of another. Our method, when applied to the Places365 dataset, demonstrates a significant improvement in the network’s ability to accurately identify scene types. By exploiting these inter-scene interactions, HTMTL significantly enhances scene classification performance, making it a potent tool for advancing scene understanding and classification. Additionally, this study explores the contribution of individual tasks and task groupings on the performance of other tasks. To further validate the generality of HTMTL, we applied it to the Cityscapes dataset, where the results also show promise. This indicates the broad applicability and effectiveness of our approach across different datasets and scene types.

Original languageEnglish
Title of host publicationPattern Recognition
Subtitle of host publication27th International Conference, ICPR 2024, Kolkata, India, December 1–5, 2024, Proceedings, Part I
EditorsApostolos Antonacopoulos, Subhasis Chaudhuri, Rama Chellappa, Cheng-Lin Liu, Saumik Bhattacharya, Umapada Pal
PublisherSpringer
Pages231-248
Number of pages18
ISBN (Electronic)978-3-031-78107-0
ISBN (Print)978-3-031-78106-3
DOIs
Publication statusPublished - 2025
Event27th International Conference on Pattern Recognition, ICPR 2024 - Kolkata, India
Duration: 1 Dec 20245 Dec 2024

Publication series

NameLecture Notes in Computer Science
Volume15301
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference27th International Conference on Pattern Recognition, ICPR 2024
Country/TerritoryIndia
CityKolkata
Period1/12/245/12/24

Keywords

  • Multi-task Learning
  • Scene Classification
  • Transfer Learning

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Hierarchical Transfer Multi-task Learning Approach for Scene Classification'. Together they form a unique fingerprint.

Cite this