TY - GEN
T1 - Hierarchical Transfer Multi-task Learning Approach for Scene Classification
AU - Khoshkangini, Reza
AU - Tajgardan, Mohsen
AU - Jamali, Mahtab
AU - Ljungqvist, Martin Georg
AU - Mihailescu, Radu-Casian
AU - Davidsson, Paul
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - 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.
AB - 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.
KW - Multi-task Learning
KW - Scene Classification
KW - Transfer Learning
UR - http://www.scopus.com/inward/record.url?scp=85211958209&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-78107-0_15
DO - 10.1007/978-3-031-78107-0_15
M3 - Conference contribution
AN - SCOPUS:85211958209
SN - 978-3-031-78106-3
T3 - Lecture Notes in Computer Science
SP - 231
EP - 248
BT - Pattern Recognition
A2 - Antonacopoulos, Apostolos
A2 - Chaudhuri, Subhasis
A2 - Chellappa, Rama
A2 - Liu, Cheng-Lin
A2 - Bhattacharya, Saumik
A2 - Pal, Umapada
PB - Springer
T2 - 27th International Conference on Pattern Recognition, ICPR 2024
Y2 - 1 December 2024 through 5 December 2024
ER -