Khondaker Tasrif Noor

Khondaker Tasrif Noor

Khondaker Tasrif Noor is a researcher at Deakin University with a focus on Deep Learning, Computer Vision, and Machine Learning. He is a recipient of the prestigious Deakin University Postgraduate Research Scholarship (DUPR). He has published numerous papers in top-tier journals and conferences. He is also a member of the Australian Pattern Recognition Society (APRS). He is a reviewer of several top-tier journals and conferences.

H-CapsNet: A capsule network for hierarchical image classification

Published in Pattern Recognition, 2024

In this paper, we present H-CapsNet, a capsule network for hierarchical image classification. Our network makes use of the natural capacity of CapsNets (capsule networks) to capture hierarchical relationships. Thus, our network is such that each multi-layer capsule network accounts for each of the class hierarchies using dedicated capsules. Further, we make use of a modified hinge loss that enforces consistency amongst the hierarchies involved. We also present a strategy to dynamically adjust the training parameters to achieve a better balance between the class hierarchies under consideration. We have performed experiments using several widely available datasets and compared them against several alternatives. In our experiments, HCapsNet delivers a margin of improvement over competing hierarchical classification networks elsewhere in the literature.

Recommended citation: K. T. Noor and A. Robles-Kelly, ‘H-CapsNet: A capsule network for hierarchical image classification’, Pattern Recognition, vol. 147, p. 110135, Mar. 2024, doi: 10.1016/j.patcog.2023.110135.
Download Paper