Khondaker Tasrif Noor
BSc. in EEE | MEng. in Electronics | PhD in Computer Vision (Expected)
Researcher: Computer Vision | Machine Learning | Deep Learning
Deakin University | Geelong, VIC, Australia
Research Publications
2025
- 5.Noor, K. T., Luo, W., Robles-Kelly, A., Zhang, L. Y., & Bouadjenek, M. R. (2025). Taxonomy-Guided Routing in Capsule Network for Hierarchical Multi-Label Image Classification (SSRN Scholarly Paper No. 5127434). Social Science Research Network. https://doi.org/10.2139/ssrn.5127434
Hierarchical classification is a significant challenge in computer vision due to the logical order and interconnectedness of multiple labels. This paper presents HD-CapsNet, a novel neural network architecture based on deep capsule networks, specifically designed for hierarchical multi-label classification(HMC). By incorporating a tree-like hierarchical structure, HD-CapsNet is designed to leverage the inherent ontological order within the hierarchical label tree, thereby ensuring classification consistency across different levels. Additionally, we introduce a specialized loss function that promotes accurate hierarchical relationships while penalizing inconsistencies. This not only enhances classification performance but also strengthens the network’s robustness. We rigorously evaluate HD-CapsNet’s efficacy by benchmarking it against existing HMC methods across six diverse datasets: Fashion-MNIST, Marine-Tree, CIFAR-10, CIFAR-100, Caltech-UCSD Birds-200-2011, and Stanford Cars. Our results conclusively demonstrate that HD-CapsNet excels in learning hierarchical relationships and significantly outperforms the competition in various image classification tasks.
2024
- 4.K. T. Noor, A. Robles-Kelly, L. Y. Zhang, M. R. Bouadjenek, and W. Luo, ‘A consistency-aware deep capsule network for hierarchical multi-label image classification’, Neurocomputing, vol. 604, p. 128376, Nov. 2024, doi: 10.1016/j.neucom.2024.128376.
Hierarchical classification is a significant challenge in computer vision due to the logical order and interconnectedness of multiple labels. This paper presents HD-CapsNet, a novel neural network architecture based on deep capsule networks, specifically designed for hierarchical multi-label classification(HMC). By incorporating a tree-like hierarchical structure, HD-CapsNet is designed to leverage the inherent ontological order within the hierarchical label tree, thereby ensuring classification consistency across different levels. Additionally, we introduce a specialized loss function that promotes accurate hierarchical relationships while penalizing inconsistencies. This not only enhances classification performance but also strengthens the network’s robustness. We rigorously evaluate HD-CapsNet’s efficacy by benchmarking it against existing HMC methods across six diverse datasets: Fashion-MNIST, Marine-Tree, CIFAR-10, CIFAR-100, Caltech-UCSD Birds-200-2011, and Stanford Cars. Our results conclusively demonstrate that HD-CapsNet excels in learning hierarchical relationships and significantly outperforms the competition in various image classification tasks.
- 3.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.
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.
2023
- 2.K. T. Noor, A. Robles-Kelly, L. Y. Zhang, and M. R. Bouadjenek, ‘A Bottom-Up Capsule Network for Hierarchical Image Classification’, in 2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Nov. 2023, pp. 325–331. doi: 10.1109/DICTA60407.2023.00052.
Hierarchical image classification is an arduous task in deep learning and computer vision. It requires classifying multiple image classes following a taxonomy or data hierarchy. This paper introduces a bottom-up hierarchical capsule network (BUH-CapsNet) designed to address hierarchical multi-label classification. The hierarchical structure of BUH-CapsNet allows it to build a tree-like structure for classification problems, making use of the data hierarchy. This structure enables the network to learn more complex relationships in the taxonomy by balancing the hierarchical levels and following the fine-to-coarse paradigm, leading to more accurate classification results. Furthermore, the bottom-up architecture of the BUH-CapsNet enforces hierarchical consistency, using the hierarchical structure of the datasets. We trained our BUH-CapsNet considering the hierarchical level weights that keep a balance between the levels. Experiments on six widely available datasets show that BUH-CapsNet achieves better results than existing multi-label classification methods and performs better when handling hierarchical labels.
2022
- 1.K. T. Noor, A. Robles-Kelly, and B. Kusy, ‘A Capsule Network for Hierarchical Multi-label Image Classification’, in Structural, Syntactic, and Statistical Pattern Recognition, A. Krzyzak, C. Y. Suen, A. Torsello, and N. Nobile, Eds., in Lecture Notes in Computer Science. Cham: Springer International Publishing, 2022, pp. 163–172. doi: 10.1007/978-3-031-23028-8_17.
Image classification is one of the most important areas in computer vision. Hierarchical multi-label classification applies when a multi-class image classification problem is arranged into smaller ones based upon a hierarchy or taxonomy. Thus, hierarchical classification modes generally provide multiple class predictions on each instance, whereby these are expected to reflect the structure of image classes as related to one another. In this paper, we propose a multi-label capsule network (ML-CapsNet) for hierarchical classification. Our ML-CapsNet predicts multiple image classes based on a hierarchical class-label tree structure. To this end, we present a loss function that takes into account the multi-label predictions of the network. As a result, the training approach for our ML-CapsNet uses a coarse to fine paradigm while maintaining consistency with the structure in the classification levels in the labelhierarchy. We also perform experiments using widely available datasets and compare the model with alternatives elsewhere in the literature. In our experiments, our ML-CapsNet yields a margin of improvement with respect to these alternative methods.