TMTCPT: The Tree Method based on the Taxonomic Categorization and the Phylogenetic Tree for fine-grained categorization

Bameri, Fatemeh; Pourreza, Hamid Reza; Taherinia, Amir Hossein; Aliabadian, Mansour; Mortezapour, Hamidreza; Abdilzadeh, Raziyeh

doi:10.1016/j.biosystems.2020.104137

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [22], a binary tree hierarchy is built based on the visual features rather than the features extracted by CNNs, i.e., manual labeling is required. Similarly, Bameri et al [23] propose a hierarchical method for classification based on the phylogenetic information of birds, which means that additional information is needed when processing the dataset. In the above approaches [22,23], manual calibration is required to build the tree hierarchy, which requires various efforts.…”

Section: Related Workmentioning

confidence: 99%

A Self-Supervised Tree-Structured Framework for Fine-Grained Classification

et al. 2023

View full text Add to dashboard Cite

In computer vision, fine-grained classification has become an important issue in recognizing objects with slight visual differences. Usually, it is challenging to generate good performance when solving fine-grained classification problems using traditional convolutional neural networks. To improve the accuracy and training time of convolutional neural networks in solving fine-grained classification problems, this paper proposes a tree-structured framework by eliminating the effect of differences between clusters. The contributions of the proposed method include the following three aspects: (1) a self-supervised method that automatically creates a classification tree, eliminating the need for manual labeling; (2) a machine-learning matcher which determines the cluster to which an item belongs, minimizing the impact of inter-cluster variations on classification; and (3) a pruning criterion which filters the tree-structured classifier, retaining only the models with superior classification performance. The experimental evaluation of the proposed tree-structured framework demonstrates its effectiveness in reducing training time and improving the accuracy of fine-grained classification across various datasets in comparison with conventional convolutional neural network models. Specifically, for the CUB 200 2011, FGVC aircraft, and Stanford car datasets, the proposed method achieves a reduction in training time of 32.91%, 35.87%, and 14.48%, and improves the accuracy of fine-grained classification by 1.17%, 2.01%, and 0.59%, respectively.

show abstract