Relative attribute classification with deep-ranksvm

Ali Ahmed, Sara Atito and Yanıkoğlu, Berrin (2021) Relative attribute classification with deep-ranksvm. In: 25th International Conference on Pattern Recognition Workshops, ICPR 2020, Virtual, Online

Full text not available from this repository. (Request a copy)


Relative attributes indicate the strength of a particular attribute between image pairs. We introduce a deep Siamese network with rank SVM loss function, called Deep-RankSVM, that can decide which one of a pair of images has a stronger presence of a specific attribute. The network is trained in an end-to-end fashion to jointly learn the visual features and the ranking function. The trained network for an attribute can predict the relative strength of that attribute in novel images. We demonstrate the effectiveness of our approach against the state-of-the-art methods on four image benchmark datasets: LFW-10, PubFig, UTZap50K-2 and UTZap50K-lexi datasets. Deep-RankSVM surpasses state-of-art in terms of the average accuracy across attributes, on three of the four image benchmark datasets.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: Classification; Deep learning; Rank SVM; Relative attributes
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Berrin Yanıkoğlu
Date Deposited: 02 Sep 2022 10:49
Last Modified: 02 Sep 2022 10:49

Actions (login required)

View Item
View Item