Tóm tắt:
Large-scale multi-class image classification is essential for big data applications. One of the challenges is to deal with situations in which the number of classes is very large and for which the standard one-versus-all method is not appropriate because its computational complexity is linear in the number of classes. Using a label tree is a popular way to reduce complexity. By organizing classes into a hierarchical structure, the number of classifier evaluations of a test sample when traveling from the root node to a leaf node is significantly reduced. Having a balanced learned tree is essential to this approach. The current methods for learning the tree structure use clustering techniques, such as k-means or spectral clustering, to group confusing classes into clusters associated with the nodes. However, the output tree in such cases might not be balanced. In this paper, we propose a method for learning effective and balanced trees by jointly optimizing balance and confusion constraints. Experimental results on large-scale datasets including Caltech-256, SUN-397, ILSVRC2010-1K, and ImageNet-10K, show that our method outperforms other state-of-the-art methods.
Tác giả: Tien-Dung Mai; Thanh Duc Ngo; Duy-Dinh Le; Duc Anh Duong; Kiem Hoang; Shin’ichi Satoh
Từ khóa: Large-Scale Image Classification; Multi-Class Classification; Label Tree Learning; Balanced Tree; Hierarchical Classification; Clustering
Tạp chí: Computer Vision and Image Understanding
Chỉ số: ISSN: 1077-3142; Thomson ISI, SCI, Scorpus, SCI IF: 2.134
Link tải: https://www.sciencedirect.com/science/article/abs/pii/S1077314216301631
SAIGON INTERNATIONAL UNIVERSITY (SIU) THAODIEN CAMPUS
Lewis Hall: 8C Tống Hữu Định, Phường Thảo Điền, TP.Thủ Đức, TPHCM, Việt Nam
Eliot Hall: 7, 9 Tống Hữu Định, Phường Thảo Điền, TP.Thủ Đức, TPHCM, Việt Nam
McCarthy Hall: 10 Tống Hữu Định, Phường Thảo Điền, TP.Thủ Đức, TPHCM, Việt Nam
Fleming Hall: 16 Tống Hữu Định, Phường Thảo Điền, TP.Thủ Đức, TPHCM, Việt Nam
Đông A Hall: 18 Tống Hữu Định, Phường Thảo Điền, TP.Thủ Đức, TPHCM, Việt Nam
SIU GRADUATE SCHOOL
11 Tống Hữu Định, Phường Thảo Điền, TP.Thủ Đức, TPHCM, Việt Nam
226A Pasteur, Phường Võ Thị Sáu, Quận 3, TPHCM, Việt Nam
Hotline: 0933180765; 0985610648
Tel: 028.36203932 (ext. 200)
Email: siug@siu.edu.vn