Large scale multi-class classification using latent classifiers

Tóm tắt:

We study the problem of multi-class image classification with large number of classes, of which the one-vs-all based approach is prohibitive in practical applications. Recent state-of-the-art approaches rely on label tree to reduce classification complexity. However, building optimal tree structures and learning precise classifiers to optimize tree loss is challenging. In this paper, we introduce a novel approach using latent classifiers that can achieve comparable speed but better performance. The key idea is that instead of using C one-vs-all classifiers (C is the number of classes) to generate the score matrix for label prediction, a much smaller number of classifiers are used. These classifiers, called latent classifiers, are generated by analyzing the correlation among classes and removing redundancy. Experiments on several large datasets including ImageNet-1K, SUN-397, and Caltech-256 show the efficiency of our approach.

Tác giả: Tien-Dung Mai; Thanh Duc Ngo; Duy-Dinh Le; Duc Anh Duong; Kiem Hoang; Shin’ichi Satoh

Từ khóa: Testing, Matrix decomposition, Training, Complexity theory, Encoding, Sparse matrices, Correlation

Tạp chí: 2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)

Chỉ số: Electronic ISBN:978-1-4673-7478-1; USB ISBN:978-1-4673-7477-4; Thomson ISI, EI, Scorpus.

Link tải: https://ieeexplore.ieee.org/document/7340800