Learning mid-level features from object hierarchy for image classification

Somayah Albaradei, Yang Wang, Liangliang Cao, Li-Jia Li

Abstract: We propose a new approach for constructing mid-level visual features for image classification. We represent an image using the outputs of a collection of binary classifiers. These binary classifiers are trained to differentiate pairs of object classes in an object hierarchy. Our feature representation implicitly captures the hierarchical structure in object classes. We show that our proposed approach outperforms other baseline methods in image classification.