Deep visual words: Improved fisher vector for image classification
Ali Diba, Ali Mohammad Pazandeh, Luc Van Gool · 2017
Image classification has been revolutionized by deep convolutiosnal neural networks. Using previous state-of-the-art classification methods like Fisher vector encoding in combination with deep CNNs has been shown to be promising. Motivated by the recent work on dense CNN features to extract Fisher encoding(FV-CNN), we present a scheme to discover better visual words with CNNs, to obtain improved Fisher vector features. Our method (Deep Visual Words-DVW) learns semantic visual clusters per each category, by iteratively learning and refining groups of visual patches. DVW represents an efficient feature space embedding to capture the discriminative potential between meaningful visual clusters. We evaluate our approach on popular datasets in object, scene and action classification and outperformed the state-of-the-art: scene classification MIT indoor, object categorization PASCAL VOC 2007 and Stanford40 human actions.