Multiple VLAD encoding of CNNs for image classification
This work addresses image classification challenges by enhancing feature representation, but it appears incremental as it builds on established VLAD and SPM techniques.
The paper tackled the limitation of CNNs in capturing variation information in images by proposing a multiple VLAD encoding framework with spatial pyramid matching, resulting in improved performance over existing methods.
Despite the effectiveness of convolutional neural networks (CNNs) especially in image classification tasks, the effect of convolution features on learned representations is still limited. It mostly focuses on the salient object of the images, but ignores the variation information on clutter and local. In this paper, we propose a special framework, which is the multiple VLAD encoding method with the CNNs features for image classification. Furthermore, in order to improve the performance of the VLAD coding method, we explore the multiplicity of VLAD encoding with the extension of three kinds of encoding algorithms, which are the VLAD-SA method, the VLAD-LSA and the VLAD-LLC method. Finally, we equip the spatial pyramid patch (SPM) on VLAD encoding to add the spatial information of CNNs feature. In particular, the power of SPM leads our framework to yield better performance compared to the existing method.