Siamese Network of Deep Fisher-Vector Descriptors for Image Retrieval
This addresses the problem of accurately ranking image similarity for large-scale retrieval, representing an incremental advancement by integrating and jointly learning existing components.
The paper tackles large-scale image retrieval by proposing a Siamese network that combines CNN and Fisher Vector components, learning both simultaneously to improve accuracy. It achieves significant improvements over state-of-the-art methods on Oxford and Paris datasets, with baseline performance measures including 1 million distractors.
This paper addresses the problem of large scale image retrieval, with the aim of accurately ranking the similarity of a large number of images to a given query image. To achieve this, we propose a novel Siamese network. This network consists of two computational strands, each comprising of a CNN component followed by a Fisher vector component. The CNN component produces dense, deep convolutional descriptors that are then aggregated by the Fisher Vector method. Crucially, we propose to simultaneously learn both the CNN filter weights and Fisher Vector model parameters. This allows us to account for the evolving distribution of deep descriptors over the course of the learning process. We show that the proposed approach gives significant improvements over the state-of-the-art methods on the Oxford and Paris image retrieval datasets. Additionally, we provide a baseline performance measure for both these datasets with the inclusion of 1 million distractors.