Learning High-level Image Representation for Image Retrieval via Multi-Task DNN using Clickthrough Data
This work addresses the gap between low-level image features and high-level query semantics for image retrieval systems, representing an incremental improvement.
The paper tackled the problem of image retrieval by proposing a multi-task deep neural network to learn high-level image representations from clickthrough data, showing effectiveness in experiments on simulated and real datasets.
Image retrieval refers to finding relevant images from an image database for a query, which is considered difficult for the gap between low-level representation of images and high-level representation of queries. Recently further developed Deep Neural Network sheds light on automatically learning high-level image representation from raw pixels. In this paper, we proposed a multi-task DNN learned for image retrieval, which contains two parts, i.e., query-sharing layers for image representation computation and query-specific layers for relevance estimation. The weights of multi-task DNN are learned on clickthrough data by Ring Training. Experimental results on both simulated and real dataset show the effectiveness of the proposed method.