A Neural Network to Retrieve Images from Text Queries
David Grangier, Samy Bengio · 2006
Abstract. This work presents a neural network for the retrieval of images from text queries. The proposed network is composed of two main modules: the first one extracts a global picture representation from local block descriptors while the second one aims at solving the retrieval problem from the extracted representation. Both modules are trained jointly to minimize a loss related to the retrieval performance. This approach is shown to be advantageous when compared to previous models relying on unsupervised feature extraction: average precision over Corel queries reaches 26.2 % for our model, which should be compared to 21.6 % for PAMIR, the best alternative. 1