Recent innovations in training deep convolutional neural network models have motivated the design of new methods to automatically learn local image descriptors. The latest deep ConvNets proposed for this task consist(from machine learning show that replacing this siamese by a triplet network can improve the classification accuracy in several problems, but this has yet to be demonstrated for local image descr iptor learning. Moreover, current siamese and triplet networks have been trained with stochastic gradient descent that computes)