Improvement of One-Shot-Learning by Integrating a Convolutional Neural Network and an Image Descriptor into a Siamese Neural Network

Abstract

Over the last few years, several techniques have been developed with the aim of implementing one-shot learning, a concept that allows classifying images with only a single image per training category. Conceptually, these methods seek to reproduce certain behavior that humans have. People are able to recognize a person they have only seen once, but they are probably not able to do the same with certain animals, such as a monkey. This is because our brains have been trained for years with images of people but not so much of animals. Among the one-shot learning techniques, some of them have used data generation, such as Generative Adversarial Networks (GAN). Other techniques have been based on the matching of descriptors traditionally used for object detection. Finally, one of the most prominent techniques involves using Siamese neural networks. Siamese networks are usually implemented with two convolutional nets that share their weights. They receive two images as input and can detect whether they belong to the same category or not. In the field of grocery products, there has been a lot of research on the one-shot learning problem but not so much on the use of Siamese networks. In this paper, several classifiers are firstly evaluated to decide on a convolutional model to be used with the Siamese and to improve the baseline results obtained in the dataset used. Then, two existing techniques are integrated within the Siamese model: a convolutional net and a Local Maximal Occurrence (LOMO) descriptor. The latter was initially used for the re-identification of people although it has shown its effectiveness to improve the values of a traditional Siamese with only convolutional sisters. The whole network is trained on categories and responds to different categories, showing its strong capacity to deal with the problem of having only one image per category.

CerviCell-detector: An object detection approach for identifying the cancerous cells in pap smear images of cervical cancer

“…Detectron2 is written in PyTorch with an extra layer called Detectron2go [ 34 ]. In our experimentation, we used the ResNeXt-101-32 × 8d model from the framework [ 35 ]. The ResNeXt models are pre-trained on 940 million Instagram images with 1000 ImageNet1K synsets.…”

Siamese DeNPE network framework for fault detection of batch process

“…Siamese networks are widely used in process situations with limited data due to their effectiveness in dealing with small samples of data. [30][31][32] Qin and Hu [33] proposed an ANS-Net framework for measuring inherent differences by using a small number of signals, and established a fault diagnosis model. Yang et al [34] utilized a Siamese two-dimensional convolutional neural network to extract the feature vectors of the input fault signal couple.…”