Related papers: ReSet: Learning Recurrent Dynamic Routing in ResNe…

Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the…

Image classification has become one of the main tasks in the field of computer vision technologies. In this context, a recent algorithm called CapsNet that implements an approach based on activity vectors and dynamic routing between…

Dynamic routing networks, aimed at finding the best routing paths in the networks, have achieved significant improvements to neural networks in terms of accuracy and efficiency. In this paper, we see dynamic routing networks in a fresh…

In this paper, we present a high-performance and light-weight deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the aerial scene of a remote sensing image. To this end, we first valuate various…

Recurrent neural networks (RNN) are popular for many computer vision tasks, including multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered for the multi-label classification task. Current approaches…

Convolutional Neural Networks (CNNs) have demonstrated remarkable success in image classification tasks; however, the choice between designing a custom CNN from scratch and employing established pre-trained architectures remains an…

The use of deep learning (DL) in medical image analysis has significantly improved the ability to predict lung cancer. In this study, we introduce a novel deep convolutional neural network (CNN) model, named ResNet+, which is based on the…

Recent work suggests goal-driven training of neural networks can be used to model neural activity in the brain. While response properties of neurons in artificial neural networks bear similarities to those in the brain, the network…

One practice of employing deep neural networks is to apply the same architecture to all the input instances. However, a fixed architecture may not be representative enough for data with high diversity. To promote the model capacity,…

We introduce a biologically inspired, multilayer neural architecture composed of Rectified Spectral Units (ReSUs). Each ReSU projects a recent window of its input history onto a canonical direction obtained via canonical correlation…

Deep neural networks have been widely used in computer vision. There are several well trained deep neural networks for the ImageNet classification challenge, which has played a significant role in image recognition. However, little work has…

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise.…

How can neural networks such as ResNet efficiently learn CIFAR-10 with test accuracy more than 96%, while other methods, especially kernel methods, fall relatively behind? Can we more provide theoretical justifications for this gap?…

Medical image segmentation have drawn massive attention as it is important in biomedical image analysis. Good segmentation results can assist doctors with their judgement and further improve patients' experience. Among many available…

In recent days, with increased population and traffic on roadways, vehicle collision is one of the leading causes of death worldwide. The automotive industry is motivated on developing techniques to use sensors and advancements in the field…

ImageNet serves as the primary dataset for evaluating the quality of computer-vision models. The common practice today is training each architecture with a tailor-made scheme, designed and tuned by an expert. In this paper, we present a…

ResNet or DenseNet? Nowadays, most deep learning based approaches are implemented with seminal backbone networks, among them the two arguably most famous ones are ResNet and DenseNet. Despite their competitive performance and overwhelming…

Filters in convolutional networks are typically parameterized in a pixel basis, that does not take prior knowledge about the visual world into account. We investigate the generalized notion of frames designed with image properties in mind,…

Accurate segmentation is crucial for clinical applications, but existing models often assume fixed, high-resolution inputs and degrade significantly when faced with lower-resolution data in real-world scenarios. To address this limitation,…

Document structure analysis, such as zone segmentation and table recognition, is a complex problem in document processing and is an active area of research. The recent success of deep learning in solving various computer vision and machine…