Related papers: Convolutional Networks with Adaptive Inference Gra…

Systematic relations between multiple objects that occur in various fields can be represented as networks. Real-world networks typically exhibit complex topologies whose structural properties are key factors in characterizing and further…

We propose a novel method that trains a conditional Generative Adversarial Network (GAN) to generate visual interpretations of a Convolutional Neural Network (CNN). To comprehend a CNN, the GAN is trained with information on how the CNN…

Improving information flow in deep networks helps to ease the training difficulties and utilize parameters more efficiently. Here we propose a new convolutional neural network architecture with alternately updated clique (CliqueNet). In…

Deep learning has gained great success in various classification tasks. Typically, deep learning models learn underlying features directly from data, and no underlying relationship between classes are included. Similarity between classes…

In traditional Graph Neural Networks (GNN), graph convolutional learning is carried out through topology-driven recursive node content aggregation for network representation learning. In reality, network topology and node content are not…

Traditionally, deep convolutional neural networks consist of a series of convolutional and pooling layers followed by one or more fully connected (FC) layers to perform the final classification. While this design has been successful, for…

Many different classification tasks need to manage structured data, which are usually modeled as graphs. Moreover, these graphs can be dynamic, meaning that the vertices/edges of each graph may change during time. Our goal is to jointly…

Deep learning algorithms have been known to be vulnerable to adversarial perturbations in various tasks such as image classification. This problem was addressed by employing several defense methods for detection and rejection of particular…

Link prediction for knowledge graphs is the task of predicting missing relationships between entities. Previous work on link prediction has focused on shallow, fast models which can scale to large knowledge graphs. However, these models…

As object recognition becomes an increasingly common ML task, and recent research demonstrating CNNs vulnerability to attacks and small image perturbations necessitate fully understanding the foundations of object recognition. We focus on…

Recently, the deep learning community has given growing attention to neural architectures engineered to learn problems in relational domains. Convolutional Neural Networks employ parameter sharing over the image domain, tying the weights of…

Material classification in natural settings is a challenge due to complex interplay of geometry, reflectance properties, and illumination. Previous work on material classification relies strongly on hand-engineered features of visual…

The majority of medical images, especially those that resemble cells, have similar characteristics. These images, which occur in a variety of shapes, often show abnormalities in the organ or cell region. The convolution operation possesses…

The convolution neural nets (conv nets) have achieved a state-of-the-art performance in many applications of image and video processing. The most recent studies illustrate that the conv nets are fragile in terms of recognition accuracy to…

The structural and spatial arrangements of cells within tissues represent their functional states, making graph-based learning highly suitable for histopathology image analysis. Existing methods often rely on fixed graphs with predefined…

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…

While deeper convolutional networks are needed to achieve maximum accuracy in visual perception tasks, for many inputs shallower networks are sufficient. We exploit this observation by learning to skip convolutional layers on a per-input…

Generative Adversarial Networks (GANs) have been very successful for synthesizing the images in a given dataset. The artificially generated images by GANs are very realistic. The GANs have shown potential usability in several computer…

The rapid progress in image classification has been largely driven by the adoption of Graph Convolutional Networks (GCNs), which offer a robust framework for handling complex data structures. This study introduces a novel approach that…

Knowledge graphs are graphical representations of large databases of facts, which typically suffer from incompleteness. Inferring missing relations (links) between entities (nodes) is the task of link prediction. A recent state-of-the-art…