Related papers: Attention-gating for improved radio galaxy classif…
We present an attention mechanism inspired from definition of screened Coulomb potential. This attention mechanism was used to interpret the Graph Attention (GAT) model layers and training dataset by using a flexible and scalable framework…
Attention mechanisms have raised significant interest in the research community, since they promise significant improvements in the performance of neural network architectures. However, in any specific problem, we still lack a principled…
Graph-structured data arise naturally in many different application domains. By representing data as graphs, we can capture entities (i.e., nodes) as well as their relationships (i.e., edges) with each other. Many useful insights can be…
Deep learning has become a powerful tool for medical image analysis; however, conventional Convolutional Neural Networks (CNNs) often fail to capture the fine-grained and complex features critical for accurate diagnosis. To address this…
3D Convolutional Neural Network (3D CNN) captures spatial and temporal information on 3D data such as video sequences. However, due to the convolution and pooling mechanism, the information loss seems unavoidable. To improve the visual…
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks. Despite its powerful capacity to learn and generalize the model from few samples, GNN usually…
Attention has long been proposed by psychologists as important for effectively dealing with the enormous sensory stimulus available in the neocortex. Inspired by the visual attention models in computational neuroscience and the need of…
Music genre classification is a critical component of music recommendation systems, generation algorithms, and cultural analytics. In this work, we present an innovative model for classifying music genres using attention-based temporal…
Student attention is an indispensable input for uncovering their goals, intentions, and interests, which prove to be invaluable for a multitude of research areas, ranging from psychology to interactive systems. However, most existing…
Deep neural network models have recently draw lots of attention, as it consistently produce impressive results in many computer vision tasks such as image classification, object detection, etc. However, interpreting such model and show the…
Deep neural networks have achieved strong performance in genomic sequence classification; however, relating their predictions to biologically meaningful sequence patterns remains challenging. In this work, we present AttnGen, an…
In the current salient object detection network, the most popular method is using U-shape structure. However, the massive number of parameters leads to more consumption of computing and storage resources which are not feasible to deploy on…
Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability. Most current models use deterministic attention…
Convolutional Neural Networks (CNNs) excel in local spatial pattern recognition. For many vision tasks, such as object recognition and segmentation, salient information is also present outside CNN's kernel boundaries. However, CNNs struggle…
Graph neural networks have become the standard approach for dealing with learning problems on graphs. Among the different variants of graph neural networks, graph attention networks (GATs) have been applied with great success to different…
Attention--or attribution--maps methods are methods designed to highlight regions of the model's input that were discriminative for its predictions. However, different attention maps methods can highlight different regions of the input,…
We describe an Artificial Neural Network (ANN) approach to classification of galaxy images and spectra. ANNs can replicate the classification of galaxy images by a human expert to the same degree of agreement as that between two human…
Data-driven saliency has recently gained a lot of attention thanks to the use of Convolutional Neural Networks for predicting gaze fixations. In this paper we go beyond standard approaches to saliency prediction, in which gaze maps are…
We aim to better understand attention over nodes in graph neural networks (GNNs) and identify factors influencing its effectiveness. We particularly focus on the ability of attention GNNs to generalize to larger, more complex or noisy…
Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e.g., relative positions and poses). In this paper, we…