相关论文: Cascade Network with Guided Loss and Hybrid Attent…

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

Graph Convolutional Network (GCN) has been widely used in graph learning tasks. However, GCN-based models (GCNs) is an inherently coupled training framework repetitively conducting the complex neighboring aggregation, which leads to the…

The Hierarchical Attention Network (HAN) has made great strides, but it suffers a major limitation: at level 1, each sentence is encoded in complete isolation. In this work, we propose and compare several modifications of HAN in which the…

Neural network architecture design requires making many crucial decisions. The common desiderata is that similar decisions, with little modifications, can be reused in a variety of tasks and applications. To satisfy that, architectures must…

Attention models are typically learned by optimizing one of three standard loss functions that are variously called -- soft attention, hard attention, and latent variable marginal likelihood (LVML) attention. All three paradigms are…

Attention mechanism of late has been quite popular in the computer vision community. A lot of work has been done to improve the performance of the network, although almost always it results in increased computational complexity. In this…

Scene text recognition has been a hot topic in computer vision. Recent methods adopt the attention mechanism for sequence prediction which achieve convincing results. However, we argue that the existing attention mechanism faces the problem…

Monocular depth estimation, which plays a key role in understanding 3D scene geometry, is fundamentally an ill-posed problem. Existing methods based on deep convolutional neural networks (DCNNs) have examined this problem by learning…

Forensic analysis of manipulated pixels requires the identification of various hidden and subtle features from images. Conventional image recognition models generally fail at this task because they are biased and more attentive toward the…

Using deep learning models to recognize functional brain networks (FBNs) in functional magnetic resonance imaging (fMRI) has been attracting increasing interest recently. However, most existing work focuses on detecting static FBNs from…

Convolutional Neural Networks (CNNs) frequently "cheat" by exploiting superficial correlations, raising concerns about whether they make predictions for the right reasons. Inspired by cognitive science, which highlights the role of…

Anomaly detection is a task that recognizes whether an input sample is included in the distribution of a target normal class or an anomaly class. Conventional generative adversarial network (GAN)-based methods utilize an entire image…

Visual explanation enables human to understand the decision making of Deep Convolutional Neural Network (CNN), but it is insufficient to contribute the performance improvement. In this paper, we focus on the attention map for visual…

Retinal vessel segmentation methods based on standard overlap losses tend to miss thin peripheral vessels because these structures occupy very few pixels and have low contrast against the background. We propose HMS-VesselNet, a hierarchical…

Deep Convolutional Neural Network (CNN) features have been demonstrated to be effective perceptual quality features. The perceptual loss, based on feature maps of pre-trained CNN's has proven to be remarkably effective for CNN based…

We show that learning can be improved by using loss functions that evolve cyclically during training to emphasize one class at a time. In underparameterized networks, such dynamical loss functions can lead to successful training for…

In practical applications, multi-view data depicting objectives from assorted perspectives can facilitate the accuracy increase of learning algorithms. However, given multi-view data, there is limited work for learning discriminative node…

Attention is typically used to select informative sub-phrases that are used for prediction. This paper investigates the novel use of attention as a form of feature augmentation, i.e, casted attention. We propose Multi-Cast Attention…

Hybrid CNN-Transformer architectures achieve strong results in image super-resolution, but scaling attention windows or convolution kernels significantly increases computational cost, limiting deployment on resource-constrained devices. We…

We present an attention-based spatial graph convolution (AGC) for graph neural networks (GNNs). Existing AGCs focus on only using node-wise features and utilizing one type of attention function when calculating attention weights. Instead,…