Related papers: GradAttn: Replacing Fixed Residual Connections wit…
This paper presents a comparative study of a custom convolutional neural network (CNN) architecture against widely used pretrained and transfer learning CNN models across five real-world image datasets. The datasets span binary…
In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion. Our Residual…
We introduce the Graded Transformer framework, a new class of sequence models that embeds algebraic inductive biases through grading transformations on vector spaces. Extending Graded Neural Networks (GNNs), we propose two architectures:…
Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an improved version of ResNets. Our proposed improvements address…
Currently, convolutional neural networks (CNN) (e.g., U-Net) have become the de facto standard and attained immense success in medical image segmentation. However, as a downside, CNN based methods are a double-edged sword as they fail to…
Deep learning architectures suffer from depth-related performance degradation, limiting the effective depth of neural networks. Approaches like ResNet are able to mitigate this, but they do not completely eliminate the problem. We introduce…
Deep convolutional neural networks (CNNs) for image denoising can effectively exploit rich hierarchical features and have achieved great success. However, many deep CNN-based denoising models equally utilize the hierarchical features of…
Designed as extremely deep architectures, deep residual networks which provide a rich visual representation and offer robust convergence behaviors have recently achieved exceptional performance in numerous computer vision problems. Being…
Deep residual networks (ResNets) made a recent breakthrough in deep learning. The core idea of ResNets is to have shortcut connections between layers that allow the network to be much deeper while still being easy to optimize avoiding…
Near-field channel estimation is a fundamental challenge in the sixth-generation (6G) wireless communication, where extremely large antenna arrays (ELAA) enable near-field communication (NFC) but introduce significant signal processing…
The success of Vision Transformer (ViT) has been widely reported on a wide range of image recognition tasks. ViT can learn global dependencies superior to CNN, yet CNN's inherent locality can substitute for expensive training resources.…
In this paper, we tackle the high computational overhead of Transformers for efficient image super-resolution~(SR). Motivated by the observations of self-attention's inter-layer repetition, we introduce a convolutionized self-attention…
Existing Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighboring nodes, or by applying a non-uniform score (attending) to the features. Recent…
Deep feedforward and recurrent networks have achieved impressive results in many perception and language processing applications. This success is partially attributed to architectural innovations such as convolutional and long short-term…
In image denoising, deep convolutional neural networks (CNNs) can obtain favorable performance on removing spatially invariant noise. However, many of these networks cannot perform well on removing the real noise (i.e. spatially variant…
We address the challenging problem of deep representation learning--the efficient adaption of a pre-trained deep network to different tasks. Specifically, we propose to explore gradient-based features. These features are gradients of the…
Graph Transformers (GTs) have demonstrated their advantages across a wide range of tasks. However, the self-attention mechanism in GTs overlooks the graph's inductive biases, particularly biases related to structure, which are crucial for…
Recently, many works have designed wider and deeper networks to achieve higher image super-resolution performance. Despite their outstanding performance, they still suffer from high computational resources, preventing them from directly…
In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce…
Gradient dynamics play a central role in determining the stability and generalization of deep neural networks. In this work, we provide an empirical analysis of how variance and standard deviation of gradients evolve during training,…