Related papers: Differentiable Learning-to-Group Channels via Grou…
Deep Neural Networks (DNNs) are often criticized for being susceptible to adversarial attacks. Most successful defense strategies adopt adversarial training or random input transformations that typically require retraining or fine-tuning…
Deep graph neural networks (GNNs) have achieved excellent results on various tasks on increasingly large graph datasets with millions of nodes and edges. However, memory complexity has become a major obstacle when training deep GNNs for…
Efficiency is quite important for 3D lane detection due to practical deployment demand. In this work, we propose a simple, fast, and end-to-end detector that still maintains high detection precision. Specifically, we devise a set of fully…
Traditional computer graphics rendering pipeline is designed for procedurally generating 2D quality images from 3D shapes with high performance. The non-differentiability due to discrete operations such as visibility computation makes it…
Most existing deep neural networks are static, which means they can only do inference at a fixed complexity. But the resource budget can vary substantially across different devices. Even on a single device, the affordable budget can change…
We present a novel class of Convolutional Neural Networks called Pre-defined Filter Convolutional Neural Networks (PFCNNs), where all nxn convolution kernels with n>1 are pre-defined and constant during training. It involves a special form…
The training of deep and/or convolutional neural networks (DNNs/CNNs) is traditionally done on servers with powerful CPUs and GPUs. Recent efforts have emerged to localize machine learning tasks fully on the edge. This brings advantages in…
Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only operate convolution on…
Convolutional layers are one of the basic building blocks of modern deep neural networks. One fundamental assumption is that convolutional kernels should be shared for all examples in a dataset. We propose conditionally parameterized…
Various normalization layers have been proposed to help the training of neural networks. Group Normalization (GN) is one of the effective and attractive studies that achieved significant performances in the visual recognition task. Despite…
Convolution Neural Networks on Graphs are important generalization and extension of classical CNNs. While previous works generally assumed that the graph structures of samples are regular with unified dimensions, in many applications, they…
Group convolutional neural networks (G-CNNs) can be used to improve classical CNNs by equipping them with the geometric structure of groups. Central in the success of G-CNNs is the lifting of feature maps to higher dimensional disentangled…
The convolutional neural networks (CNNs) have proven to be a powerful tool for discriminative learning. Recently researchers have also started to show interest in the generative aspects of CNNs in order to gain a deeper understanding of…
In this paper, we present a novel framework for enhancing the performance of Quanvolutional Neural Networks (QuNNs) by introducing trainable quanvolutional layers and addressing the critical challenges associated with them. Traditional…
Deep edge intelligence aims to deploy deep learning models that demand computationally expensive training in the edge network with limited computational power. Moreover, many deep edge intelligence applications require handling distributed…
Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels…
Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the high-dimensional data…
This paper introduces a novel convolution method, called generative convolution (GConv), which is simple yet effective for improving the generative adversarial network (GAN) performance. Unlike the standard convolution, GConv first selects…
Multimodal learning robust to missing modality has attracted increasing attention due to its practicality. Existing methods tend to address it by learning a common subspace representation for different modality combinations. However, we…
This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent…