相关论文: Parameter-Efficient Architectural Modifications fo…

While parameter efficient tuning (PET) methods have shown great potential with transformer architecture on Natural Language Processing (NLP) tasks, their effectiveness with large-scale ConvNets is still under-studied on Computer Vision (CV)…

Diagnosis of breast cancer malignancy at the early stages is a crucial step for controlling its side effects. Histopathological analysis provides a unique opportunity for malignant breast cancer detection. However, such a task would be…

We propose a novel architecture that learns an end-to-end mapping function to improve the spatial resolution of the input natural images. The model is unique in forming a nonlinear combination of three traditional interpolation techniques…

Previous work generally believes that improving the spatial invariance of convolutional networks is the key to object counting. However, after verifying several mainstream counting networks, we surprisingly found too strict pixel-level…

We propose a novel method to increase shift invariance and prediction accuracy in convolutional neural networks. Specifically, we replace the first-layer combination "real-valued convolutions + max pooling" (RMax) by "complex-valued…

This work presents and analyzes three convolutional neural network (CNN) models for efficient pixelwise classification of images. When using convolutional neural networks to classify single pixels in patches of a whole image, a lot of…

In this paper, we propose a novel Global Norm-Aware Pooling (GNAP) block, which reweights local features in a convolutional neural network (CNN) adaptively according to their L2 norms and outputs a global feature vector with a global…

Deep learning in k-space has demonstrated great potential for image reconstruction from undersampled k-space data in fast magnetic resonance imaging (MRI). However, existing deep learning-based image reconstruction methods typically apply…

While Convolutional Neural Networks (CNNs) excel at learning complex latent-space representations, their over-parameterization can lead to overfitting and reduced performance, particularly with limited data. This, alongside their high…

Recently proposed neural architecture search (NAS) methods co-train billions of architectures in a supernet and estimate their potential accuracy using the network weights detached from the supernet. However, the ranking correlation between…

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks over the years. However, this comes at the cost of heavy computation and memory intensive network designs, suggesting potential…

Graph neural networks (GNN) have shown great advantages in many graph-based learning tasks but often fail to predict accurately for a task-based on sets of nodes such as link/motif prediction and so on. Many works have recently proposed to…

Convolutional neural networks (CNNs) have revolutionized the world of computer vision over the last few years, pushing image classification beyond human accuracy. The computational effort of today's CNNs requires power-hungry parallel…

We reduce training time in convolutional networks (CNNs) with a method that, for some of the mini-batches: a) scales down the resolution of input images via downsampling, and b) reduces the forward pass operations via pooling on the…

Deep convolutional networks have become the mainstream in computer vision applications. Although CNNs have been successful in many computer vision tasks, it is not free from drawbacks. The performance of CNN is dramatically degraded by…

Convolutional neural networks (CNNs) achieve state-of-the-art accuracy in a variety of tasks in computer vision and beyond. One of the major obstacles hindering the ubiquitous use of CNNs for inference on low-power edge devices is their…

While convolutional neural networks (CNN) have achieved impressive performance on various classification/recognition tasks, they typically consist of a massive number of parameters. This results in significant memory requirement as well as…

Many scientific and engineering processes produce spatially unstructured data. However, most data-driven models require a feature matrix that enforces both a set number and order of features for each sample. They thus cannot be easily…

Convolutional neural networks (CNNs) tend to become a standard approach to solve a wide array of computer vision problems. Besides important theoretical and practical advances in their design, their success is built on the existence of…

Lossy image compression algorithms are pervasively used to reduce the size of images transmitted over the web and recorded on data storage media. However, we pay for their high compression rate with visual artifacts degrading the user…