Related papers: Efficient ResNets: Residual Network Design

One of the most computationally intensive parts in modern recognition systems is an inference of deep neural networks that are used for image classification, segmentation, enhancement, and recognition. The growing popularity of edge…

Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its…

Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very…

Empirical adversarial risk minimization (EARM) is a widely used mathematical framework to robustly train deep neural nets (DNNs) that are resistant to adversarial attacks. However, both natural and robust accuracies, in classifying clean…

For all the ways convolutional neural nets have revolutionized computer vision in recent years, one important aspect has received surprisingly little attention: the effect of image size on the accuracy of tasks being trained for. Typically,…

We propose to focus on the problem of discovering neural network architectures efficient in terms of both prediction quality and cost. For instance, our approach is able to solve the following tasks: learn a neural network able to predict…

Gradient-based algorithms for training ResNets typically require a forward pass of the input data, followed by back-propagating the objective gradient to update parameters, which are time-consuming for deep ResNets. To break the…

Neural network pruning with suitable retraining can yield networks with considerably fewer parameters than the original with comparable degrees of accuracy. Typical pruning methods require large, fully trained networks as a starting point…

Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve very good performance at relatively low…

Learning-based methods have demonstrated remarkable performance in solving inverse problems, particularly in image reconstruction tasks. Despite their success, these approaches often lack theoretical guarantees, which are crucial in…

As the world continues to face the challenges of climate change, it is crucial to consider the environmental impact of the technologies we use. In this study, we investigate the performance and computational carbon emissions of various…

The ResNet architecture has been widely adopted in deep learning due to its significant boost to performance through the use of simple skip connections, yet the underlying mechanisms leading to its success remain largely unknown. In this…

Spiking neural networks (SNNs) have received significant attention for their biological plausibility. SNNs theoretically have at least the same computational power as traditional artificial neural networks (ANNs). They possess potential of…

Convolutional Neural Networks (CNNs) are pivotal in image classification tasks due to their robust feature extraction capabilities. However, their high computational and memory requirements pose challenges for deployment in…

Rock Classification is an essential geological problem since it provides important formation information. However, exploration on this problem using convolutional neural networks is not sufficient. To tackle this problem, we propose two…

Recently, deep learning-based compressed sensing (CS) has achieved great success in reducing the sampling and computational cost of sensing systems and improving the reconstruction quality. These approaches, however, largely overlook the…

Despite the rapid progress of neuromorphic computing, the inadequate depth and the resulting insufficient representation power of spiking neural networks (SNNs) severely restrict their application scope in practice. Residual learning and…

Convolutional Neural Network (CNN) has an amount of parameter redundancy, filter pruning aims to remove the redundant filters and provides the possibility for the application of CNN on terminal devices. However, previous works pay more…

This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image. This architecture is end-to-end trainable, deterministic and problem-agnostic.…

Deep learning based approaches has achieved great performance in single image super-resolution (SISR). However, recent advances in efficient super-resolution focus on reducing the number of parameters and FLOPs, and they aggregate more…