Related papers: Scaling the Scattering Transform: Deep Hybrid Netw…

We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in kernel methods, enabling nested part-of-part relations. Unlike…

In this paper, we present two image classification models on the Tiny ImageNet dataset. We built two very different networks from scratch based on the idea of Densely Connected Convolution Networks. The architecture of the networks is…

Diffracted scattering and occlusion are important acoustic effects in interactive auralization and noise control applications, typically requiring expensive numerical simulation. We propose training a convolutional neural network to map…

Despite the remarkable progress of deep learning in stereo matching, there exists a gap in accuracy between real-time models and slower state-of-the-art models which are suitable for practical applications. This paper presents an iterative…

Synchronized stochastic gradient descent (SGD) optimizers with data parallelism are widely used in training large-scale deep neural networks. Although using larger mini-batch sizes can improve the system scalability by reducing the…

In the past few years, convolutional neural nets (CNN) have shown incredible promise for learning visual representations. In this paper, we use CNNs for the task of predicting surface normals from a single image. But what is the right…

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…

Deep convolutional neural networks (CNNs) achieve remarkable performance on image classification tasks. Recent studies, however, have demonstrated that generalization abilities are more important than the depth of neural networks for…

Recent advancements in areas such as natural language processing and computer vision rely on intricate and massive models that have been trained using vast amounts of unlabelled or partly labeled data and training or deploying these…

Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the…

Conventional Convolutional neural networks (CNN) are trained on large domain datasets and are hence typically over-represented and inefficient in limited class applications. An efficient way to convert such large many-class pre-trained…

We proposes a simple deep learning architecture combining elements of Inception, ResNet and Xception networks. Four new datasets were used for classification with both small and large training samples. Results in terms of classification…

In the reconstruction process of unknown multiple scattering objects in inverse medium scattering problems, the first important step is to effectively locate some approximate domains that contain all inhomogeneous media. Without such an…

Heterogeneous materials such as biological tissue scatter light in random, yet deterministic, ways. Wavefront shaping can reverse the effects of scattering to enable deep-tissue microscopy. Such methods require either invasive access to the…

We examine five machine learning-based architectures to estimate the droplet size distributions obtained using digital inline holography. The architectures, namely, U-Net, R2 U-Net, Attention U-Net, V-Net, and Residual U-Net are trained…

We present MatrixNets (xNets), a new deep architecture for object detection. xNets map objects with similar sizes and aspect ratios into many specialized layers, allowing xNets to provide a scale and aspect ratio aware architecture. We…

Deep convolutional neural networks accuracy is heavily impacted by rotations of the input data. In this paper, we propose a convolutional predictor that is invariant to rotations in the input. This architecture is capable of predicting the…

Deep networks often suffer from vanishing or exploding gradients due to inefficient signal propagation, leading to long training times or convergence difficulties. Various architecture designs, sophisticated residual-style networks, and…

Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as…

Visual attributes play an essential role in real applications based on image retrieval. For instance, the extraction of attributes from images allows an eCommerce search engine to produce retrieval results with higher precision. The…