Related papers: Separable Convolutions for Optimizing 3D Stereo Ne…
Modern deep neural networks are typically highly overparameterized. Pruning techniques are able to remove a significant fraction of network parameters with little loss in accuracy. Recently, techniques based on dynamic reallocation of…
Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accuracy. However, as a model of the brain they are seriously…
The success of deep learning in the computer vision and natural language processing communities can be attributed to training of very deep neural networks with millions or billions of parameters which can then be trained with massive…
Convolutional neural networks (CNNs) allow for parameter sharing and translational equivariance by using convolutional kernels in their linear layers. By restricting these kernels to be SO(3)-steerable, CNNs can further improve parameter…
Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of…
Although deep learning-based methods have dominated stereo matching leaderboards by yielding unprecedented disparity accuracy, their inference time is typically slow, on the order of seconds for a pair of 540p images. The main reason is…
To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary…
With the thriving of deep learning, 3D Convolutional Neural Networks have become a popular choice in volumetric image analysis due to their impressive 3D contexts mining ability. However, the 3D convolutional kernels will introduce a…
The published literature on topology optimization has exploded over the last two decades to include methods that use shape and topological derivatives or evolutionary algorithms formulated on various geometric representations and…
End-to-end deep-learning networks recently demonstrated extremely good perfor- mance for stereo matching. However, existing networks are difficult to use for practical applications since (1) they are memory-hungry and unable to process even…
Convolution Neural Networks, known as ConvNets exceptionally perform well in many complex machine learning tasks. The architecture of ConvNets demands the huge and rich amount of data and involves with a vast number of parameters that leads…
For video and volumetric data understanding, 3D convolution layers are widely used in deep learning, however, at the cost of increasing computation and training time. Recent works seek to replace the 3D convolution layer with convolution…
Deep neural networks have shown excellent performance for stereo matching. Many efforts focus on the feature extraction and similarity measurement of the matching cost computation step while less attention is paid on cost aggregation which…
Convolutional Neural Networks (CNNs) have become indispensable for solving machine learning tasks in speech recognition, computer vision, and other areas that involve high-dimensional data. A CNN filters the input feature using a network…
Typical convolutional neural networks (CNNs) have several millions of parameters and require a large amount of annotated data to train them. In medical applications where training data is hard to come by, these sophisticated machine…
We propose ways to improve the performance of fully connected networks. We found that two approaches in particular have a strong effect on performance: linear bottleneck layers and unsupervised pre-training using autoencoders without hidden…
3D neural networks have become prevalent for many 3D vision tasks including object detection, segmentation, registration, and various perception tasks for 3D inputs. However, due to the sparsity and irregularity of 3D data, custom 3D…
This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce…
Leveraging on the recent developments in convolutional neural networks (CNNs), matching dense correspondence from a stereo pair has been cast as a learning problem, with performance exceeding traditional approaches. However, it remains…
We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy but each image evaluation requires millions of floating point…