Related papers: Learning from Images: Proactive Caching with Paral…
In this work, we propose a simple but effective channel pruning framework called Progressive Channel Pruning (PCP) to accelerate Convolutional Neural Networks (CNNs). In contrast to the existing channel pruning methods that prune channels…
In multi-access edge computing (MEC) systems, there are multiple local cache servers caching contents to satisfy the users' requests, instead of letting the users download via the remote cloud server. In this paper, a multi-cell content…
We present highly efficient algorithms for performing forward and backward propagation of Convolutional Neural Network (CNN) for pixelwise classification on images. For pixelwise classification tasks, such as image segmentation and object…
Convolutional Neural Networks (CNNs) have achieved remarkable success in various computer vision tasks but rely on tremendous computational cost. To solve this problem, existing approaches either compress well-trained large-scale models or…
In this work, we develop a novel input feature selection framework for ReLU-based deep neural networks (DNNs), which builds upon a mixed-integer optimization approach. While the method is generally applicable to various classification…
We introduce a class of causal video understanding models that aims to improve efficiency of video processing by maximising throughput, minimising latency, and reducing the number of clock cycles. Leveraging operation pipelining and…
Content-based image retrieval is the process of retrieving a subset of images from an extensive image gallery based on visual contents, such as color, shape or spatial relations, and texture. In some applications, such as localization,…
In computer vision, convolutional networks (CNNs) often adopts pooling to enlarge receptive field which has the advantage of low computational complexity. However, pooling can cause information loss and thus is detrimental to further…
Convolutional Neural Networks (CNNs) are state-of-the-art models for document image classification tasks. However, many of these approaches rely on parameters and architectures designed for classifying natural images, which differ from…
Convolutional neural networks (CNN) have achieved state of the art performance on both classification and segmentation tasks. Applying CNNs to microscopy images is challenging due to the lack of datasets labeled at the single cell level. We…
In many real-life tasks of application of supervised learning approaches, all the training data are not available at the same time. The examples are lifelong image classification or recognition of environmental objects during interaction of…
In this paper, we propose a novel deep convolutional neural network (CNN)-based algorithm for solving ill-posed inverse problems. Regularized iterative algorithms have emerged as the standard approach to ill-posed inverse problems in the…
Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensive prior work has explored learning such models from high-level descriptions of state…
Numerous real-world decision-making problems can be formulated and solved using Mixed-Integer Linear Programming (MILP) models. However, the transformation of these problems into MILP models heavily relies on expertise in operations…
Although deep learning-based personalized recommendation systems provide qualified recommendations, they strain data center resources. The main bottleneck is the embedding layer, which is highly memory-intensive due to its sparse, irregular…
Mixed-integer linear programming (MILP) stands as a notable NP-hard problem pivotal to numerous crucial industrial applications. The development of effective algorithms, the tuning of solvers, and the training of machine learning models for…
Depth prediction plays a key role in understanding a 3D scene. Several techniques have been developed throughout the years, among which Convolutional Neural Network has recently achieved state-of-the-art performance on estimating depth from…
The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, the field has increasingly prioritized marginal performance gains on a…
Learning to represent videos is a very challenging task both algorithmically and computationally. Standard video CNN architectures have been designed by directly extending architectures devised for image understanding to include the time…
Network function virtualization (NFV) and content caching are two promising technologies that hold great potential for network operators and designers. This paper optimizes the deployment of NFV and content caching in 5G networks and…