Related papers: A Lightweight, Efficient and Explainable-by-Design…
This work attempts to interpret modern deep (convolutional) networks from the principles of rate reduction and (shift) invariant classification. We show that the basic iterative gradient ascent scheme for optimizing the rate reduction of…
We propose a constrained linear data-feature-mapping model as an interpretable mathematical model for image classification using a convolutional neural network (CNN). From this viewpoint, we establish detailed connections between the…
Real-time traffic light recognition is essential for autonomous driving. Yet, a cohesive overview of the underlying model architectures for this task is currently missing. In this work, we conduct a comprehensive survey and analysis of…
Capsule Networks, as alternatives to Convolutional Neural Networks, have been proposed to recognize objects from images. The current literature demonstrates many advantages of CapsNets over CNNs. However, how to create explanations for…
Traffic classification has been studied for two decades and applied to a wide range of applications from QoS provisioning and billing in ISPs to security-related applications in firewalls and intrusion detection systems. Port-based, data…
Accurate and fast scene understanding is one of the challenging task for autonomous driving, which requires to take full advantage of LiDAR point clouds for semantic segmentation. In this paper, we present a \textbf{concise} and…
Traffic prediction is the cornerstone of an intelligent transportation system. Accurate traffic forecasting is essential for the applications of smart cities, i.e., intelligent traffic management and urban planning. Although various methods…
Medical image classification is crucial for supporting healthcare professionals in decision-making and training. While Convolutional Neural Networks (CNNs) have traditionally dominated this field, Transformer-based models are gaining…
While machine learning techniques have been successfully applied in several fields, the black-box nature of the models presents challenges for interpreting and explaining the results. We develop a new framework called Adaptive Explainable…
Convolutional Neural Networks (CNN) increase depth by stacking convolutional layers, and deeper network models perform better in image recognition. Empirical research shows that simply stacking convolutional layers does not make the network…
With the ever increasing application of Convolutional Neural Networks to customer products the need emerges for models to efficiently run on embedded, mobile hardware. Slimmer models have therefore become a hot research topic with various…
The deployment of deep convolutional neural networks (CNNs) in many real world applications is largely hindered by their high computational cost. In this paper, we propose a novel learning scheme for CNNs to simultaneously 1) reduce the…
Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications. We introduce BlockDrop, an approach that learns to dynamically choose which…
Focus on Deep Neural Network based malicious and normal computer Network Traffic classification. (such as attacks, phishing, any other illegal activity and normal traffic identification). In this paper, the main idea is to review, existed…
We explore the use of convolutional neural networks for the semantic classification of remote sensing scenes. Two recently proposed architectures, CaffeNet and GoogLeNet, are adopted, with three different learning modalities. Besides…
In many interesting cases, the application of machine learning is hindered by data having a complicated structure stimulated by a structured file-formats like JSONs, XMLs, or ProtoBuffers, which is non-trivial to convert to a vector /…
This paper presents a system for session-level traffic classification on endpoint devices, developed using a Hardware-aware Neural Architecture Search (HW-NAS) framework. HW-NAS optimizes Convolutional Neural Network (CNN) architectures by…
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…
FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow estimation, requires over 160M parameters to achieve accurate flow estimation. In this paper we present an alternative network that outperforms FlowNet2 on…
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we…