Related papers: EAutoDet: Efficient Architecture Search for Object…

This paper provides a report on our solution including model selection, tuning strategy and results obtained for Global Road Damage Detection Challenge. This Big Data Cup Challenge was held as a part of IEEE International Conference on Big…

Modern efficient Convolutional Neural Networks(CNNs) always use Depthwise Separable Convolutions(DSCs) and Neural Architecture Search(NAS) to reduce the number of parameters and the computational complexity. But some inherent…

Real-time accurate detection of three-dimensional (3D) objects is a fundamental necessity for self-driving vehicles. Most existing computer vision approaches are based on convolutional neural networks (CNNs). Although the CNN-based…

The local feature detector and descriptor are essential in many computer vision tasks, such as SLAM and 3D reconstruction. In this paper, we introduce two separate CNNs, lightweight SobelNet and DesNet, to detect key points and to compute…

On-board real-time vehicle detection is of great significance for UAVs and other embedded mobile platforms. We propose a computationally inexpensive detection network for vehicle detection in UAV imagery which we call ShuffleDet. In order…

Computing at the edge offers intriguing possibilities for the development of autonomy and artificial intelligence. The advancements in autonomous technologies and the resurgence of computer vision have led to a rise in demand for fast and…

Searching techniques in most of existing neural architecture search (NAS) algorithms are mainly dominated by differentiable methods for the efficiency reason. In contrast, we develop an efficient continuous evolutionary approach for…

Purpose: Visual perception enables robots to perceive the environment. Visual data is processed using computer vision algorithms that are usually time-expensive and require powerful devices to process the visual data in real-time, which is…

Deep learning applications are being transferred from the cloud to edge with the rapid development of embedded computing systems. In order to achieve higher energy efficiency with the limited resource budget, neural networks(NNs) must be…

Object detection has made impressive progress in recent years with the help of deep learning. However, state-of-the-art algorithms are both computation and memory intensive. Though many lightweight networks are developed for a trade-off…

Resource is an important constraint when deploying Deep Neural Networks (DNNs) on mobile and edge devices. Existing works commonly adopt the cell-based search approach, which limits the flexibility of network patterns in learned cell…

The ability to perform pixel-wise semantic segmentation in real-time is of paramount importance in mobile applications. Recent deep neural networks aimed at this task have the disadvantage of requiring a large number of floating point…

Recently, neural architecture search (NAS) has been exploited to design feature pyramid networks (FPNs) and achieved promising results for visual object detection. Encouraged by the success, we propose a novel One-Shot Path Aggregation…

This paper describes an optimized single-stage deep convolutional neural network to detect objects in urban environments, using nothing more than point cloud data. This feature enables our method to work regardless the time of the day and…

High-performance deep neural network (DNN)-based systems are in high demand in edge environments. Due to its high computational complexity, it is challenging to deploy DNNs on edge devices with strict limitations on computational resources.…

We present here, a novel network architecture called MergeNet for discovering small obstacles for on-road scenes in the context of autonomous driving. The basis of the architecture rests on the central consideration of training with less…

We propose Efficient Neural Architecture Search (ENAS), a fast and inexpensive approach for automatic model design. In ENAS, a controller learns to discover neural network architectures by searching for an optimal subgraph within a large…

This paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints. Instead of developing new building blocks or using computationally-intensive reinforcement…

We address the challenge of training a large supernet for the object detection task, using a relatively small amount of training data. Specifically, we propose an efficient supernet-based neural architecture search (NAS) method that uses…

Real-time fault detection for freight trains plays a vital role in guaranteeing the security and optimal operation of railway transportation under stringent resource requirements. Despite the promising results for deep learning based…