Related papers: A lightweight target detection algorithm based on …

In the current salient object detection network, the most popular method is using U-shape structure. However, the massive number of parameters leads to more consumption of computing and storage resources which are not feasible to deploy on…

Object detection and recognition algorithms using deep convolutional neural networks (CNNs) tend to be computationally intensive to implement. This presents a particular challenge for embedded systems, such as mobile robots, where the…

Automatic detection and recognition of banknotes can be a very useful technology for people with visual difficulties and also for the banks itself by providing efficient management for handling different paper currencies. Lightweight models…

This paper is focused on the improvement the efficiency of the sparse convolutional neural networks (CNNs) layers on graphic processing units (GPU). The Nvidia deep neural network (cuDnn) library provides the most effective implementation…

Shot boundary detection (SBD) is an important first step in many video processing applications. This paper presents a simple modular convolutional neural network architecture that achieves state-of-the-art results on the RAI dataset with…

Semantic segmentation is a key technology for autonomous vehicles to understand the surrounding scenes. The appealing performances of contemporary models usually come at the expense of heavy computations and lengthy inference time, which is…

Recent advances in event camera research emphasize processing data in its original sparse form, which allows the use of its unique features such as high temporal resolution, high dynamic range, low latency, and resistance to image blur. One…

To train deep convolutional neural networks, the input data and the intermediate activations need to be kept in memory to calculate the gradient descent step. Given the limited memory available in the current generation accelerator cards,…

Recent advances in camera designs and imaging pipelines allow us to capture high-quality images using smartphones. However, due to the small size and lens limitations of the smartphone cameras, we commonly find artifacts or degradation in…

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…

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…

We consider an important task of effective and efficient semantic image segmentation. In particular, we adapt a powerful semantic segmentation architecture, called RefineNet, into the more compact one, suitable even for tasks requiring…

Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images. However, hyperspectral super-resolution remains…

We study performance characteristics of convolutional neural networks (CNN) for mobile computer vision systems. CNNs have proven to be a powerful and efficient approach to implement such systems. However, the system performance depends…

Lightweight convolutional neural networks (e.g., MobileNets) are specifically designed to carry out inference directly on mobile devices. Among the various lightweight models, depthwise convolution (DWConv) and pointwise convolution…

Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks that enables…

Object detection is widely used on embedded devices. With the wide availability of CNN (Convolutional Neural Networks) accelerator chips, the object detection applications are expected to run with low power consumption, and high inference…

Edge computing allows more computing tasks to take place on the decentralized nodes at the edge of networks. Today many delay sensitive, mission-critical applications can leverage these edge devices to reduce the time delay or even to…

State-of-the-art neural network architectures such as ResNet, MobileNet, and DenseNet have achieved outstanding accuracy over low MACs and small model size counterparts. However, these metrics might not be accurate for predicting the…

Pixel-level road crack detection has always been a challenging task in intelligent transportation systems. Due to the external environments, such as weather, light, and other factors, pavement cracks often present low contrast, poor…