相关论文: Slim-neck by GSConv: A lightweight-design for real…

SSD is one of the state-of-the-art object detection algorithms, and it combines high detection accuracy with real-time speed. However, it is widely recognized that SSD is less accurate in detecting small objects compared to large objects,…

Slimmable Neural Networks (S-Net) is a novel network which enabled to select one of the predefined proportions of channels (sub-network) dynamically depending on the current computational resource availability. The accuracy of each…

Real-time gas classification is an essential issue and challenge in applications such as food and beverage quality control, accident prevention in industrial environments, for instance. In recent years, the Deep Learning (DL) models have…

Saliency computation models aim to imitate the attention mechanism in the human visual system. The application of deep neural networks for saliency prediction has led to a drastic improvement over the last few years. However, deep models…

In this chapter, we present a brief overview of the recent development in object detection using convolutional neural networks (CNN). Several classical CNN-based detectors are presented. Some developments are based on the detector…

Vision-based vehicle detection approaches achieve incredible success in recent years with the development of deep convolutional neural network (CNN). However, existing CNN based algorithms suffer from the problem that the convolutional…

Object trackers deployed on low-power devices need to be light-weight, however, most of the current state-of-the-art (SOTA) methods rely on using compute-heavy backbones built using CNNs or transformers. Large sizes of such models do not…

Convolutional Neural Networks (CNNs) can provide accurate object classification. They can be extended to perform object detection by iterating over dense or selected proposed object regions. However, the runtime of such detectors scales as…

Emerging chips with hundreds and thousands of cores require networks with unprecedented energy/area efficiency and scalability. To address this, we propose Slim NoC (SN): a new on-chip network design that delivers significant improvements…

Modern deep neural networks tend to be evaluated on static test sets. One shortcoming of this is the fact that these deep neural networks cannot be easily evaluated for robustness issues with respect to specific scene variations. For…

In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. We utilise the advantage of convolutional neural networks to automatically learn the…

Synthetic Aperture Radar (SAR) object detection faces significant challenges from speckle noise, small target ambiguities, and on-board computational constraints. While existing approaches predominantly focus on SAR-specific architectural…

Object detection is essential in space applications targeting Space Domain Awareness and also applications involving relative navigation scenarios. Current deep learning models for Object Detection in space applications are often trained on…

3D spatial information is known to be beneficial to the semantic segmentation task. Most existing methods take 3D spatial data as an additional input, leading to a two-stream segmentation network that processes RGB and 3D spatial…

Object tracking has achieved significant progress over the past few years. However, state-of-the-art trackers become increasingly heavy and expensive, which limits their deployments in resource-constrained applications. In this work, we…

Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs). Semantic segmentation and saliency detection algorithms developed lately have been mostly based…

Despite their strong modeling capacities, Convolutional Neural Networks (CNNs) are often scale-sensitive. For enhancing the robustness of CNNs to scale variance, multi-scale feature fusion from different layers or filters attracts great…

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

Modern applications such as autonomous vehicles, intelligent surveillance, and smart city systems increasingly require object detection on resource-constrained edge devices. Yet, there is still limited understanding of how different object…

In the past decade, convolutional neural networks (CNNs) have shown prominence for semantic segmentation. Although CNN models have very impressive performance, the ability to capture global representation is still insufficient, which…