Related papers: DupNet: Towards Very Tiny Quantized CNN with Impro…
This paper implements and analyzes multiple networks with the goal of understanding their suitability for edge device applications such as X-ray threat detection. In this study, we use the state-of-the-art YOLO object detection model to…
Deep Neural Networks (DNNs) have been widely applied in Internet of Things (IoT) systems for various tasks such as image classification and object detection. However, heavyweight DNN models can hardly be deployed on edge devices due to…
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…
In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach…
With the emergence of service robots and surveillance cameras, dynamic face recognition (DFR) in wild has received much attention in recent years. Face detection and head pose estimation are two important steps for DFR. Very often, the pose…
"Lightweight convolutional neural networks" is an important research topic in the field of embedded vision. To implement image recognition tasks on a resource-limited hardware platform, it is necessary to reduce the memory size and the…
Deep Learning Architectures employ heavy computations and bulk of the computational energy is taken up by the convolution operations in the Convolutional Neural Networks. The objective of our proposed work is to reduce the energy…
This paper introduces a framework for systematic complexity scaling of deep neural network(DNN) based MIMO detectors. The model uses a fraction of the DNN inputs by scaling their values through weights that follow monotonically…
This paper aims at constructing a light-weight object detector that inputs a depth and a color image from a stereo camera. Specifically, by extending the network architecture of YOLOv3 to 3D in the middle, it is possible to output in the…
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically…
Most of the current face hallucination methods, whether they are shallow learning-based or deep learning-based, all try to learn a relationship model between Low-Resolution (LR) and High-Resolution (HR) spaces with the help of a training…
This paper implements a Binary Neural Network (BNN) based YOLOv3-tiny-like object detector on a low-cost FPGA. The network takes 320*320*3 RGB images as input. Its main convolution layers use 1-bit weights and 8-bit activations, while Conv1…
Real-time CNN-based object detection models for applications like surveillance can achieve high accuracy but are computationally expensive. Recent works have shown 10 to 100x reduction in computation cost for inference by using…
Recent years have witnessed a substantial increase in the deep learning (DL)architectures proposed for visual recognition tasks like person re-identification,where individuals must be recognized over multiple distributed cameras.…
Objective: In clinical practice, small lung nodules can be easily overlooked by radiologists. The paper aims to provide an efficient and accurate detection system for small lung nodules while keeping good performance for large nodules.…
The volume of convolutional neural network (CNN) models proposed for face recognition has been continuously growing larger to better fit large amount of training data. When training data are obtained from internet, the labels are likely to…
To achieve lightweight object detectors for deployment on the edge devices, an effective model compression pipeline is proposed in this paper. The compression pipeline consists of automatic channel pruning for the backbone, fixed channel…
Object detection has gained great progress driven by the development of deep learning. Compared with a widely studied task -- classification, generally speaking, object detection even need one or two orders of magnitude more FLOPs (floating…
Deep Convolutional Neural Networks (CNNs) are increasingly difficult to deploy on microcontrollers (MCUs) and lightweight NPUs (Neural Processing Units) due to their growing size and compute demands. Low-rank tensor decomposition, such as…
This paper presents incremental network quantization (INQ), a novel method, targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version whose weights are constrained…