CNN architectures are generally heavy on memory and computational requirements which makes them infeasible for embedded systems with limited hardware resources. We propose dual convolutional kernels (DualConv) for constructing lightweight deep neural networks. DualConv combines 3$\times$3 and 1$\times$1 convolutional kernels to process the same input feature map channels simultaneously and exploits the group convolution technique to efficiently arrange convolutional filters. DualConv can be employed in any CNN model such as VGG-16 and ResNet-50 for image classification, YOLO and R-CNN for object detection, or FCN for semantic segmentation. In this paper, we extensively test DualConv for classification since these network architectures form the backbones for many other tasks. We also test DualConv for image detection on YOLO-V3. Experimental results show that, combined with our structural innovations, DualConv significantly reduces the computational cost and number of parameters of deep neural networks while surprisingly achieving slightly higher accuracy than the original models in some cases. We use DualConv to further reduce the number of parameters of the lightweight MobileNetV2 by 54% with only 0.68% drop in accuracy on CIFAR-100 dataset. When the number of parameters is not an issue, DualConv increases the accuracy of MobileNetV1 by 4.11% on the same dataset. Furthermore, DualConv significantly improves the YOLO-V3 object detection speed and improves its accuracy by 4.4% on PASCAL VOC dataset.
We propose DualConvMesh-Nets (DCM-Net) a family of deep hierarchical convolutional networks over 3D geometric data that combines two types of convolutions. The first type, geodesic convolutions, defines the kernel weights over mesh surfaces or graphs. That is, the convolutional kernel weights are mapped to the local surface of a given mesh. The second type, Euclidean convolutions, is independent of any underlying mesh structure. The convolutional kernel is applied on a neighborhood obtained from a local affinity representation based on the Euclidean distance between 3D points. Intuitively, geo…
We propose a lightweight CPU network based on the MKLDNN acceleration strategy, named PP-LCNet, which improves the performance of lightweight models on multiple tasks. This paper lists technologies which can improve network accuracy while the latency is almost constant. With these improvements, the accuracy of PP-LCNet can greatly surpass the previous network structure with the same inference time for classification. As shown in Figure 1, it outperforms the most state-of-the-art models. And for downstream tasks of computer vision, it also performs very well, such as object detection, semantic …
1 National Engineering Research Center of Communications；Networking, Nanjing University of Posts \& Telecommunications, P.R. China. 2 School of Internet of Things, Nanjing University of Posts \& Telecommunications, P.R. China.
This paper introduces a lightweight convolutional neural network, called FDDWNet, for real-time accurate semantic segmentation. In contrast to recent advances of lightweight networks that prefer to utilize shallow structure, FDDWNet makes an effort to design more deeper network architecture, while maintains faster inference speed and higher segmentation accuracy. Our network uses factorized dilated depth-wise separable convolutions (FDDWC) to learn feature representations from different scale receptive fields with fewer model parameters. Additionally, FDDWNet has multiple branches of skipped c…
The architecture of deep convolutional networks (CNNs) has evolved for years, becoming more accurate and faster. However, it is still challenging to design reasonable network structures that aim at obtaining the best accuracy under a limited computational budget. In this paper, we propose a Tree block, named after its appearance, which extends the One-Shot Aggregation (OSA) module while being more lightweight and flexible. Specifically, the Tree block replaces each of the $3\times3$ Conv layers in OSA into a stack of shallow residual block (SRB) and $1\times1$ Conv layer. The $1\times1$ Conv l…
We propose model with larger spatial size of feature maps and evaluate it on object detection task. With the goal to choose the best feature extraction network for our model we compare several popular lightweight networks. After that we conduct a set of experiments with channels reduction algorithms in order to accelerate execution. Our vehicle detection models are accurate, fast and therefore suit for embedded visual applications. With only 1.5 GFLOPs our best model gives 93.39 AP on validation subset of challenging DETRAC dataset. The smallest of our models is the first to achieve real-time …
Technische Universität München（慕尼黑工业大学）；Tongji University（同济大学）；University of Science and Technology of China（中国科学技术大学）；Fortiss Research Institute（Fortiss研究院）
The method of deep learning has achieved excellent results in improving the performance of robotic grasping detection. However, the deep learning methods used in general object detection are not suitable for robotic grasping detection. Current modern object detectors are difficult to strike a balance between high accuracy and fast inference speed. In this paper, we present an efficient and robust fully convolutional neural network model to perform robotic grasping pose estimation from an n-channel input image of the real grasping scene. The proposed network is a lightweight generative architec…
Vision based human pose estimation is an non-invasive technology for Human-Computer Interaction (HCI). Direct use of the hand as an input device provides an attractive interaction method, with no need for specialized sensing equipment, such as exoskeletons, gloves etc, but a camera. Traditionally, HCI is employed in various applications spreading in areas including manufacturing, surgery, entertainment industry and architecture, to mention a few. Deployment of vision based human pose estimation algorithms can give a breath of innovation to these applications. In this letter, we present a novel…
Multi-scale learning frameworks have been regarded as a capable class of models to boost semantic segmentation. The problem nevertheless is not trivial especially for the real-world deployments, which often demand high efficiency in inference latency. In this paper, we thoroughly analyze the design of convolutional blocks (the type of convolutions and the number of channels in convolutions), and the ways of interactions across multiple scales, all from lightweight standpoint for semantic segmentation. With such in-depth comparisons, we conclude three principles, and accordingly devise Lightwei…
Recently, FCNs have attracted widespread attention in the CD field. In pursuit of better CD performance, it has become a tendency to design deeper and more complicated FCNs, which inevitably brings about huge numbers of parameters and an unbearable computational burden. With the goal of designing a quite deep architecture to obtain more precise CD results while simultaneously decreasing parameter numbers to improve efficiency, in this work, we present a very deep and efficient CD network, entitled EffCDNet. In EffCDNet, to reduce the numerous parameters associated with deep architecture, an ef…
Semantic segmentation is a pixel-level prediction task to classify each pixel of the input image. Deep learning models, such as convolutional neural networks (CNNs), have been extremely successful in achieving excellent performances in this domain. However, mobile application, such as autonomous driving, demand real-time processing of incoming stream of images. Hence, achieving efficient architectures along with enhanced accuracy is of paramount importance. Since, accuracy and model size of CNNs are intrinsically contentious in nature, the challenge is to achieve a decent trade-off between acc…
In this paper, we introduce the spatial bias to learn global knowledge without self-attention in convolutional neural networks. Owing to the limited receptive field, conventional convolutional neural networks suffer from learning long-range dependencies. Non-local neural networks have struggled to learn global knowledge, but unavoidably have too heavy a network design due to the self-attention operation. Therefore, we propose a fast and lightweight spatial bias that efficiently encodes global knowledge without self-attention on convolutional neural networks. Spatial bias is stacked on the feat…
In this research, we propose a tiny image segmentation model, L^3U-net, that works on low-resource edge devices in real-time. We introduce a data folding technique that reduces inference latency by leveraging the parallel convolutional layer processing capability of the CNN accelerators. We also deploy the proposed model to such a device, MAX78000, and the results show that L^3U-net achieves more than 90% accuracy over two different segmentation datasets with 10 fps.
Tsinghua University（清华大学）；University of Southern California（南加州大学）；Hebei University of Engineering（河北工程大学）
Image segmentation is an important task in the medical image field and many convolutional neural networks (CNNs) based methods have been proposed, among which U-Net and its variants show promising performance. In this paper, we propose GP-module and GPU-Net based on U-Net, which can learn more diverse features by introducing Ghost module and atrous spatial pyramid pooling (ASPP). Our method achieves better performance with more than 4 times fewer parameters and 2 times fewer FLOPs, which provides a new potential direction for future research. Our plug-and-play module can also be applied to exi…
Recently, many Convolution Neural Networks (CNN) have been successfully employed in bitemporal SAR image change detection. However, most of the existing networks are too heavy and occupy a large volume of memory for storage and calculation. Motivated by this, in this paper, we propose a lightweight neural network to reduce the computational and spatial complexity and facilitate the change detection on an edge device. In the proposed network, we replace normal convolutional layers with bottleneck layers that keep the same number of channels between input and output. Next, we employ dilated conv…
Graph convolution networks (GCNs) are currently mainstream in learning with irregular data. These models rely on message passing and attention mechanisms that capture context and node-to-node relationships. With multi-head attention, GCNs become highly accurate but oversized, and their deployment on cheap devices requires their pruning. However, pruning at high regimes usually leads to topologically inconsistent networks with weak generalization. In this paper, we devise a novel method for lightweight GCN design. Our proposed approach parses and selects subnetworks with the highest magnitudes …
Extremely efficient convolutional neural network architectures are one of the most important requirements for limited-resource devices (such as embedded and mobile devices). The computing power and memory size are two important constraints of these devices. Recently, some architectures have been proposed to overcome these limitations by considering specific hardware-software equipment. In this paper, the lightweight residual densely connected blocks are proposed to guaranty the deep supervision, efficient gradient flow, and feature reuse abilities of convolutional neural network. The proposed …
Iowa State University（爱荷华州立大学）；University of Iowa（爱荷华大学）；Tippie College of Business（蒂皮商学院）
For a globally recognized planting breeding organization, manually-recorded field observation data is crucial for plant breeding decision making. However, certain phenotypic traits such as plant color, height, kernel counts, etc. can only be collected during a specific time-window of a crop's growth cycle. Due to labor-intensive requirements, only a small subset of possible field observations are recorded each season. To help mitigate this data collection bottleneck in wheat breeding, we propose a novel deep learning framework to accurately and efficiently count wheat heads to aid in the gathe…
In this paper, we design lightweight graph convolutional networks (GCNs) using a particular class of regularizers, dubbed as phase-field models (PFMs). PFMs exhibit a bi-phase behavior using a particular ultra-local term that allows training both the topology and the weight parameters of GCNs as a part of a single "end-to-end" optimization problem. Our proposed solution also relies on a reparametrization that pushes the mask of the topology towards binary values leading to effective topology selection and high generalization while implementing any targeted pruning rate. Both masks and weights …
Modern neural network modules which can significantly enhance the learning power usually add too much computational complexity to the original neural networks. In this paper, we pursue very efficient neural network modules which can significantly boost the learning power of deep convolutional neural networks with negligible extra computational cost. We first present both theoretically and experimentally that elementwise square operator has a potential to enhance the learning power of neural networks. Then, we design four types of lightweight modules with elementwise square operators, named as …
Technion（以色列理工学院）；Habana Labs — An Intel Company（Habana Labs — 英特尔公司）
Convolutional neural networks (CNNs) introduce state-of-the-art results for various tasks with the price of high computational demands. Inspired by the observation that spatial correlation exists in CNN output feature maps (ofms), we propose a method to dynamically predict whether ofm activations are zero-valued or not according to their neighboring activation values, thereby avoiding zero-valued activations and reducing the number of convolution operations. We implement the zero activation predictor (ZAP) with a lightweight CNN, which imposes negligible overheads and is easy to deploy on exis…
Graph convolutional networks (GCNs) aim at extending deep learning to arbitrary irregular domains, namely graphs. Their success is highly dependent on how the topology of input graphs is defined and most of the existing GCN architectures rely on predefined or handcrafted graph structures. In this paper, we introduce a novel method that learns the topology (or connectivity) of input graphs as a part of GCN design. The main contribution of our method resides in building an orthogonal connectivity basis that optimally aggregates nodes, through their neighborhood, prior to achieve convolution. Our…
Yazd University（亚兹德大学）；Sharif University of Technology（谢里夫理工大学）；University of Alberta（阿尔伯塔大学）
In recent years, visual tracking methods that are based on discriminative correlation filters (DCF) have been very promising. However, most of these methods suffer from a lack of robust scale estimation skills. Although a wide range of recent DCF-based methods exploit the features that are extracted from deep convolutional neural networks (CNNs) in their translation model, the scale of the visual target is still estimated by hand-crafted features. Whereas the exploitation of CNNs imposes a high computational burden, this paper exploits pre-trained lightweight CNNs models to propose two efficie…
SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases
Department of Robotics and Mechatronics Engineering, University of Dhaka, Dhaka 1000, Bangladesh（机器人与机电工程系，达卡大学，达卡1000，孟加拉国）；GIS and Remote Sensing Lab, Gazipur Agricultural University, Gazipur 1706, Bangladesh（地理信息系统与遥感实验室，加兹ipur农业大学，加兹ipur 1706，孟加拉国）；Bangladesh Sugarcrop Research Institute, Ishwardi, Pabna, Bangladesh（孟加拉国甘蔗作物研究 institute，Ishwardi，Pabna，孟加拉国）；Department of Computer Science and Engineering, University of Dhaka, Dhaka 1000, Bangladesh（计算机科学与工程系，达卡大学，达卡1000，孟加拉国）
End-to-end learning methods have achieved impressive results in many areas of computer vision. At the same time, these methods still suffer from a degradation in performance when testing on new datasets that stem from a different distribution. This is known as the domain shift effect. Recently proposed adaptation methods focus on retraining the network parameters. However, this requires access to all (labeled) source data, a large amount of (unlabeled) target data, and plenty of computational resources. In this work, we propose a lightweight alternative, that allows adapting to the target doma…
To improve the discriminative and generalization ability of lightweight network for face recognition, we propose an efficient variable group convolutional network called VarGFaceNet. Variable group convolution is introduced by VarGNet to solve the conflict between small computational cost and the unbalance of computational intensity inside a block. We employ variable group convolution to design our network which can support large scale face identification while reduce computational cost and parameters. Specifically, we use a head setting to reserve essential information at the start of the net…
A Lightweight CNN Integrated Compact Convolutional Transformer for Multi-Scale Feature Learning and reducing computational complexity for breast cancer mammography image detection and classification
Previous studies on image classification have mainly focused on the performance of the networks, not on real-time operation or model compression. We propose a Gaussian Deep Recurrent visual Attention Model (GDRAM)- a reinforcement learning based lightweight deep neural network for large scale image classification that outperforms the conventional CNN (Convolutional Neural Network) which uses the entire image as input. Highly inspired by the biological visual recognition process, our model mimics the stochastic location of the retina with Gaussian distribution. We evaluate the model on Large cl…
In the paper of ExquisiteNetV1, the ability of classification of ExquisiteNetV1 is worse than DenseNet. In this article, we propose a faster and better model ExquisiteNetV2. We conduct many experiments to evaluate its performance. We test ExquisiteNetV2, ExquisiteNetV1 and other 9 well-known models on 15 credible datasets under the same condition. According to the experimental results, ExquisiteNetV2 gets the highest classification accuracy over half of the datasets. Important of all, ExquisiteNetV2 has fewest amounts of parameters. Besides, in most instances, ExquisiteNetV2 has fastest comput…
National Institute of Technology Silchar（西尔查尔国家理工学院）；Indian Institute of Technology, Indore（印多尔印度理工学院）
Structural alterations have been thoroughly investigated in the brain during the early onset of schizophrenia (SCZ) with the development of neuroimaging methods. The objective of the paper is an efficient classification of SCZ in 2 different classes: Cognitive Normal (CN), and SCZ using magnetic resonance imaging (MRI) images. This paper proposed a lightweight 3D convolutional neural network (CNN) based framework for SCZ diagnosis using MRI images. In the proposed model, lightweight 3D CNN is used to extract both spatial and spectral features simultaneously from 3D volume MRI scans, and classi…
CUHK-SenseTime Joint Lab, The Chinese University of Hong Kong（香港中文大学-商汤科技联合实验室，香港中文大学）
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 the challenging Sintel final pass and KITTI benchmarks, while being 30 times smaller in the model size and 1.36 times faster in the running speed. This is made possible by drilling down to architectural details that might have been missed in the current frameworks: (1) We present a more effective flow inference approach at each pyramid level through a lightwe…
In recent years, the use of Generative Adversarial Networks (GANs) has become very popular in generative image modeling. While style-based GAN architectures yield state-of-the-art results in high-fidelity image synthesis, computationally, they are highly complex. In our work, we focus on the performance optimization of style-based generative models. We analyze the most computationally hard parts of StyleGAN2, and propose changes in the generator network to make it possible to deploy style-based generative networks in the edge devices. We introduce MobileStyleGAN architecture, which has x3.5 fe…
We propose an accurate and lightweight convolutional neural network for stereo estimation with depth completion. We name this method fully-convolutional deformable similarity network with depth completion (FCDSN-DC). This method extends FC-DCNN by improving the feature extractor, adding a network structure for training highly accurate similarity functions and a network structure for filling inconsistent disparity estimates. The whole method consists of three parts. The first part consists of fully-convolutional densely connected layers that computes expressive features of rectified image pairs…
Autonomous driving vehicles (ADVs) hold great hopes to solve traffic congestion problems and reduce the number of traffic accidents. Accurate trajectories prediction of other traffic agents around ADVs is of key importance to achieve safe and efficient driving. Pedestrians, particularly, are more challenging to forecast due to their complex social in-teractions and randomly moving patterns. We propose a Residual Graph Convolutional Neural Network (Res-GCNN), which models the interactive behaviors of pedes-trians by using the adjacent matrix of the constructed graph for the current scene. Thoug…
In recent years, the use of large convolutional kernels has become popular in designing convolutional neural networks due to their ability to capture long-range dependencies and provide large receptive fields. However, the increase in kernel size also leads to a quadratic growth in the number of parameters, resulting in heavy computation and memory requirements. To address this challenge, we propose a neighborhood attention (NA) module that upgrades the standard convolution with a self-attention mechanism. The NA module efficiently extracts long-range dependencies in a sliding window pattern, …
Technical University of Munich（慕尼黑工业大学）；Siemens AG（西门子公司）
We propose a lightweight retrieval-based pipeline to predict 6DOF camera poses from RGB images. Our pipeline uses a convolutional neural network (CNN) to encode a query image as a feature vector. A nearest neighbor lookup finds the pose-wise nearest database image. A siamese convolutional neural network regresses the relative pose from the nearest neighboring database image to the query image. The relative pose is then applied to the nearest neighboring absolute pose to obtain the query image's final absolute pose prediction. Our model is a distilled version of NN-Net that reduces its paramete…
UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution
Ho Chi Minh City Open University（胡志明市开放大学）；AI Tech Lab, Ho Chi Minh City University of Technology（胡志明市科技大学人工智能技术实验室）；Code Mely AI Research Team（Code Mely 人工智能研究团队）；Global College, Shanghai Jiao Tong University（上海交通大学全球学院）；Ha Noi University of Science and Technology（河内科技大学）；University of Manitoba（曼尼托巴大学）
School of Computer and Information Technology, Shanxi University（山西大学计算机与信息技术学院）；Harbin Institute of Technology（哈尔滨工业大学）
Recent years have witnessed great success of convolutional neural network (CNN) for various problems both in low and high level visions. Especially noteworthy is the residual network which was originally proposed to handle high-level vision problems and enjoys several merits. This paper aims to extend the merits of residual network, such as skip connection induced fast training, for a typical low-level vision problem, i.e., single image super-resolution. In general, the two main challenges of existing deep CNN for supper-resolution lie in the gradient exploding/vanishing problem and large numb…
