视觉地点识别（VPR）是一个具有挑战性的任务，具有巨大的计算成本与高识别性能之间的不平衡。由于轻质卷积神经网络（CNNS）和局部聚合描述符（VLAD）层向量的火车能力的实用特征提取能力，我们提出了一种由前部组成的轻量级弱监管的端到端神经网络-anded的感知模型称为ghostcnn和学习的VLAD层作为后端。 Ghostcnn基于幽灵模块，这些模块是基于重量的CNN架构。它们可以使用线性操作而不是传统的卷积过程生成冗余特征映射，从而在计算资源和识别准确性之间进行良好的权衡。为了进一步增强我们提出的轻量级模型，我们将扩张的卷曲添加到Ghost模块中，以获取包含更多空间语义信息的功能，提高准确性。最后，在常用的公共基准和我们的私人数据集上进行的丰富实验验证了所提出的神经网络，分别将VGG16-NetVlad的拖鞋和参数减少了99.04％和80.16％。此外，两种模型都达到了类似的准确性。

Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design. This paper proposes a novel Ghost module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features. The proposed Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks. Ghost bottlenecks are designed to stack Ghost modules, and then the lightweight Ghost-Net can be easily established. Experiments conducted on benchmarks demonstrate that the proposed Ghost module is an impressive alternative of convolution layers in baseline models, and our GhostNet can achieve higher recognition performance (e.g. 75.7% top-1 accuracy) than MobileNetV3 with similar computational cost on the ImageNet ILSVRC-2012 classification dataset. Code is available at https: //github.com/huawei-noah/ghostnet.

We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following three principal contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the "Vector of Locally Aggregated Descriptors" image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we develop a training procedure, based on a new weakly supervised ranking loss, to learn parameters of the architecture in an end-to-end manner from images depicting the same places over time downloaded from Google Street View Time Machine. Finally, we show that the proposed architecture significantly outperforms non-learnt image representations and off-the-shelf CNN descriptors on two challenging place recognition benchmarks, and improves over current stateof-the-art compact image representations on standard image retrieval benchmarks.

由于存储器和计算资源有限，部署在移动设备上的卷积神经网络（CNNS）是困难的。我们的目标是通过利用特征图中的冗余来设计包括CPU和GPU的异构设备的高效神经网络，这很少在神经结构设计中进行了研究。对于类似CPU的设备，我们提出了一种新颖的CPU高效的Ghost（C-Ghost）模块，以生成从廉价操作的更多特征映射。基于一组内在的特征映射，我们使用廉价的成本应用一系列线性变换，以生成许多幽灵特征图，可以完全揭示内在特征的信息。所提出的C-Ghost模块可以作为即插即用组件，以升级现有的卷积神经网络。 C-Ghost瓶颈旨在堆叠C-Ghost模块，然后可以轻松建立轻量级的C-Ghostnet。我们进一步考虑GPU设备的有效网络。在建筑阶段的情况下，不涉及太多的GPU效率（例如，深度明智的卷积），我们建议利用阶段明智的特征冗余来制定GPU高效的幽灵（G-GHOST）阶段结构。舞台中的特征被分成两个部分，其中使用具有较少输出通道的原始块处理第一部分，用于生成内在特征，另一个通过利用阶段明智的冗余来生成廉价的操作。在基准测试上进行的实验证明了所提出的C-Ghost模块和G-Ghost阶段的有效性。 C-Ghostnet和G-Ghostnet分别可以分别实现CPU和GPU的准确性和延迟的最佳权衡。代码可在https://github.com/huawei-noah/cv-backbones获得。

Visual Place Recognition is an essential component of systems for camera localization and loop closure detection, and it has attracted widespread interest in multiple domains such as computer vision, robotics and AR/VR. In this work, we propose a faster, lighter and stronger approach that can generate models with fewer parameters and can spend less time in the inference stage. We designed RepVGG-lite as the backbone network in our architecture, it is more discriminative than other general networks in the Place Recognition task. RepVGG-lite has more speed advantages while achieving higher performance. We extract only one scale patch-level descriptors from global descriptors in the feature extraction stage. Then we design a trainable feature matcher to exploit both spatial relationships of the features and their visual appearance, which is based on the attention mechanism. Comprehensive experiments on challenging benchmark datasets demonstrate the proposed method outperforming recent other state-of-the-art learned approaches, and achieving even higher inference speed. Our system has 14 times less params than Patch-NetVLAD, 6.8 times lower theoretical FLOPs, and run faster 21 and 33 times in feature extraction and feature matching. Moreover, the performance of our approach is 0.5\% better than Patch-NetVLAD in Recall@1. We used subsets of Mapillary Street Level Sequences dataset to conduct experiments for all other challenging conditions.

Image descriptors based on activations of Convolutional Neural Networks (CNNs) have become dominant in image retrieval due to their discriminative power, compactness of representation, and search efficiency. Training of CNNs, either from scratch or fine-tuning, requires a large amount of annotated data, where a high quality of annotation is often crucial. In this work, we propose to fine-tune CNNs for image retrieval on a large collection of unordered images in a fully automated manner. Reconstructed 3D models obtained by the state-of-the-art retrieval and structure-from-motion methods guide the selection of the training data. We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval. CNN descriptor whitening discriminatively learned from the same training data outperforms commonly used PCA whitening. We propose a novel trainable Generalized-Mean (GeM) pooling layer that generalizes max and average pooling and show that it boosts retrieval performance. Applying the proposed method to the VGG network achieves state-of-the-art performance on the standard benchmarks: Oxford Buildings, Paris, and Holidays datasets.

Semiconductor manufacturing is on the cusp of a revolution: the Internet of Things (IoT). With IoT we can connect all the equipment and feed information back to the factory so that quality issues can be detected. In this situation, more and more edge devices are used in wafer inspection equipment. This edge device must have the ability to quickly detect defects. Therefore, how to develop a high-efficiency architecture for automatic defect classification to be suitable for edge devices is the primary task. In this paper, we present a novel architecture that can perform defect classification in a more efficient way. The first function is self-proliferation, using a series of linear transformations to generate more feature maps at a cheaper cost. The second function is self-attention, capturing the long-range dependencies of feature map by the channel-wise and spatial-wise attention mechanism. We named this method as self-proliferation-and-attention neural network. This method has been successfully applied to various defect pattern classification tasks. Compared with other latest methods, SP&A-Net has higher accuracy and lower computation cost in many defect inspection tasks.

Semantic segmentation of UAV aerial remote sensing images provides a more efficient and convenient surveying and mapping method for traditional surveying and mapping. In order to make the model lightweight and improve a certain accuracy, this research developed a new lightweight and efficient network for the extraction of ground features from UAV aerial remote sensing images, called LDMCNet. Meanwhile, this research develops a powerful lightweight backbone network for the proposed semantic segmentation model. It is called LDCNet, and it is hoped that it can become the backbone network of a new generation of lightweight semantic segmentation algorithms. The proposed model uses dual multi-scale context modules, namely the Atrous Space Pyramid Pooling module (ASPP) and the Object Context Representation module (OCR). In addition, this research constructs a private dataset for semantic segmentation of aerial remote sensing images from drones. This data set contains 2431 training sets, 945 validation sets, and 475 test sets. The proposed model performs well on this dataset, with only 1.4M parameters and 5.48G floating-point operations (FLOPs), achieving an average intersection-over-union ratio (mIoU) of 71.12%. 7.88% higher than the baseline model. In order to verify the effectiveness of the proposed model, training on the public datasets "LoveDA" and "CITY-OSM" also achieved excellent results, achieving mIoU of 65.27% and 74.39%, respectively.

近年来，已经产生了大量的视觉内容，并从许多领域共享，例如社交媒体平台，医学成像和机器人。这种丰富的内容创建和共享引入了新的挑战，特别是在寻找类似内容内容的图像检索（CBIR）-A的数据库中，即长期建立的研究区域，其中需要改进的效率和准确性来实时检索。人工智能在CBIR中取得了进展，并大大促进了实例搜索过程。在本调查中，我们审查了最近基于深度学习算法和技术开发的实例检索工作，通过深网络架构类型，深度功能，功能嵌入方法以及网络微调策略组织了调查。我们的调查考虑了各种各样的最新方法，在那里，我们识别里程碑工作，揭示各种方法之间的联系，并呈现常用的基准，评估结果，共同挑战，并提出未来的未来方向。

现有的多尺度解决方案会导致仅增加接受场大小的风险，同时忽略小型接受场。因此，有效构建自适应神经网络以识别各种空间尺度对象是一个具有挑战性的问题。为了解决这个问题，我们首先引入一个新的注意力维度，即除了现有的注意力维度（例如渠道，空间和分支）之外，并提出了一个新颖的选择性深度注意网络，以对称地处理各种视觉中的多尺度对象任务。具体而言，在给定神经网络的每个阶段内的块，即重新连接，输出层次功能映射共享相同的分辨率但具有不同的接收场大小。基于此结构属性，我们设计了一个舞台建筑模块，即SDA，其中包括树干分支和类似SE的注意力分支。躯干分支的块输出融合在一起，以通过注意力分支指导其深度注意力分配。根据提出的注意机制，我们可以动态选择不同的深度特征，这有助于自适应调整可变大小输入对象的接收场大小。这样，跨块信息相互作用会导致沿深度方向的远距离依赖关系。与其他多尺度方法相比，我们的SDA方法结合了从以前的块到舞台输出的多个接受场，从而提供了更广泛，更丰富的有效接收场。此外，我们的方法可以用作其他多尺度网络以及注意力网络的可插入模块，并创造为SDA- $ x $ net。它们的组合进一步扩展了有效的接受场的范围，可以实现可解释的神经网络。我们的源代码可在\ url {https://github.com/qingbeiguo/sda-xnet.git}中获得。

Visual localization plays an important role for intelligent robots and autonomous driving, especially when the accuracy of GNSS is unreliable. Recently, camera localization in LiDAR maps has attracted more and more attention for its low cost and potential robustness to illumination and weather changes. However, the commonly used pinhole camera has a narrow Field-of-View, thus leading to limited information compared with the omni-directional LiDAR data. To overcome this limitation, we focus on correlating the information of 360 equirectangular images to point clouds, proposing an end-to-end learnable network to conduct cross-modal visual localization by establishing similarity in high-dimensional feature space. Inspired by the attention mechanism, we optimize the network to capture the salient feature for comparing images and point clouds. We construct several sequences containing 360 equirectangular images and corresponding point clouds based on the KITTI-360 dataset and conduct extensive experiments. The results demonstrate the effectiveness of our approach.

人类自然有效地在复杂的场景中找到突出区域。通过这种观察的动机，引入了计算机视觉中的注意力机制，目的是模仿人类视觉系统的这一方面。这种注意机制可以基于输入图像的特征被视为动态权重调整过程。注意机制在许多视觉任务中取得了巨大的成功，包括图像分类，对象检测，语义分割，视频理解，图像生成，3D视觉，多模态任务和自我监督的学习。在本调查中，我们对计算机愿景中的各种关注机制进行了全面的审查，并根据渠道注意，空间关注，暂时关注和分支注意力进行分类。相关的存储库https：//github.com/menghaoguo/awesome-vision-tions致力于收集相关的工作。我们还建议了未来的注意机制研究方向。

随着对手工卫生的需求不断增长和使用的便利性，掌上识别最近具有淡淡的发展，为人识别提供了有效的解决方案。尽管已经致力于该地区的许多努力，但仍然不确定无接触棕榈污染的辨别能力，特别是对于大规模数据集。为了解决问题，在本文中，我们构建了一个大型无尺寸的棕榈纹数据集，其中包含了来自1167人的2334个棕榈手机。为了我们的最佳知识，它是有史以来最大的非接触式手掌形象基准，而是关于个人和棕榈树的数量收集。此外，我们提出了一个名为3DCPN（3D卷积棕榈识别网络）的无棕榈识别的新型深度学习框架，它利用3D卷积来动态地集成多个Gabor功能。在3DCPN中，嵌入到第一层中的新颖变体以增强曲线特征提取。通过精心设计的集合方案，然后将低级别的3D功能卷积以提取高级功能。最后在顶部，我们设置了基于地区的损失功能，以加强全局和本地描述符的辨别能力。为了展示我们方法的优越性，在我们的数据集和其他流行数据库同济和IITD上进行了广泛的实验，其中结果显示了所提出的3DCPN实现最先进的或可比性的性能。

X射线图像在制造业的质量保证中起着重要作用，因为它可以反映焊接区域的内部条件。然而，不同缺陷类型的形状和规模大大变化，这使得模型检测焊接缺陷的挑战性。在本文中，我们提出了一种基于卷积神经网络的焊接缺陷检测方法，即打火机和更快的YOLO（LF-YOLO）。具体地，增强的多尺度特征（RMF）模块旨在实现基于参数和无参数的多尺度信息提取操作。 RMF使得提取的特征映射能够代表更丰富的信息，该信息是通过卓越的层级融合结构实现的。为了提高检测网络的性能，我们提出了一个有效的特征提取（EFE）模块。 EFE处理具有极低消耗量的输入数据，并提高了实际行业中整个网络的实用性。实验结果表明，我们的焊接缺陷检测网络在性能和消耗之间实现了令人满意的平衡，达到92.9平均平均精度MAP50，每秒61.5帧（FPS）。为了进一步证明我们方法的能力，我们在公共数据集MS Coco上测试它，结果表明我们的LF-YOLO具有出色的多功能性检测性能。代码可在https://github.com/lmomoy/lf-yolo上获得。

交通标志检测是无人驾驶系统的具有挑战性的任务，特别是对于检测多尺度目标和检测的实时问题。在交通标志检测过程中，目标的比例大大变化，这将对检测精度产生一定的影响。特征金字塔广泛用于解决这个问题，但它可能会破坏不同的交通标志尺度的功能一致性。此外，在实际应用中，常用方法难以提高多尺度交通标志的检测精度，同时确保实时检测。在本文中，我们提出了一种改进的特征金字塔模型，名为AF-FPN，它利用自适应注意模块（AAM）和特征增强模块（FEM）来减少特征映射生成过程中的信息损失，并提高表示能力特征金字塔。我们用AF-FPN替换了YOLOV5中的原始特征金字塔网络，这在确保实时检测的前提下提高了YOLOV5网络的多尺度目标的检测性能。此外，提出了一种新的自动学习数据增强方法来丰富数据集，提高模型的稳健性，使其更适合实际情况。关于清华腾讯100K（TT100K）数据集的广泛实验结果证明了与多种最先进的方法相比，所提出的方法的有效性和优越性。

皮肤镜图像中的皮肤病变检测对于通过计算机化设备对皮肤癌的准确和早期诊断至关重要。当前的皮肤病变细分方法在具有挑战性的环境中表现出较差的性能，例如不明显的病变边界，病变和周围区域之间的对比度低，或导致皮肤病变分割的异质背景。为了准确识别邻近区域的病变，我们提出了基于卷积分解的扩张尺度特征融合网络。我们的网络旨在同时提取不同尺度的功能，这些功能是系统地融合的，以更好地检测。提出的模型具有令人满意的精度和效率。进行病变分割的各种实验以及与最新模型的比较。我们提出的模型始终展示最先进的结果。

人行道表面数据的获取和评估在路面条件评估中起着至关重要的作用。在本文中，提出了一个称为RHA-NET的自动路面裂纹分割的有效端到端网络，以提高路面裂纹分割精度。 RHA-NET是通过将残留块（重阻）和混合注意块集成到编码器架构结构中来构建的。这些重组用于提高RHA-NET提取高级抽象特征的能力。混合注意块旨在融合低级功能和高级功能，以帮助模型专注于正确的频道和裂纹区域，从而提高RHA-NET的功能表现能力。构建并用于训练和评估所提出的模型的图像数据集，其中包含由自设计的移动机器人收集的789个路面裂纹图像。与其他最先进的网络相比，所提出的模型在全面的消融研究中验证了添加残留块和混合注意机制的功能。此外，通过引入深度可分离卷积生成的模型的轻加权版本可以更好地实现性能和更快的处理速度，而U-NET参数数量的1/30。开发的系统可以在嵌入式设备Jetson TX2（25 fps）上实时划分路面裂纹。实时实验拍摄的视频将在https://youtu.be/3xiogk0fig4上发布。

In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience community that the receptive field size of visual cortical neurons are modulated by the stimulus, which has been rarely considered in constructing CNNs. We propose a dynamic selection mechanism in CNNs that allows each neuron to adaptively adjust its receptive field size based on multiple scales of input information. A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer. Multiple SK units are stacked to a deep network termed Selective Kernel Networks (SKNets). On the ImageNet and CIFAR benchmarks, we empirically show that SKNet outperforms the existing state-of-the-art architectures with lower model complexity. Detailed analyses show that the neurons in SKNet can capture target objects with different scales, which verifies the capability of neurons for adaptively adjusting their receptive field sizes according to the input. The code and models are available at https://github.com/implus/SKNet.

Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layerwise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods. The source code and trained models are available on https://mmcheng.net/res2net/.

Real-time semantic segmentation has played an important role in intelligent vehicle scenarios. Recently, numerous networks have incorporated information from multi-size receptive fields to facilitate feature extraction in real-time semantic segmentation tasks. However, these methods preferentially adopt massive receptive fields to elicit more contextual information, which may result in inefficient feature extraction. We believe that the elaborated receptive fields are crucial, considering the demand for efficient feature extraction in real-time tasks. Therefore, we propose an effective and efficient architecture termed Dilation-wise Residual segmentation (DWRSeg), which possesses different sets of receptive field sizes within different stages. The architecture involves (i) a Dilation-wise Residual (DWR) module for extracting features based on different scales of receptive fields in the high level of the network; (ii) a Simple Inverted Residual (SIR) module that uses an inverted bottleneck structure to extract features from the low stage; and (iii) a simple fully convolutional network (FCN)-like decoder for aggregating multiscale feature maps to generate the prediction. Extensive experiments on the Cityscapes and CamVid datasets demonstrate the effectiveness of our method by achieving a state-of-the-art trade-off between accuracy and inference speed, in addition to being lighter weight. Without using pretraining or resorting to any training trick, we achieve 72.7% mIoU on the Cityscapes test set at a speed of 319.5 FPS on one NVIDIA GeForce GTX 1080 Ti card, which is significantly faster than existing methods. The code and trained models are publicly available.