Recent works show that contrastive learning based on memory banks is an effective framework for unsupervised person Re-IDentification (ReID). In existing methods, memory banks are typically initialized with cluster centroids and rewritten with positive samples via the momentum mechanism along with the model training. However, this mechanism solely focuses on the intra-class compactness by pulling memory banks close to positive samples, neglecting the inter-class separability among different memory banks. Rewriting memory banks with partial constraint limits their discrimination capacities, and hence hinders learning discriminative features based on those memory banks. In this paper, we claim that memory banks should be rewritten with both intra-class and inter-class constraints, and therefore propose a unified memory bank rewriting mechanism, Bidirectionally Memory bank reWriting (BMW), to chase enhanced discrimination capacity. Specifically, BMW formulates the memory bank rewriting as the gradient descent update with two objectives, i.e., reducing intra-class diversity and enhancing inter-class separability. To effectively enhance the separability of memory banks with limited number of rewriting steps, we further design a novel objective formulation for the inter-class constraint, which is more effective for one step update. BMW enhances both representation and discrimination capacities of memory banks, thus leads to an effective ReID feature optimization. BMW is simple yet effective and can serve as a new paradigm for person ReID methods based on memory banks. Extensive experiments on standard benchmarks demonstrate the effectiveness of our BMW method in unsupervised ReID model training. Specially, BMW even outperforms previous methods that use stronger backbones. Code is available at https://github.com/liu-xb/BMW.

In the deep learning approach for identifying plant diseases, the high complexity of the network model, the large number of parameters, and great computational effort make it challenging to deploy the model on terminal devices with limited computational resources. In this study, a lightweight method for plant diseases identification that is an improved version of the ShuffleNetV2 model is proposed. In the proposed model, the depthwise convolution in the basic module of ShuffleNetV2 is replaced with mixed depthwise convolution to capture crop pest images with different resolutions; the efficient channel attention module is added into the ShuffleNetV2 model network structure to enhance the channel features; and the ReLU activation function is replaced with the ReLU6 activation function to prevent the gen-eration of large gradients. Experiments are conducted on the public dataset PlantVillage. The results show that the proposed model achieves an accuracy of 99.43%, which is an improvement of 0.6 percentage points compared to the ShuffleNetV2 model. Compared to lightweight network models, such as MobileNetV2, MobileNetV3, EfficientNet, and EfficientNetV2, and classical convolutional neural network models, such as ResNet34, ResNet50, and ResNet101, the proposed model has fewer parameters and higher recognition accuracy, which provides guidance for deploying crop pest identification methods on resource-constrained devices, including mobile terminals.

Using intelligent agriculture is an important way for the industry to achieve high-quality development. To improve the accuracy of the identification of crop diseases under conditions of limited computing resources, such as in mobile and edge computing, we propose an improved lightweight MobileNetV2 crop disease identification model. In this study, MobileNetV2 is used as the backbone network for the application of an improved Bottleneck structure. First, the number of operation channels is reduced using point-by-point convolution, the number of parameters of the model is reduced, and the re-parameterized multilayer perceptron (RepMLP) module is introduced; the latter can capture long-distance dependencies between features and obtain local a priori information to enhance the global perception of the model. Second, the efficient channel-attention mechanism is added to adjust the image-feature channel weights so as to improve the recognition accuracy of the model, and the Hardswish activation function is introduced instead of the ReLU6 activation function to further improve performance. The final experimental results show that the improved MobilNetV2 model achieves 99.53% accuracy in the PlantVillage crop disease dataset, which is 0.3% higher than the original model, and the number of covariates is only 0.9M, which is 59% less than the original model. Also, the inference speed is improved by 8.5% over the original model. The crop disease identification method proposed in this article provides a reference for deployment and application on edge and mobile devices.

•It is an original work on domain gap evaluation.•Proposed method can reasonably measure domain gaps.•Proposed method is also instructive for applications on unlabeled datasets.

Recent works show that mean-teaching is an effective framework for unsupervised domain adaptive person re-identification. However, existing methods perform contrastive learning on selected samples between teacher and student networks, which is sensitive to noises in pseudo labels and neglects the relationship among most samples. Moreover, these methods are not effective in cooperation of different teacher networks. To handle these issues, this paper proposes a Graph Consistency based Mean-Teaching (GCMT) method with constructing the Graph Consistency Constraint (GCC) between teacher and student networks. Specifically, given unlabeled training images, we apply teacher networks to extract corresponding features and further construct a teacher graph for each teacher network to describe the similarity relationships among training images. To boost the representation learning, different teacher graphs are fused to provide the supervise signal for optimizing student networks. GCMT fuses similarity relationships predicted by different teacher networks as supervision and effectively optimizes student networks with more sample relationships involved. Experiments on three datasets, i.e., Market-1501, DukeMTMCreID, and MSMT17, show that proposed GCMT outperforms state-of-the-art methods by clear margin. Specially, GCMT even outperforms the previous method that uses a deeper backbone. Experimental results also show that GCMT can effectively boost the performance with multiple teacher and student networks. Our code is available at https://github.com/liu-xb/GCMT .

Traditional Bag-of-visual Words (BoWs) model is commonly generated with many steps including local feature extraction, codebook generation, and feature quantization, etc. Those steps are relatively independent with each other and are hard to be jointly optimized. Moreover, the dependency on hand-crafted local feature makes BoWs model not effective in conveying high-level semantics. These issues largely hinder the performance of BoWs model in large-scale image applications. To conquer these issues, we propose an End-to-End BoWs (E^2BoWs) model based on Deep Convolutional Neural Network (DCNN). Our model takes an image as input, then identifies and separates the semantic objects in it, and finally outputs the visual words with high semantic discriminative power. Specifically, our model firstly generates Semantic Feature Maps (SFMs) corresponding to different object categories through convolutional layers, then introduces Bag-of-Words Layers (BoWL) to generate visual words for each individual feature map. We also introduce a novel learning algorithm to reinforce the sparsity of the generated E^2BoWs model, which further ensures the time and memory efficiency. We evaluate the proposed E^2BoWs model on several image search datasets including CIFAR-10, CIFAR-100, MIRFLICKR-25K and NUS-WIDE. Experimental results show that our method achieves promising accuracy and efficiency compared with recent deep learning based retrieval works.

Domain adaptive person Re-Identification (ReID) is challenging owing to the domain gap and shortage of annotations on target scenarios. To handle those two challenges, this paper proposes a coupling optimization method including the Domain-Invariant Mapping (DIM) method and the Global-Local distance Optimization (GLO), respectively. Different from previous methods that transfer knowledge in two stages, the DIM achieves a more efficient one-stage knowledge transfer by mapping images in labeled and unlabeled datasets to a shared feature space. GLO is designed to train the ReID model with unsupervised setting on the target domain. Instead of relying on existing optimization strategies designed for supervised training, GLO involves more images in distance optimization, and achieves better robustness to noisy label prediction. GLO also integrates distance optimizations in both the global dataset and local training batch, thus exhibits better training efficiency. Extensive experiments on three large-scale datasets, i.e., Market-1501, DukeMTMC-reID, and MSMT17, show that our coupling optimization outperforms state-of-the-art methods by a large margin. Our method also works well in unsupervised training, and even outperforms several recent domain adaptive methods.

The laborious manual person ID annotation results in limited training data and increased difficulty in learning discriminative representations. Meanwhile, high dimensional deep features are not ready for fast indexing and matching. Those challenges hinder the application of person Re-Identification (ReID) in large-scale data. To conquer those challenges, we propose a novel training strategy to learn compact binary hash codes. To facilitate feature learning, person images are decomposed into body parts, which are then composed across images into new positive and negative training samples. Binary code quality restrictions are also applied the during training procedure. Requiring no extra annotation costs, our algorithm iteratively generates hard training samples by itself and makes discriminative hash code learning with a limited number of labeled data possible. We hence use "self-guided" to describe this training procedure. Extensive experiments are conducted on two large-scale person ReID datasets, i.e., Market1501 and MSMT17 with distractors, showing our method is competitive compared with recent works.

Image understanding is a fundamental task for many multimedia and computer vision applications, such as self-driving, multimedia retrieval, and augmented reality, etc. In this paper, we demonstrate that edge detection could aid image understanding tasks such as semantic segmentation, optical flow estimation, and object proposal generation. Based on our recent research efforts on edge detection, we develop a robust and efficient Edge-Aided imaGe undERstanding system named as EAGER. EAGER is built on a compact and efficient edge detection module, which is constructed with a bi-directional cascade network, multi-scale feature enhancement, and layer-specific training supervision, respectively. Based on detected edges, EAGER achieves accurate semantic segment, optical flow estimation, as well as object bounding-box proposal generation for user-uploaded images and videos.

Vehicle Re-Identification (Re-ID) is challenging because vehicles of the same model commonly show similar appearance. We tackle this challenge by proposing a Global-Regional Feature (GRF) that depicts extra local details to enhance discrimination power in addition to the global context. It is motivated by the observation that, vehicles of same color, maker, and model can be distinguished by their regional difference, e.g., the decorations on the windshields. To accelerate the GRF learning and promote its discrimination power, we propose a Group-Group Loss (GGL) to optimize the distance within and across vehicle image groups. Different from the siamese or triplet loss, GGL is directly computed on image groups rather than individual sample pairs or triplets. By avoiding traversing numerous sample combinations, GGL makes the model training easier and more efficient. Those two contributions highlight this work from previous methods on vehicle Re-ID task, which commonly learn global features with triplet loss or its variants. We evaluate our methods on two large-scale vehicle Re-ID datasets, i.e., VeRi and VehicleID. Experimental results show our methods achieve promising performance in comparison with recent works.

Previous works on vehicle Re-ID mainly focus on extracting global features and learning distance metrics. Because some vehicles commonly share same model and maker, it is hard to distinguish them based on their global appearances. Compared with the global appearance, local regions such as decorations and inspection stickers attached to the windshield, may be more distinctive for vehicle Re-ID. To embed the detailed visual cues in those local regions, we propose a Region-Aware deep Model (RAM). Specifically, in addition to extracting global features, RAM also extracts features from a series of local regions. As each local region conveys more distinctive visual cues, RAM encourages the deep model to learn discriminative features. We also introduce a novel learning algorithm to jointly use vehicle IDs, types/models, and colors to train the RAM. This strategy fuses more cues for training and results in more discriminative global and regional features. We evaluate our methods on two large-scale vehicle Re-ID datasets, i.e., VeRi and VehicleID. Experimental results show our methods achieve promising performance in comparison with recent works.

Most existing methods on vehicle Re-Identification (ReID) extract global features on vehicles. However, as some vehicles have the same model and color, it is hard to distinguish them only depend on global appearance. Compared with global appearance, some local regions could be more discriminative. Moreover, it is not reasonable to use feature maps with equal channels weights for methods based on Deep Convolutional Neural Network (DCNN), as different channels have different discrimination ability. To automatically discover discriminative regions on vehicles and discriminative channels in networks, we propose a Spatial and Channel Attention Network (SCAN) based on DCNN. Specifically, the attention model contains two branches, i.e., spatial attention branch and channel attention branch, which are embedded after convolutional layers to refine the feature maps. Spatial and channel attention branches adjust the weights of outputs in different positions and different channels to highlight the outputs in discriminative regions and channels, respectively. Then feature maps are refined by our attention model and more discriminative features can be extracted automatically. We jointly train the attention branches and convolutional layers by triplet loss and cross-entropy loss. We evaluate our methods on two large-scale vehicle ReID datasets, i.e., VehicleID and VeRi-776. Extensive evaluations on two datasets show that our methods achieve promising results and outperform the state-of-the-art approaches on VeRi-776.

With the capability of locating and tracking specific suspects or vehicles in a large camera network, person Re-Identification (ReID) and vehicle ReID show potential to be a key technology in smart surveillance system. They have been drawing lots of attentions from both academia and industry. To demonstrate our recent research progresses on those two tasks, we develop a robust and efficient person and video ReID system named as VP-ReID. This system is build based on our recent works including Deep Convolutional Neural Network design for discriminative feature extraction, efficient off-line indexing, as well as distance metric optimization for deep feature learning. Constructed upon those algorithms, VP-ReID identifies query vehicle and person efficiently and accurately from a large gallery set.

一、利用网络与计算机技术改进医院财务内部控制 1.强化会计电算化下医院财务控制制度的建立.严格的内控制度是会计电算化信息真实可靠的保证.必须要建立健全操作管理制度、硬件与软件管理制度、会计档案管理制度、医疗收费管理制度、收费稽核管理制度、退费管理制度等.每个操作人员要凭个人密码进入微机,做到责任明确、有法可依、有章可循,严格执行已制定的各项制度,并重点针对业务处理过程中的关键控制点,落实到决策、执行、监督、反馈等各个环节.同时,要随着外部环境的变化、单位业务的不断调整和管理要求的提高,不断健全与更新内部控制制度.