Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks,which lies in the fact that examples closer to the decision boundaries are much more vulnerable t...
详细信息
Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks,which lies in the fact that examples closer to the decision boundaries are much more vulnerable to being attacked and should be given larger *** probability margin(PM)method is a promising approach to continuously and path-independently mea-suring such closeness between the example and decision ***,the performance of PM is limited due to the fact that PM fails to effectively distinguish the examples having only one misclassified category and the ones with multiple misclassified categories,where the latter is closer to multi-classification decision boundaries and is supported to be more critical in our *** tackle this problem,this paper proposed an improved PM criterion,called confused-label-based PM(CL-PM),to measure the closeness mentioned above and reweight adversarial examples during ***-cally,a confused label(CL)is defined as the label whose prediction probability is greater than that of the ground truth label given a specific adversarial *** of considering the discrepancy between the probability of the true label and the probability of the most misclassified label as the PM method does,we evaluate the closeness by accumulating the probability differences of all the CLs and ground truth ***-PM shares a negative correlation with data vulnerability:data with larger/smaller CL-PM is safer/riskier and should have a smaller/larger *** demonstrated that CL-PM is more reliable in indicating the closeness regarding multiple misclassified categories,and reweighting adversarial training based on CL-PM outperformed state-of-the-art counterparts.
Recent state-of-the-art semi-supervised learning(SSL)methods usually use data augmentations as core *** methods,however,are limited to simple transformations such as the augmentations under the instance’s naive repre...
详细信息
Recent state-of-the-art semi-supervised learning(SSL)methods usually use data augmentations as core *** methods,however,are limited to simple transformations such as the augmentations under the instance’s naive representations or the augmentations under the instance’s semantic *** tackle this problem,we offer a unique insight into data augmentations and propose a novel data-augmentation-based semi-supervised learning method,called Attentive Neighborhood Feature Aug-mentation(ANFA).The motivation of our method lies in the observation that the relationship between the given feature and its neighborhood may contribute to constructing more reliable transformations for the data,and further facilitating the classifier to distinguish the ambiguous features from the low-dense ***,we first project the labeled and unlabeled data points into an embedding space and then construct a neighbor graph that serves as a similarity measure based on the similar representations in the embedding ***,we employ an attention mechanism to transform the target features into augmented ones based on the neighbor ***,we formulate a novel semi-supervised loss by encouraging the predictions of the interpolations of augmented features to be consistent with the corresponding interpolations of the predictions of the target *** carried out exper-iments on SVHN and CIFAR-10 benchmark datasets and the experimental results demonstrate that our method outperforms the state-of-the-art methods when the number of labeled examples is limited.
Mobile Industrial Internet of Things(IIoT)applications have achieved the explosive growth in recent *** mobile IIoT has flourished and become the backbone of the industry,laying a solid foundation for the interconnect...
详细信息
Mobile Industrial Internet of Things(IIoT)applications have achieved the explosive growth in recent *** mobile IIoT has flourished and become the backbone of the industry,laying a solid foundation for the interconnection of all *** variety of application scenarios has brought serious challenges to mobile IIoT networks,which face complex and changeable communication *** data secure transmission is critical for mobile IIoT *** paper investigates the data secure transmission performance prediction of mobile IIoT *** cut down computational complexity,we propose a data secure transmission scheme employing Transmit Antenna Selection(TAS).The novel secrecy performance expressions are first ***,to realize real-time secrecy analysis,we design an improved Convolutional Neural Network(CNN)model,and propose an intelligent data secure transmission performance prediction *** mobile signals,the important features may be removed by the pooling *** will lead to negative effects on the secrecy performance prediction.A novel nine-layer improved CNN model is *** of the input and output layers,it removes the pooling layer and contains six convolution ***,Back-Propagation(BP)and LeNet methods are employed to compare with the proposed *** simulation analysis,good prediction accuracy is achieved by the CNN *** prediction accuracy obtains a 59%increase.
Different from the traditional warehousing system, in the multi-AGV warehouse scheduling control system, the constraints of poor connectivity of the conveying track have led to the emergence of urgent problems such as...
详细信息
Video archives play a crucial role in various industries, from media and entertainment to security and surveillance. Managing these archives efficiently and securely is a growing challenge due to the increasing volume...
详细信息
Semi-supervised learning has garnered significant attention, particularly in medical image segmentation, owing to its capacity to leverage a large number of unlabeled data and a limited amount of labeled data to impro...
详细信息
In the recognition of distracted driving behaviour, traditional manual feature extraction is subjective and complex;single deep convolutional network also has problems such as insufficient generalisation performance a...
详细信息
Establishing dense correspondences between semantically similar images is a challenging task. Cost aggregation is a crucial step in finding correct dense correspondences, with the goal of optimizing the initial correl...
详细信息
Semi-supervised learning (SSL) is a successful paradigm that can use unlabelled data to alleviate the labelling cost problem in supervised learning. However, the excellent performance brought by SSL does not transfer ...
详细信息
intelligent Transportation Systems are tasked with enhancing road safety, a crucial challenge given that approximately 1.35 million fatalities occur globally each year, with 15%–27% of these deaths attributed to Anom...
详细信息
intelligent Transportation Systems are tasked with enhancing road safety, a crucial challenge given that approximately 1.35 million fatalities occur globally each year, with 15%–27% of these deaths attributed to Anomalous Driving Behaviors (ADBs). Detecting these behaviors in real time is vital for preventing accidents and improving traffic safety. However, the complexity of driving environments, characterized by diverse scenarios, drivers, and vehicle conditions, makes ADB detection a challenging task. This article proposes a novel approach for ADB detection, leveraging the advantages of multimodal data, adaptive masking, and multihead self-attention mechanisms. The proposed method first employs an adaptive masking technique based on the Softmax function to sparsify input features, effectively reducing the influence of irrelevant information. By focusing on key features, the model becomes more resilient to noise, such as background clutter or irrelevant driver actions, which might otherwise interfere with the detection of abnormal behaviors. To further enhance feature integration across different data modalities (e.g., visual, infrared, and depth data), a multihead self-attention mechanism is incorporated. This mechanism enables the model to prioritize important information from various sensor inputs, fostering more effective multimodal fusion and better decision-making for behavior classification. In addition, a supervised contrastive learning strategy is utilized to mitigate memory usage, a common challenge in real-time systems where computational resources are limited. This approach ensures efficient learning by emphasizing the distinction between normal and abnormal behaviors while minimizing the memory footprint of the model. Extensive experiments on two benchmark datasets, 3MDAD and DAD, demonstrate the proposed method's superior performance in detecting ADBs. The results indicate a significant improvement in detection accuracy and robustness, highlighting th
暂无评论