Search

This paper proposes a channel pruning method based on multi-stage feature de-correlation to obtain a more efficient convolutional neural network (CNN) model. Based on the correlation of hidden features at each level of the network, we refine more efficient features of each convolutional layer by applying feature de-correlation constraints (MFD Loss) to each convolutional layer of the network and then prune channels according to the modulus of the feature maps output from each layer. After several rounds of pruning and fine-tuning, a network with similar accuracy, a substantially smaller network size, and more efficient operation is generated compared to the original model. Our experiments on pruning various popular CNN models on many standard datasets demonstrate the method’s effectiveness. Specifically, for VGG-16 on CIFAR10, our approach eliminates parameters by 97.0%, saves Float-Point-Operations (FLOPs) by 66.9%, with a 0.4% accuracy gain and state-of-art performance. For ResNet-50 on the ImageNet dataset, our method eliminates parameters by 30.0%, and saves FLOPs by 52%, with 1.4% accuracy loss, which also proves the effectiveness of the method. The code for the paper can be found at https://github.com/lovelyemperor/MFD. [ABSTRACT FROM AUTHOR]

Single Shot Multibox Detector (SSD) uses multi-scale feature maps to detect and recognize objects, which considers the advantages of both accuracy and speed, but it is still limited to detecting small-sized objects. Many researchers design new detectors to improve the accuracy by changing the structure of the multi-scale feature pyramid which has proved very useful. But most of them only simply merge several feature maps without making full use of the close connection between features with different scales. In contrast, a novel feature fusion module and an effective feature enhancement module is proposed, which can significantly improve the performance of the original SSD. In the feature fusion module, the feature pyramid is produced through iteratively fusing three feature maps with different receptive fields to obtain contextual information. In the feature enhancement module, the features are enhanced along the channel and spatial dimensions at the same time to improve their expression ability. Our network can achieve 82.5% mean Average Precision (mAP) on the VOC 2007 t e s t , 81.4% mAP on the VOC 2012 t e s t and 34.8% mAP on COCO t e s t - d e v 2017, respectively, with the input size 5 1 2 × 5 1 2. Comparative experiments prove that our method outperforms many state-of-the-art detectors in both aspects of accuracy and speed. [ABSTRACT FROM AUTHOR]

When the network is subject to intrusion and attack, the node output channel equalization will be affected, resulting in bit error and distortion in the output of network transmission symbols. In order to improve the anti-attack ability and equalization of network node, a network intrusion feature map node equalization algorithm based on modified variable step-size constant modulus blind equalization algorithm (MISO-VSS-MCMA) is proposed. In this algorithm, the node transmission channel model after network intrusion is constructed, and sequential processing is performed to intruded nodes with the variable structure feedback link control method. With diversity spread spectrum technology, the channel loss after network intrusion is compensated and the network intrusion map feature is extracted. According to the extracted feature amount, channel equalization processing is performed for the cost function with the MISO-VSS-MCMA method to reduce the damage of network intrusion to the channel. Simulation results show that in node transmission channel equalization after network intrusion, this algorithm can reduce the error bit rate of signal transmission in network, and provide a good ability of correcting phase deflection in the output constellation, thus avoiding the error bit distortion and channel damage caused by network intrusion to the signal with a good equalization effect. This algorithm provides stronger convergence and map concentration, which demonstrates that its anti-interference and signal recovery capabilities are better, so it improves the anti-attack ability of the network. [ABSTRACT FROM AUTHOR]

This paper proposes a unified framework for the investigation of constrained learning theory in reflexive Banach spaces of features via regularized empirical risk minimization. The focus is placed on Tikhonov-like regularization with totally convex functions. This broad class of regularizers provides a flexible model for various priors on the features, including, in particular, hard constraints and powers of Banach norms. In such context, the main results establish a new general form of the representer theorem and the consistency of the corresponding learning schemes under general conditions on the loss function, the geometry of the feature space, and the modulus of total convexity of the regularizer. In addition, the proposed analysis gives new insight into basic tools such as reproducing Banach spaces, feature maps, and universality. Even when specialized to Hilbert spaces, this framework yields new results that extend the state of the art. [ABSTRACT FROM AUTHOR]