The traditional manual inspection is gradually replaced by the unmanned aerial vehicles (UAV) automatic inspection. However, due to the limited computational resources carried by the UAV, the existing deep learning-based algorithm needs a large amount of computational resources, which makes it impossible to realize the online detection. Moreover, there is no effective online detection system at present. To realize the high-precision online detection of electrical equipment, this paper proposes an SSD (Single Shot Multibox Detector) detection algorithm based on the improved Dual network for the images of insulators and spacers taken by UAVs. The proposed algorithm uses MnasNet and MobileNetv3 to form the Dual network to extract multi-level features, which overcomes the shortcoming of single convolutional network-based backbone for feature extraction. Then the features extracted from the two networks are fused together to obtain the features with high-level semantic information. Finally, the proposed algorithm is tested on the public dataset of the insulator and spacer. The experimental results show that the proposed algorithm can detect insulators and spacers efficiently. Compared with other methods, the proposed algorithm has the advantages of smaller model size and higher accuracy. The object detection accuracy of the proposed method is up to 95.1%.

We propose a new framework for estimating depth information from a single image. Our framework is relatively small and straightforward by employing a two-stage architecture: a residual network and a simple decoder network. Our residual network in this paper is a remodeled of the original ResNet-50 architecture, which consists of only thirty-eight convolution layers in the residual block following by pair of two up-sampling and layers. While the simple decoder network, stack of five convolution layers, accepts the initial depth to be refined as the final output depth. During training, we monitor the loss behavior and adjust the learning rate hyperparameter in order to improve the performance. Furthermore, instead of using a single common pixel-wise loss, we also compute loss based on gradient-direction, and their structure similarity. This setting in our network can significantly reduce the number of network parameters, and simultaneously get a more accurate image depth map. The performance of our approach has been evaluated by conducting both quantitative and qualitative comparisons with several prior related methods on the publicly NYU and KITTI datasets.

Encrypted traffic identification is to predict traffic types of encrypted traffic. A deep residual convolution network is proposed for this task. The Softmax classifier is fused with its angular variant, which sets an angular margin to achieve better discrimination. The proposed method improves representation learning and reaches excellent results on the public dataset.

Feature learning based on deep network has been verified as beneficial for person re-identification (Re-ID) in recent years. However, most researches use a single network as the baseline, without considering the fusion of different deep features. By analyzing the attention maps of different networks, we find that the information learned by different networks can complement each other. Therefore, a novel Dual Network Fusion (DNF) framework is proposed. DNF is designed with a trunk branch and two auxiliary branches. In the trunk branch, deep features are cascaded directly along the channel direction. One of the auxiliary branch is channel attention branch, which is used to allocate weight for different deep features. Another one is multi-loss training branch. To verify the performance of DNF, we test it on three benchmark datasets, including CUHK03NP, Market-1501 and DukeMTMC-reID. The results show that the effect of using DNF is significantly better than a single network and is comparable to most state-of-the-art methods.

With the continuous refinement of Deep Neural Networks (DNNs), a series of deep and complex networks such as Residual Networks (ResNets) show impressive prediction accuracy in image classification tasks. Unfortunately, the structural complexity and computational cost of residual networks make hardware implementation difficult. In this paper, we present the quantized and reconstructed deep neural network (QR-DNN) technique, which first inserts batch normalization (BN) layers in the network during training, and later removes them to facilitate efficient hardware implementation. Moreover, an accurate and efficient residual network accelerator (RNA) is presented based on QR-DNN with batch-normalization-free structures and weights represented in a logarithmic number system. RNA employs a systolic array architecture to perform shift-and-accumulate operations instead of multiplication operations. QR-DNN is shown to achieve a 1∼2% improvement in accuracy over existing techniques, and RNA over previous best fixed-point accelerators. An FPGA implementation on a Xilinx Zynq XC7Z045 device achieves 804.03 GOPS, 104.15 FPS and 91.41% top-5 accuracy for the ResNet-50 benchmark, and state-of-the-art results are also reported for AlexNet and VGG.

In this letter, we propose a sequential convolutional residual network, where we first analyze a tangled network architecture using simplified equations and determine the critical point to untangle the complex network architecture. Although the residual network shows good performance, the learning efficiency is not better than expected at deeper layers because the network is excessively intertwined. To solve this problem, we propose a network in which the information is transmitted sequentially. In this network architecture, the neighboring layer output adds the input of the current layer and iteratively passes its result to the next sequential layer. Thus, the proposed network can improve the learning efficiency and performance by successfully mitigating the complexity in deep networks. We show that the proposed network performs well on the Cifar-10 and Cifar-100 datasets. In particular, we prove that the proposed method is superior to the baseline method as the depth increases.

How to represent images into highly compact binary codes is a critical issue in many computer vision tasks. Existing deep hashing methods typically focus on designing loss function by using pairwise or triplet labels. However, these methods ignore the attention mechanism in the human visual system. In this letter, we propose a novel Deep Attention Residual Hashing (DARH) method, which directly learns hash codes based on a simple pointwise classification loss function. Compared to previous methods, our method does not need to generate all possible pairwise or triplet labels from the training dataset. Specifically, we develop a new type of attention layer which can learn human eye fixation and significantly improves the representation ability of hash codes. In addition, we embedded the attention layer into the residual network to simultaneously learn discriminative image features and hash codes in an end-to-end manner. Extensive experiments on standard benchmarks demonstrate that our method preserves the instance-level similarity and outperforms state-of-the-art deep hashing methods in the image retrieval application.