Biblio
In this paper, inspired by Gatys's recent work, we propose a novel approach that transforms photos to comics using deep convolutional neural networks (CNNs). While Gatys's method that uses a pre-trained VGG network generally works well for transferring artistic styles such as painting from a style image to a content image, for more minimalist styles such as comics, the method often fails to produce satisfactory results. To address this, we further introduce a dedicated comic style CNN, which is trained for classifying comic images and photos. This new network is effective in capturing various comic styles and thus helps to produce better comic stylization results. Even with a grayscale style image, Gatys's method can still produce colored output, which is not desirable for comics. We develop a modified optimization framework such that a grayscale image is guaranteed to be synthesized. To avoid converging to poor local minima, we further initialize the output image using grayscale version of the content image. Various examples show that our method synthesizes better comic images than the state-of-the-art method.
In this paper, we propose to impose a multiscale contextual loss for image style transfer based on Convolutional Neural Networks (CNN). In the traditional optimization framework, a new stylized image is synthesized by constraining the high-level CNN features similar to a content image and the lower-level CNN features similar to a style image, which, however, appears to lost many details of the content image, presenting unpleasing and inconsistent distortions or artifacts. The proposed multiscale contextual loss, named Haar loss, is responsible for preserving the lost details by dint of matching the features derived from the content image and the synthesized image via wavelet transform. It endows the synthesized image with the characteristic to better retain the semantic information of the content image. More specifically, the unpleasant distortions can be effectively alleviated while the style can be well preserved. In the experiments, we show the visually more consistent and simultaneously well-stylized images generated by incorporating the multiscale contextual loss.
The growing volume of data and its increasing complexity require even more efficient and faster information retrieval techniques. Approximate nearest neighbor search algorithms based on hashing were proposed to query high-dimensional datasets due to its high retrieval speed and low storage cost. Recent studies promote the use of Convolutional Neural Network (CNN) with hashing techniques to improve the search accuracy. However, there are challenges to solve in order to find a practical and efficient solution to index CNN features, such as the need for a heavy training process to achieve accurate query results and the critical dependency on data-parameters. In this work we execute exhaustive experiments in order to compare recent methods that are able to produces a better representation of the data space with a less computational cost for a better accuracy by computing the best data-parameter values for optimal sub-space projection exploring the correlations among CNN feature attributes using fractal theory. We give an overview of these different techniques and present our comparative experiments for data representation and retrieval performance.
Stochastic Computing (SC) is an alternative design paradigm particularly useful for applications where cost is critical. SC has been applied to neural networks, as neural networks are known for their high computational complexity. However previous work in this area has critical limitations such as the fully-parallel architecture assumption, which prevent them from being applicable to recent ones such as convolutional neural networks, or ConvNets. This paper presents the first SC architecture for ConvNets, shows its feasibility, with detailed analyses of implementation overheads. Our SC-ConvNet is a hybrid between SC and conventional binary design, which is a marked difference from earlier SC-based neural networks. Though this might seem like a compromise, it is a novel feature driven by the need to support modern ConvNets at scale, which commonly have many, large layers. Our proposed architecture also features hybrid layer composition, which helps achieve very high recognition accuracy. Our detailed evaluation results involving functional simulation and RTL synthesis suggest that SC-ConvNets are indeed competitive with conventional binary designs, even without considering inherent error resilience of SC.
Here we explore the applicability of traditional sliding window based convolutional neural network (CNN) detection pipeline and region based object detection techniques such as Faster Region-based CNN (R-CNN) and Region-based Fully Convolutional Networks (R-FCN) on the problem of object detection in X-ray security imagery. Within this context, with limited dataset availability, we employ a transfer learning paradigm for network training tackling both single and multiple object detection problems over a number of R-CNN/R-FCN variants. The use of first-stage region proposal within the Faster RCNN and R-FCN provide superior results than traditional sliding window driven CNN (SWCNN) approach. With the use of Faster RCNN with VGG16, pretrained on the ImageNet dataset, we achieve 88.3 mAP for a six object class X-ray detection problem. The use of R-FCN with ResNet-101, yields 96.3 mAP for the two class firearm detection problem requiring 0.1 second computation per image. Overall we illustrate the comparative performance of these techniques as object localization strategies within cluttered X-ray security imagery.
In video surveillance, face recognition (FR) systems seek to detect individuals of interest appearing over a distributed network of cameras. Still-to-video FR systems match faces captured in videos under challenging conditions against facial models, often designed using one reference still per individual. Although CNNs can achieve among the highest levels of accuracy in many real-world FR applications, state-of-the-art CNNs that are suitable for still-to-video FR, like trunk-branch ensemble (TBE) CNNs, represent complex solutions for real-time applications. In this paper, an efficient CNN architecture is proposed for accurate still-to-video FR from a single reference still. The CCM-CNN is based on new cross-correlation matching (CCM) and triplet-loss optimization methods that provide discriminant face representations. The matching pipeline exploits a matrix Hadamard product followed by a fully connected layer inspired by adaptive weighted cross-correlation. A triplet-based training approach is proposed to optimize the CCM-CNN parameters such that the inter-class variations are increased, while enhancing robustness to intra-class variations. To further improve robustness, the network is fine-tuned using synthetically-generated faces based on still and videos of non-target individuals. Experiments on videos from the COX Face and Chokepoint datasets indicate that the CCM-CNN can achieve a high level of accuracy that is comparable to TBE-CNN and HaarNet, but with a significantly lower time and memory complexity. It may therefore represent the better trade-off between accuracy and complexity for real-time video surveillance applications.
Hierarchical approaches for representation learning have the ability to encode relevant features at multiple scales or levels of abstraction. However, most hierarchical approaches exploit only the last level in the hierarchy, or provide a multiscale representation that holds a significant amount of redundancy. We argue that removing redundancy across the multiple levels of abstraction is important for an efficient representation of compositionality in object-based representations. With the perspective of feature learning as a data compression operation, we propose a new greedy inference algorithm for hierarchical sparse coding. Convolutional matching pursuit with a L0-norm constraint was used to encode the input signal into compact and non-redundant codes distributed across levels of the hierarchy. Simple and complex synthetic datasets of temporal signals were created to evaluate the encoding efficiency and compare with the theoretical lower bounds on the information rate for those signals. Empirical evidence have shown that the algorithm is able to infer near-optimal codes for simple signals. However, it failed for complex signals with strong overlapping between objects. We explain the inefficiency of convolutional matching pursuit that occurred in such case. This brings new insights about the NP-hard optimization problem related to using L0-norm constraint in inferring optimally compact and distributed object-based representations.
Biometrics has become ubiquitous and spurred common use in many authentication mechanisms. Keystroke dynamics is a form of behavioral biometrics that can be used for user authentication while actively working at a terminal. The proposed mechanisms involve digraph, trigraph and n-graph analysis as separate solutions or suggest a fusion mechanism with certain limitations. However, deep learning can be used as a unifying machine learning technique that consolidates the power of all different features since it has shown tremendous results in image recognition and natural language processing. In this paper, we investigate the applicability of deep learning on three different datasets by using convolutional neural networks and Gaussian data augmentation technique. We achieve 10% higher accuracy and 7.3% lower equal error rate (EER) than existing methods. Also, our sensitivity analysis indicates that the convolution operation and the fully-connected layer are the most prominent factors that affect the accuracy and the convergence rate of a network trained with keystroke data.
With the popularization and development of network knowledge, network intruders are increasing, and the attack mode has been updated. Intrusion detection technology is a kind of active defense technology, which can extract the key information from the network system, and quickly judge and protect the internal or external network intrusion. Intrusion detection is a kind of active security technology, which provides real-time protection for internal attacks, external attacks and misuse, and it plays an important role in ensuring network security. However, with the diversification of intrusion technology, the traditional intrusion detection system cannot meet the requirements of the current network security. Therefore, the implementation of intrusion detection needs diversifying. In this context, we apply neural network technology to the network intrusion detection system to solve the problem. In this paper, on the basis of intrusion detection method, we analyze the development history and the present situation of intrusion detection technology, and summarize the intrusion detection system overview and architecture. The neural network intrusion detection is divided into data acquisition, data analysis, pretreatment, intrusion behavior detection and testing.
Convolution serves as the basic computational primitive for various associative computing tasks ranging from edge detection to image matching. CMOS implementation of such computations entails significant bottlenecks in area and energy consumption due to the large number of multiplication and addition operations involved. In this paper, we propose an ultra-low power and compact hybrid spintronic-CMOS design for the convolution computing unit. Low-voltage operation of domain-wall motion based magneto-metallic "Spin-Memristor"s interfaced with CMOS circuits is able to perform the convolution operation with reasonable accuracy. Simulation results of Gabor filtering for edge detection reveal \textasciitilde 2.5× lower energy consumption compared to a baseline 45nm-CMOS implementation.
A novel short-time Fourier transform (STFT) domain adaptive filtering scheme is proposed that can be easily combined with nonlinear post filters such as residual echo or noise reduction in acoustic echo cancellation. Unlike normal STFT subband adaptive filters, which suffers from aliasing artifacts due to its poor prototype filter, our scheme achieves good accuracy by exploiting the relationship between the linear convolution and the poor prototype filter, i.e., the STFT window function. The effectiveness of our scheme was confirmed through the results of simulations conducted to compare it with conventional methods.
- « first
- ‹ previous
- 1
- 2
- 3
- 4