检索结果-内蒙古大学图书馆

Texture classification using Block Intensity and Gradient Difference (BIGD) descriptor

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hu, Yuting Wang, Zhen AlRegib, Ghassan Center for Signal and Information Processing School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States

In this paper, we present an efficient and distinctive local descriptor, namely block intensity and gradient difference (BIGD). In an image patch, we randomly sample multi-scale block pairs and utilize the intensity and gradient differences of pairwise blocks to construct the local BIGD descriptor. The random sampling strategy and the multi-scale framework help BIGD descriptors capture the distinctive patterns of patches at different orientations and spatial granularity levels. We use vectors of locally aggregated descriptors (VLAD) or improved Fisher vector (IFV) to encode local BIGD descriptors into a full image descriptor, which is then fed into a linear support vector machine (SVM) classifier for texture classification. We compare the proposed descriptor with typical and state-of-the-art ones by evaluating their classification performance on five public texture data sets including Brodatz, CUReT, KTH-TIPS, and KTH-TIPS-2a and -2b. Experimental results show that the proposed BIGD descriptor with stronger discriminative power yields 0:12% ∼ 6:43% higher classification accuracy than the state-of-the-art texture descriptor, dense microblock difference (DMD). Copyright © 2020, The Authors. All rights reserved.

关键词： Textures

Locally Decodable Index Codes

学校读者我要写书评

暂无评论

Locally Decodable Index Codes

作者： Natarajan, Lakshmi Prasad Krishnan, Prasad Lalitha, V. Dau, Hoang Department of Electrical Engineering Iit Hyderabad Kandi502285 India Signal Processing and Communications Research Center International Institute of Information Technology Hyderabad Hyderabad500032 India Discipline of Computer Science and Information Technology School of Science Rmit University MelbourneVIC3000 Australia

An index code for broadcast channel with receiver side information is locally decodable if each receiver can decode its demand by observing only a subset of the transmitted codeword symbols instead of the entire codeword. Local decodability in index coding is known to reduce receiver complexity, improve user privacy and decrease decoding error probability in wireless fading channels. Conventional index coding solutions assume that the receivers observe the entire codeword, and as a result, for these codes the number of codeword symbols queried by a user per decoded message symbol, which we refer to as locality, could be large. In this paper, we pose the index coding problem as that of minimizing the broadcast rate for a given value of locality (or vice versa) and designing codes that achieve the optimal trade-off between locality and rate. We identify the optimal broadcast rate corresponding to the minimum possible value of locality for all single unicast problems. We present new structural properties of index codes which allow us to characterize the optimal trade-off achieved by: vector linear codes when the side information graph is a directed cycle;and scalar linear codes when the minrank of the side information graph is one less than the order of the problem. We also identify the optimal trade-off among all codes, including non-linear codes, when the side information graph is a directed 3-cycle. Finally, we present techniques to design locally decodable index codes for arbitrary single unicast problems and arbitrary values of locality. © 1963-2012 IEEE.

关键词： Economic and social effects

Unpaired Overwater image Defogging Using Prior Map Guided CycleGAN

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mo, Yaozong Li, Chaofeng Ren, Wenqi Shang, Shaopeng Wang, Wenwu Wu, Xiao-Jun The Institute of Logistics Science and Engineering Shanghai Maritime University Shanghai201306 China The School of Cyber Science and Technology Sun Yatsen University Shenzhen518000 China The Vocational College Shanghai Jian Qiao University Shanghai201306 China The Center for Vision Speech and Signal Processing Department of Electrical and Electronic Engineering University of Surrey SurreyGU2 7XH United Kingdom The School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China

Deep learning-based methods have achieved significant performance for image defogging. However, existing methods are mainly developed for land scenes and perform poorly when dealing with overwater foggy images, since overwater scenes typically contain large expanses of sky and water. In this work, we propose a Prior map Guided CycleGAN (PG-CycleGAN) for defogging of images with overwater scenes. To promote the recovery of the objects on water in the image, two loss functions are exploited for the network where a prior map is designed to invert the dark channel and the min-max normalization is used to suppress the sky and emphasize objects. However, due to the unpaired training set, the network may learn an under-constrained domain mapping from foggy to fog-free image, leading to artifacts and loss of details. Thus, we propose an intuitive Upscaling Inception Module (UIM) and a Long-range Residual Coarse-to-fine framework (LRC) to mitigate this issue. Extensive experiments on qualitative and quantitative comparisons demonstrate that the proposed method outperforms the state-of-the-art supervised, semi-supervised, and unsupervised defogging approaches. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

On the structures of representation for the robustness of Semantic segmentation to input corruption

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lehman, Charles Temel, Dogancan AlRegib, Ghassan OLIVES at the Center for Signal and Information Processing School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332-0250 United States

Semantic segmentation is a scene understanding task at the heart of safety-critical applications where robustness to corrupted inputs is essential. Implicit Background Estimation (IBE) has demonstrated to be a promising technique to improve the robustness to out-of-distribution inputs for semantic segmentation models for little to no cost. In this paper, we provide analysis comparing the structures learned as a result of optimization objectives that use Softmax, IBE, and Sigmoid in order to improve understanding their relationship to robustness. As a result of this analysis, we propose combining Sigmoid with IBE (SCrIBE) to improve robustness. Finally, we demonstrate that SCrIBE exhibits superior segmentation performance aggregated across all corruptions and severity levels with a mIOU of 42.1 compared to both IBE 40.3 and the Softmax Baseline 37.5. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

Enhanced Machine Learning Approaches for Diagnosing Building Systems

学校读者我要写书评

暂无评论

Enhanced Machine Learning Approaches for Diagnosing Building...

2019 International Conference on Internet of Things, Embedded Systems and Communications, IINTEC 2019

作者： Gharsellaoui, Sondes Mansouri, Majdi Refaat, Shady S. Abu-Rub, Haitham Messaoud, Hassani National Higher Engineering School of Tunis Electrical Engineering Department Monfleury Tunisia Electrical and Computer Engineering Program Texas AM University at Qatar Doha Qatar National Engineering School of Monastir Laboratory of Automatic Signal and Image Processing Monastir Tunisia

ISBN: (纸本)9781728151847

Fault Detection and Classification (FDC) in Heating, Ventilation, and Air Conditioning (HVAC) systems is an important approach to guarantee the human safety of these systems. Therefore, the implementation of a FDC framework is the focus in this paper. The developed approach aims at reducing the energy needs for buildings and improving indoor environment quality. It merges the benefits of multiscale representation, Principal Component Analysis (PCA), and Machine Learning (ML) classifiers in order to improve the efficiency of FDC in heating systems. Firstly, a multiscale decomposition is used to extract the dynamics of the systems at different scales. The multiscale representation gives several advantages for monitoring heating systems generally driven by events in different time and frequency responses. Secondly, the multiscaled data-sets are then introduced into the PCA model to extract more efficient characteristics. Thirdly, the ML algorithms are applied to the extracted and selected characteristics to deal with the problem of fault diagnosis. The FDC efficiency of the developed technique is evaluated using a simulated data extracted from heating systems. © 2019 IEEE.

关键词： Fault detection

Contrastive explanations in neural networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Prabhushankar, Mohit Kwon, Gukyeong Temel, Dogancan AlRegib, Ghassan OLIVES at the Center for Signal and Information Processing School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332-0250 United States

Visual explanations are logical arguments based on visual features that justify the predictions made by neural networks. Current modes of visual explanations answer questions of the form ‘Why P?’. These Why questions operate under broad contexts thereby providing answers that are irrelevant in some cases. We propose to constrain these Why questions based on some context Q so that our explanations answer contrastive questions of the form ‘Why P, rather than Q?’. In this paper, we formalize the structure of contrastive visual explanations for neural networks. We define contrast based on neural networks and propose a methodology to extract defined contrasts. We then use the extracted contrasts as a plug-in on top of existing ‘Why P?’ techniques, specifically Grad-CAM. We demonstrate their value in analyzing both networks and data in applications of large-scale recognition, fine-grained recognition, subsurface seismic analysis, and image quality assessment. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

IMPLICIT SALIENCY in DEEP NEURAL NETWORKS

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Sun, Yutong Prabhushankar, Mohit AlRegib, Ghassan OLIVES Center for Signal and Information Processing School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332-0250 United States

In this paper, we show that existing recognition and localization deep architectures, that have not been exposed to eye tracking data or any saliency datasets, are capable of predicting the human visual saliency. We term this as implicit saliency in deep neural networks. We calculate this implicit saliency using expectancy-mismatch hypothesis in an unsupervised fashion. Our experiments show that extracting saliency in this fashion provides comparable performance when measured against the state-of-art supervised algorithms. Additionally, the robustness outperforms those algorithms when we add large noise to the input images. Also, we show that semantic features contribute more than low-level features for human visual saliency detection. Based on these properties and performances, our proposed method greatly lowers the threshold for saliency detection in terms of required data and bridges the gap between human visual saliency and model saliency. Copyright © 2020, The Authors. All rights reserved.

关键词： Visualization

Machine Learning based Multiscale Reduced Kernel PCA for Nonlinear Process Monitoring

学校读者我要写书评

暂无评论

Machine Learning based Multiscale Reduced Kernel PCA for Non...

IEEE SSD International Multi-Conference on Systems, signals and Devices

作者： Khaled Dhibi Radhia Fezai Kais Bouzrara Majdi Mansouri Abdelmalek Kouadri Mohamed-Faouzi Harkat Laboratory of Automatic Signal and Image Processing School of Engineers of Monastir University of Monastir Tunisia Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar

ISBN: (数字)9781728110806

ISBN: (纸本)9781728110813

Fault detection (FD) is fundamental for monitoring several chemical processes. Thus, this paper introduces a novel structure multiscale reduced kernel principal component analysis (MS-RKPCA). The proposed FD method aims to address the problem of great computation time and significant storage memory space by using a data reduction structure based on the Euclidean distance metric. Additionally, to further enhance the RKPCA method, a multiscale representation of data will be used. The enhanced MS-RKPCA method uses the wavelet coefficients of the reduced data at each scale to enhance the fault detection results. The detection performance of the proposed MS-RKPCA method is evaluated using the Tennessee Eastman Process (TEP). The effectiveness of the enhanced method is evaluated in terms of the missed detection rates (MDR), false alarms rates (FAR) and computation time (CT). The results demonstrate that the developed technique is more effective for fault detection mostly in terms of computation time and memory storage space.

关键词： Fault detection Computational modeling Euclidean distance Wavelet analysis Kernel Principal component analysis Wavelet coefficients

Novelty detection through model-based characterization of neural networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kwon, Gukyeong Prabhushankar, Mohit Temel, Dogancan AlRegib, Ghassan OLIVES at the Center for Signal and Information Processing School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332-0250 United States

In this paper, we propose a model-based characterization of neural networks to detect novel input types and conditions. Novelty detection is crucial to identify abnormal inputs that can significantly degrade the performance of machine learning algorithms. Majority of existing studies have focused on activation-based representations to detect abnormal inputs, which limits the characterization of abnormality from a data perspective. However, a model perspective can also be informative in terms of the novelties and abnormalities. To articulate the significance of the model perspective in novelty detection, we utilize backpropagated gradients. We conduct a comprehensive analysis to compare the representation capability of gradients with that of activation and show that the gradients outperform the activation in novel class and condition detection. We validate our approach using four image recognition datasets including MNIST, Fashion-MNIST, CIFAR-10, and CURE-TSR. We achieve a significant improvement on all four datasets with an average AUROC of 0.953, 0.918, 0.582, and 0.746, respectively. Copyright © 2020, The Authors. All rights reserved.

关键词： Chemical activation