PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2208.04284

On Rademacher Complexity-based Generalization Bounds for Deep Learning

We show that the Rademacher complexity-based approach can generate non-vacuous generalisation bounds on Convolutional Neural Networks (CNNs) for classifying a small number of classes of images. The development of new Talagrand's contraction lemmas for high-dimensional mappings between function spaces and CNNs for general Lipschitz activation functions is a key technical contribution. Our results show that the Rademacher complexity does not depend on the network length for CNNs with some special types of activation functions such as ReLU, Leaky ReLU, Parametric Rectifier Linear Unit, Sigmoid, and Tanh.

arXiv:2208.04033

Channel Estimation under Hardware Impairments: Bayesian Methods versus Deep Learning

This paper considers the impact of general hardware impairments in a multiple-antenna base station and user equipments on the uplink performance. First, the effective channels are analytically derived for distortion-aware receivers when using finite-sized signal constellations. Next, a deep feedforward neural network is designed and trained to estimate the effective channels. Its performance is compared with state-of-the-art distortion-aware and unaware Bayesian linear minimum mean-squared error (LMMSE) estimators. The proposed deep learning approach improves the estimation quality by exploiting impairment characteristics, while LMMSE methods treat distortion as noise.

arXiv:2208.03566공식 코드 · Papers with Code

Towards Robust Deep Learning using Entropic Losses

Current deep learning solutions are well known for not informing whether they can reliably classify an example during inference. One of the most effective ways to build more reliable deep learning solutions is to improve their performance in the so-called out-of-distribution detection task, which essentially consists of "know that you do not know" or "know the unknown". In other words, out-of-distribution detection capable systems may reject performing a nonsense classification when submitted to instances of classes on which the neural network was not trained. This thesis tackles the defiant out-of-distribution detection task by proposing novel loss functions and detection scores. Uncertainty estimation is also a crucial auxiliary task in building more robust deep learning systems. Therefore, we also deal with this robustness-related task, which evaluates how realistic the probabilities presented by the deep neural network are. To demonstrate the effectiveness of our approach, in addition to a substantial set of experiments, which includes state-of-the-art results, we use arguments based on the principle of maximum entropy to establish the theoretical foundation of the proposed approaches. Unlike most current methods, our losses and scores are seamless and principled solutions that produce accurate predictions in addition to fast and efficient inference. Moreover, our approaches can be incorporated into current and future projects simply by replacing the loss used to train the deep neural network and computing a rapid score for detection.

arXiv:2208.03524공식 코드 · Papers with Code

Deep Learning-enabled Spatial Phase Unwrapping for 3D Measurement

In terms of 3D imaging speed and system cost, the single-camera system projecting single-frequency patterns is the ideal option among all proposed Fringe Projection Profilometry (FPP) systems. This system necessitates a robust spatial phase unwrapping (SPU) algorithm. However, robust SPU remains a challenge in complex scenes. Quality-guided SPU algorithms need more efficient ways to identify the unreliable points in phase maps before unwrapping. End-to-end deep learning SPU methods face generality and interpretability problems. This paper proposes a hybrid method combining deep learning and traditional path-following for robust SPU in FPP. This hybrid SPU scheme demonstrates better robustness than traditional quality-guided SPU methods, better interpretability than end-to-end deep learning scheme, and generality on unseen data. Experiments on the real dataset of multiple illumination conditions and multiple FPP systems differing in image resolution, the number of fringes, fringe direction, and optics wavelength verify the effectiveness of the proposed method.

arXiv:2208.03514공식 코드 · Papers with Code

Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning

With the rapid development of artificial intelligence and autonomous driving technology, the demand for semiconductors is projected to rise substantially. However, the massive expansion of semiconductor manufacturing and the development of new technology will bring many defect wafers. If these defect wafers have not been correctly inspected, the ineffective semiconductor processing on these defect wafers will cause additional impact to our environment, such as excessive carbon dioxide emission and energy consumption. In this paper, we utilize the information processing advantages of quantum computing to promote the defect learning defect review (DLDR). We propose a classical-quantum hybrid algorithm for deep learning on near-term quantum processors. By tuning parameters implemented on it, quantum circuit driven by our framework learns a given DLDR task, include of wafer defect map classification, defect pattern classification, and hotspot detection. In addition, we explore parametrized quantum circuits with different expressibility and entangling capacities. These results can be used to build a future roadmap to develop circuit-based quantum deep learning for semiconductor defect detection.

arXiv:2208.03958

Abutting Grating Illusion: Cognitive Challenge to Neural Network Models

Even the state-of-the-art deep learning models lack fundamental abilities compared to humans. Multiple comparison paradigms have been proposed to explore the distinctions between humans and deep learning. While most comparisons rely on corruptions inspired by mathematical transformations, very few have bases on human cognitive phenomena. In this study, we propose a novel corruption method based on the abutting grating illusion, which is a visual phenomenon widely discovered in both human and a wide range of animal species. The corruption method destroys the gradient-defined boundaries and generates the perception of illusory contours using line gratings abutting each other. We applied the method on MNIST, high resolution MNIST, and silhouette object images. Various deep learning models are tested on the corruption, including models trained from scratch and 109 models pretrained with ImageNet or various data augmentation techniques. Our results show that abutting grating corruption is challenging even for state-of-the-art deep learning models because most models are randomly guessing. We also discovered that the DeepAugment technique can greatly improve robustness against abutting grating illusion. Visualisation of early layers indicates that better performing models exhibit stronger end-stopping property, which is consistent with neuroscience discoveries. To validate the corruption method, 24 human subjects are involved to classify samples of corrupted datasets.

arXiv:2208.03775

Video-based Human Action Recognition using Deep Learning: A Review

Human action recognition is an important application domain in computer vision. Its primary aim is to accurately describe human actions and their interactions from a previously unseen data sequence acquired by sensors. The ability to recognize, understand, and predict complex human actions enables the construction of many important applications such as intelligent surveillance systems, human-computer interfaces, health care, security, and military applications. In recent years, deep learning has been given particular attention by the computer vision community. This paper presents an overview of the current state-of-the-art in action recognition using video analysis with deep learning techniques. We present the most important deep learning models for recognizing human actions, and analyze them to provide the current progress of deep learning algorithms applied to solve human action recognition problems in realistic videos highlighting their advantages and disadvantages. Based on the quantitative analysis using recognition accuracies reported in the literature, our study identifies state-of-the-art deep architectures in action recognition and then provides current trends and open problems for future works in this field.

arXiv:2208.03419

Multi-view deep learning for reliable post-disaster damage classification

This study aims to enable more reliable automated post-disaster building damage classification using artificial intelligence (AI) and multi-view imagery. The current practices and research efforts in adopting AI for post-disaster damage assessment are generally (a) qualitative, lacking refined classification of building damage levels based on standard damage scales, and (b) trained based on aerial or satellite imagery with limited views, which, although indicative, are not completely descriptive of the damage scale. To enable more accurate and reliable automated quantification of damage levels, the present study proposes the use of more comprehensive visual data in the form of multiple ground and aerial views of the buildings. To have such a spatially-aware damage prediction model, a Multi-view Convolution Neural Network (MV-CNN) architecture is used that combines the information from different views of a damaged building. This spatial 3D context damage information will result in more accurate identification of damages and reliable quantification of damage levels. The proposed model is trained and validated on reconnaissance visual dataset containing expert-labeled, geotagged images of the inspected buildings following hurricane Harvey. The developed model demonstrates reasonably good accuracy in predicting the damage levels and can be used to support more informed and reliable AI-assisted disaster management practices.

arXiv:2208.04094

Towards Semantic Communications: Deep Learning-Based Image Semantic Coding

Semantic communications has received growing interest since it can remarkably reduce the amount of data to be transmitted without missing critical information. Most existing works explore the semantic encoding and transmission for text and apply techniques in Natural Language Processing (NLP) to interpret the meaning of the text. In this paper, we conceive the semantic communications for image data that is much more richer in semantics and bandwidth sensitive. We propose an reinforcement learning based adaptive semantic coding (RL-ASC) approach that encodes images beyond pixel level. Firstly, we define the semantic concept of image data that includes the category, spatial arrangement, and visual feature as the representation unit, and propose a convolutional semantic encoder to extract semantic concepts. Secondly, we propose the image reconstruction criterion that evolves from the traditional pixel similarity to semantic similarity and perceptual performance. Thirdly, we design a novel RL-based semantic bit allocation model, whose reward is the increase in rate-semantic-perceptual performance after encoding a certain semantic concept with adaptive quantization level. Thus, the task-related information is preserved and reconstructed properly while less important data is discarded. Finally, we propose the Generative Adversarial Nets (GANs) based semantic decoder that fuses both locally and globally features via an attention module. Experimental results demonstrate that the proposed RL-ASC is noise robust and could reconstruct visually pleasant and semantic consistent image, and saves times of bit cost compared to standard codecs and other deep learning-based image codecs.

arXiv:2208.03218

RadTex: Learning Efficient Radiograph Representations from Text Reports

Automated analysis of chest radiography using deep learning has tremendous potential to enhance the clinical diagnosis of diseases in patients. However, deep learning models typically require large amounts of annotated data to achieve high performance -- often an obstacle to medical domain adaptation. In this paper, we build a data-efficient learning framework that utilizes radiology reports to improve medical image classification performance with limited labeled data (fewer than 1000 examples). Specifically, we examine image-captioning pretraining to learn high-quality medical image representations that train on fewer examples. Following joint pretraining of a convolutional encoder and transformer decoder, we transfer the learned encoder to various classification tasks. Averaged over 9 pathologies, we find that our model achieves higher classification performance than ImageNet-supervised and in-domain supervised pretraining when labeled training data is limited.

arXiv:2208.03143

Deep Learning and Health Informatics for Smart Monitoring and Diagnosis

The connection between the design and delivery of health care services using information technology is known as health informatics. It involves data usage, validation, and transfer of an integrated medical analysis using neural networks of multi-layer deep learning techniques to analyze complex data. For instance, Google incorporated ''DeepMind'' health mobile tool that integrates \& leverage medical data needed to enhance professional healthcare delivery to patients. Moorfield Eye Hospital London introduced DeepMind Research Algorithms with dozens of retinal scans attributes while DeepMind UCL handled the identification of cancerous tissues using CT \& MRI Scan tools. Atomise analyzed drugs and chemicals with Deep Learning Neural Networks to identify accurate pre-clinical prescriptions. Health informatics makes medical care intelligent, interactive, cost-effective, and accessible; especially with DL application tools for detecting the actual cause of diseases. The extensive use of neural network tools leads to the expansion of different medical disciplines which mitigates data complexity and enhances 3-4D overlap images using target point label data detectors that support data augmentation, un-semi-supervised learning, multi-modality and transfer learning architecture. Health science over the years focused on artificial intelligence tools for care delivery, chronic care management, prevention/wellness, clinical supports, and diagnosis. The outcome of their research leads to cardiac arrest diagnosis through Heart Signal Computer-Aided Diagnostic tool (CADX) and other multifunctional deep learning techniques that offer care, diagnosis \& treatment. Health informatics provides monitored outcomes of human body organs through medical images that classify interstitial lung disease, detects image nodules for reconstruction \& tumor segmentation. The emergent medical research applications gave rise to clinical-pathological human-level performing tools for handling Radiological, Ophthalmological, and Dental diagnosis. This research will evaluate methodologies, Deep learning architectures, approaches, bio-informatics, specified function requirements, monitoring tools, ANN (artificial neural network), data labeling \& annotation algorithms that control data validation, modeling, and diagnosis of different diseases using smart monitoring health informatics applications.

arXiv:2208.02813공식 코드 · Papers with Code

Towards Understanding Mixture of Experts in Deep Learning

The Mixture-of-Experts (MoE) layer, a sparsely-activated model controlled by a router, has achieved great success in deep learning. However, the understanding of such architecture remains elusive. In this paper, we formally study how the MoE layer improves the performance of neural network learning and why the mixture model will not collapse into a single model. Our empirical results suggest that the cluster structure of the underlying problem and the non-linearity of the expert are pivotal to the success of MoE. To further understand this, we consider a challenging classification problem with intrinsic cluster structures, which is hard to learn using a single expert. Yet with the MoE layer, by choosing the experts as two-layer nonlinear convolutional neural networks (CNNs), we show that the problem can be learned successfully. Furthermore, our theory shows that the router can learn the cluster-center features, which helps divide the input complex problem into simpler linear classification sub-problems that individual experts can conquer. To our knowledge, this is the first result towards formally understanding the mechanism of the MoE layer for deep learning.

arXiv:2208.02716

IT/IST/IPLeiria Response to the Call for Proposals on JPEG Pleno Point Cloud Coding

This document describes a deep learning-based point cloud geometry codec and a deep learning-based point cloud joint geometry and colour codec, submitted to the Call for Proposals on JPEG Pleno Point Cloud Coding issued in January 2022. The proposed codecs are based on recent developments in deep learning-based PC geometry coding and offer some of the key functionalities targeted by the Call for Proposals. The proposed geometry codec offers a compression efficiency that outperforms the MPEG G-PCC standard and outperforms or is competitive with the V-PCC Intra standard for the JPEG Call for Proposals test set; however, the same does not happen for the joint geometry and colour codec due to a quality saturation effect that needs to be overcome.

arXiv:2208.02587

Privacy-Preserving Chaotic Extreme Learning Machine with Fully Homomorphic Encryption

The Machine Learning and Deep Learning Models require a lot of data for the training process, and in some scenarios, there might be some sensitive data, such as customer information involved, which the organizations might be hesitant to outsource for model building. Some of the privacy-preserving techniques such as Differential Privacy, Homomorphic Encryption, and Secure Multi-Party Computation can be integrated with different Machine Learning and Deep Learning algorithms to provide security to the data as well as the model. In this paper, we propose a Chaotic Extreme Learning Machine and its encrypted form using Fully Homomorphic Encryption where the weights and biases are generated using a logistic map instead of uniform distribution. Our proposed method has performed either better or similar to the Traditional Extreme Learning Machine on most of the datasets.

arXiv:2208.02707

Standardizing and Centralizing Datasets to Enable Efficient Training of Agricultural Deep Learning Models

In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural datasets. This lack of agriculture-specific fine-tuning potentially increases training time and resource use, and decreases model performance, leading an overall decrease in data efficiency. To overcome this limitation, we collect a wide range of existing public datasets for three distinct tasks, standardize them, and construct standard training and evaluation pipelines, providing us with a set of benchmarks and pretrained models. We then conduct a number of experiments using methods which are commonly used in deep learning tasks, but unexplored in their domain-specific applications for agriculture. Our experiments guide us in developing a number of approaches to improve data efficiency when training agricultural deep learning models, without large-scale modifications to existing pipelines. Our results demonstrate that even slight training modifications, such as using agricultural pretrained model weights, or adopting specific spatial augmentations into data processing pipelines, can significantly boost model performance and result in shorter convergence time, saving training resources. Furthermore, we find that even models trained on low-quality annotations can produce comparable levels of performance to their high-quality equivalents, suggesting that datasets with poor annotations can still be used for training, expanding the pool of currently available datasets. Our methods are broadly applicable throughout agricultural deep learning, and present high potential for significant data efficiency improvements.

arXiv:2208.01918

DeepProphet2 -- A Deep Learning Gene Recommendation Engine

New powerful tools for tackling life science problems have been created by recent advances in machine learning. The purpose of the paper is to discuss the potential advantages of gene recommendation performed by artificial intelligence (AI). Indeed, gene recommendation engines try to solve this problem: if the user is interested in a set of genes, which other genes are likely to be related to the starting set and should be investigated? This task was solved with a custom deep learning recommendation engine, DeepProphet2 (DP2), which is freely available to researchers worldwide via https://www.generecommender.com?utm_source=DeepProphet2_paper&utm_medium=pdf. Hereafter, insights behind the algorithm and its practical applications are illustrated. The gene recommendation problem can be addressed by mapping the genes to a metric space where a distance can be defined to represent the real semantic distance between them. To achieve this objective a transformer-based model has been trained on a well-curated freely available paper corpus, PubMed. The paper describes multiple optimization procedures that were employed to obtain the best bias-variance trade-off, focusing on embedding size and network depth. In this context, the model's ability to discover sets of genes implicated in diseases and pathways was assessed through cross-validation. A simple assumption guided the procedure: the network had no direct knowledge of pathways and diseases but learned genes' similarities and the interactions among them. Moreover, to further investigate the space where the neural network represents genes, the dimensionality of the embedding was reduced, and the results were projected onto a human-comprehensible space. In conclusion, a set of use cases illustrates the algorithm's potential applications in a real word setting.

arXiv:2208.01844

Multiclass ASMA vs Targeted PGD Attack in Image Segmentation

Deep learning networks have demonstrated high performance in a large variety of applications, such as image classification, speech recognition, and natural language processing. However, there exists a major vulnerability exploited by the use of adversarial attacks. An adversarial attack imputes images by altering the input image very slightly, making it nearly undetectable to the naked eye, but results in a very different classification by the network. This paper explores the projected gradient descent (PGD) attack and the Adaptive Mask Segmentation Attack (ASMA) on the image segmentation DeepLabV3 model using two types of architectures: MobileNetV3 and ResNet50, It was found that PGD was very consistent in changing the segmentation to be its target while the generalization of ASMA to a multiclass target was not as effective. The existence of such attack however puts all of image classification deep learning networks in danger of exploitation.

arXiv:2208.01705

Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry

For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data. Although existing works show that predictive uncertainty is useful for these tasks, it is not evident from literature which uncertainty-aware models are best suited for a given dataset. Thus, we compare six uncertainty-aware deep learning models on a set of edge-case tasks: robustness to adversarial attacks as well as out-of-distribution and adversarial detection. We find that the geometry of the data sub-manifold is an important factor in determining the success of various models. Our finding suggests an interesting direction in the study of uncertainty-aware deep learning models.

arXiv:2208.02235

Quantum-Inspired Tensor Neural Networks for Partial Differential Equations

Partial Differential Equations (PDEs) are used to model a variety of dynamical systems in science and engineering. Recent advances in deep learning have enabled us to solve them in a higher dimension by addressing the curse of dimensionality in new ways. However, deep learning methods are constrained by training time and memory. To tackle these shortcomings, we implement Tensor Neural Networks (TNN), a quantum-inspired neural network architecture that leverages Tensor Network ideas to improve upon deep learning approaches. We demonstrate that TNN provide significant parameter savings while attaining the same accuracy as compared to the classical Dense Neural Network (DNN). In addition, we also show how TNN can be trained faster than DNN for the same accuracy. We benchmark TNN by applying them to solve parabolic PDEs, specifically the Black-Scholes-Barenblatt equation, widely used in financial pricing theory, empirically showing the advantages of TNN over DNN. Further examples, such as the Hamilton-Jacobi-Bellman equation, are also discussed.

arXiv:2208.02094

A Novel Approach To Network Intrusion Detection System Using Deep Learning For Sdn: Futuristic Approach

Software-Defined Networking (SDN) is the next generation to change the architecture of traditional networks. SDN is one of the promising solutions to change the architecture of internet networks. Attacks become more common due to the centralized nature of SDN architecture. It is vital to provide security for the SDN. In this study, we propose a Network Intrusion Detection System-Deep Learning module (NIDS-DL) approach in the context of SDN. Our suggested method combines Network Intrusion Detection Systems (NIDS) with many types of deep learning algorithms. Our approach employs 12 features extracted from 41 features in the NSL-KDD dataset using a feature selection method. We employed classifiers (CNN, DNN, RNN, LSTM, and GRU). When we compare classifier scores, our technique produced accuracy results of (98.63%, 98.53%, 98.13%, 98.04%, and 97.78%) respectively. The novelty of our new approach (NIDS-DL) uses 5 deep learning classifiers and made pre-processing dataset to harvests the best results. Our proposed approach was successful in binary classification and detecting attacks, implying that our approach (NIDS-DL) might be used with great efficiency in the future.