PyTorchKR Papers

최신 논문

총 2,063편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2309.08500공식 코드 · Papers with Code

Deep-learning-powered data analysis in plankton ecology

The implementation of deep learning algorithms has brought new perspectives to plankton ecology. Emerging as an alternative approach to established methods, deep learning offers objective schemes to investigate plankton organisms in diverse environments. We provide an overview of deep-learning-based methods including detection and classification of phyto- and zooplankton images, foraging and swimming behaviour analysis, and finally ecological modelling. Deep learning has the potential to speed up the analysis and reduce the human experimental bias, thus enabling data acquisition at relevant temporal and spatial scales with improved reproducibility. We also discuss shortcomings and show how deep learning architectures have evolved to mitigate imprecise readouts. Finally, we suggest opportunities where deep learning is particularly likely to catalyze plankton research. The examples are accompanied by detailed tutorials and code samples that allow readers to apply the methods described in this review to their own data.

arXiv:2309.07159공식 코드 · Papers with Code

A Strong and Simple Deep Learning Baseline for BCI MI Decoding

We propose EEG-SimpleConv, a straightforward 1D convolutional neural network for Motor Imagery decoding in BCI. Our main motivation is to propose a simple and performing baseline to compare to, using only very standard ingredients from the literature. We evaluate its performance on four EEG Motor Imagery datasets, including simulated online setups, and compare it to recent Deep Learning and Machine Learning approaches. EEG-SimpleConv is at least as good or far more efficient than other approaches, showing strong knowledge-transfer capabilities across subjects, at the cost of a low inference time. We advocate that using off-the-shelf ingredients rather than coming with ad-hoc solutions can significantly help the adoption of Deep Learning approaches for BCI. We make the code of the models and the experiments accessible.

arXiv:2309.07175공식 코드 · Papers with Code

MELAGE: A purely python based Neuroimaging software (Neonatal)

MELAGE, a pioneering Python-based neuroimaging software, emerges as a versatile tool for the visualization, processing, and analysis of medical images. Initially conceived to address the unique challenges of processing 3D ultrasound and MRI brain images during the neonatal period, MELAGE exhibits remarkable adaptability, extending its utility to the domain of adult human brain imaging. At its core, MELAGE features a semi-automatic brain extraction tool empowered by a deep learning module, ensuring precise and efficient brain structure extraction from MRI and 3D Ultrasound data. Moreover, MELAGE offers a comprehensive suite of features, encompassing dynamic 3D visualization, accurate measurements, and interactive image segmentation. This transformative software holds immense promise for researchers and clinicians, offering streamlined image analysis, seamless integration with deep learning algorithms, and broad applicability in the realm of medical imaging.

arXiv:2309.07164공식 코드 · Papers with Code

Hybrid ASR for Resource-Constrained Robots: HMM - Deep Learning Fusion

This paper presents a novel hybrid Automatic Speech Recognition (ASR) system designed specifically for resource-constrained robots. The proposed approach combines Hidden Markov Models (HMMs) with deep learning models and leverages socket programming to distribute processing tasks effectively. In this architecture, the HMM-based processing takes place within the robot, while a separate PC handles the deep learning model. This synergy between HMMs and deep learning enhances speech recognition accuracy significantly. We conducted experiments across various robotic platforms, demonstrating real-time and precise speech recognition capabilities. Notably, the system exhibits adaptability to changing acoustic conditions and compatibility with low-power hardware, making it highly effective in environments with limited computational resources. This hybrid ASR paradigm opens up promising possibilities for seamless human-robot interaction. In conclusion, our research introduces a pioneering dimension to ASR techniques tailored for robotics. By employing socket programming to distribute processing tasks across distinct devices and strategically combining HMMs with deep learning models, our hybrid ASR system showcases its potential to enable robots to comprehend and respond to spoken language adeptly, even in environments with restricted computational resources. This paradigm sets a innovative course for enhancing human-robot interaction across a wide range of real-world scenarios.

arXiv:2309.07843공식 코드 · Papers with Code

Applying Deep Learning to Calibrate Stochastic Volatility Models

Stochastic volatility models, where the volatility is a stochastic process, can capture most of the essential stylized facts of implied volatility surfaces and give more realistic dynamics of the volatility smile/skew. However, they come with the significant issue that they take too long to calibrate. Alternative calibration methods based on Deep Learning (DL) techniques have been recently used to build fast and accurate solutions to the calibration problem. Huge and Savine developed a Differential Machine Learning (DML) approach, where Machine Learning models are trained on samples of not only features and labels but also differentials of labels to features. The present work aims to apply the DML technique to price vanilla European options (i.e. the calibration instruments), more specifically, puts when the underlying asset follows a Heston model and then calibrate the model on the trained network. DML allows for fast training and accurate pricing. The trained neural network dramatically reduces Heston calibration's computation time. In this work, we also introduce different regularisation techniques, and we apply them notably in the case of the DML. We compare their performance in reducing overfitting and improving the generalisation error. The DML performance is also compared to the classical DL (without differentiation) one in the case of Feed-Forward Neural Networks. We show that the DML outperforms the DL. The complete code for our experiments is provided in the GitHub repository: https://github.com/asridi/DML-Calibration-Heston-Model

arXiv:2309.05273공식 코드 · Papers with Code

Formalizing Multimedia Recommendation through Multimodal Deep Learning

Recommender systems (RSs) offer personalized navigation experiences on online platforms, but recommendation remains a challenging task, particularly in specific scenarios and domains. Multimodality can help tap into richer information sources and construct more refined user/item profiles for recommendations. However, existing literature lacks a shared and universal schema for modeling and solving the recommendation problem through the lens of multimodality. This work aims to formalize a general multimodal schema for multimedia recommendation. It provides a comprehensive literature review of multimodal approaches for multimedia recommendation from the last eight years, outlines the theoretical foundations of a multimodal pipeline, and demonstrates its rationale by applying it to selected state-of-the-art approaches. The work also conducts a benchmarking analysis of recent algorithms for multimedia recommendation within Elliot, a rigorous framework for evaluating recommender systems. The main aim is to provide guidelines for designing and implementing the next generation of multimodal approaches in multimedia recommendation.

arXiv:2309.04782공식 코드 · Papers with Code

IRCNN$^{+}$: An Enhanced Iterative Residual Convolutional Neural Network for Non-stationary Signal Decomposition

Time-frequency analysis is an important and challenging task in many applications. Fourier and wavelet analysis are two classic methods that have achieved remarkable success in many fields. However, they also exhibit limitations when applied to nonlinear and non-stationary signals. To address this challenge, a series of nonlinear and adaptive methods, pioneered by the empirical mode decomposition method, have been proposed. The goal of these methods is to decompose a non-stationary signal into quasi-stationary components that enhance the clarity of features during time-frequency analysis. Recently, inspired by deep learning, we proposed a novel method called iterative residual convolutional neural network (IRCNN). IRCNN not only achieves more stable decomposition than existing methods but also handles batch processing of large-scale signals with low computational cost. Moreover, deep learning provides a unique perspective for non-stationary signal decomposition. In this study, we aim to further improve IRCNN with the help of several nimble techniques from deep learning and optimization to ameliorate the method and overcome some of the limitations of this technique.

arXiv:2309.03791공식 코드 · Papers with Code

Adversarially Robust Learning with Optimal Transport Regularized Divergences

We introduce a new class of optimal-transport-regularized divergences, $D^c$, constructed via an infimal convolution between an information divergence, $D$, and an optimal-transport (OT) cost, $C$, and study their use in distributionally robust optimization (DRO). In particular, we propose the $ARMOR_D$ methods as novel approaches to enhancing the adversarial robustness of deep learning models. These DRO-based methods are defined by minimizing the maximum expected loss over a $D^c$-neighborhood of the empirical distribution of the training data. Viewed as a tool for constructing adversarial samples, our method allows samples to be both transported, according to the OT cost, and re-weighted, according to the information divergence; the addition of a principled and dynamical adversarial re-weighting on top of adversarial sample transport is a key innovation of $ARMOR_D$. $ARMOR_D$ can be viewed as a generalization of the best-performing loss functions and OT costs in the adversarial training literature; we demonstrate this flexibility by using $ARMOR_D$ to augment the UDR, TRADES, and MART methods and obtain improved performance on CIFAR-10 and CIFAR-100 image recognition. Specifically, augmenting with $ARMOR_D$ leads to 1.9\% and 2.1\% improvement against AutoAttack, a powerful ensemble of adversarial attacks, on CIFAR-10 and CIFAR-100 respectively. To foster reproducibility, we made the code accessible at https://github.com/star-ailab/ARMOR.

arXiv:2309.02527공식 코드 · Papers with Code

A skeletonization algorithm for gradient-based optimization

The skeleton of a digital image is a compact representation of its topology, geometry, and scale. It has utility in many computer vision applications, such as image description, segmentation, and registration. However, skeletonization has only seen limited use in contemporary deep learning solutions. Most existing skeletonization algorithms are not differentiable, making it impossible to integrate them with gradient-based optimization. Compatible algorithms based on morphological operations and neural networks have been proposed, but their results often deviate from the geometry and topology of the true medial axis. This work introduces the first three-dimensional skeletonization algorithm that is both compatible with gradient-based optimization and preserves an object's topology. Our method is exclusively based on matrix additions and multiplications, convolutional operations, basic non-linear functions, and sampling from a uniform probability distribution, allowing it to be easily implemented in any major deep learning library. In benchmarking experiments, we prove the advantages of our skeletonization algorithm compared to non-differentiable, morphological, and neural-network-based baselines. Finally, we demonstrate the utility of our algorithm by integrating it with two medical image processing applications that use gradient-based optimization: deep-learning-based blood vessel segmentation, and multimodal registration of the mandible in computed tomography and magnetic resonance images.

arXiv:2309.02995공식 코드 · Papers with Code

Continual Evidential Deep Learning for Out-of-Distribution Detection

Uncertainty-based deep learning models have attracted a great deal of interest for their ability to provide accurate and reliable predictions. Evidential deep learning stands out achieving remarkable performance in detecting out-of-distribution (OOD) data with a single deterministic neural network. Motivated by this fact, in this paper we propose the integration of an evidential deep learning method into a continual learning framework in order to perform simultaneously incremental object classification and OOD detection. Moreover, we analyze the ability of vacuity and dissonance to differentiate between in-distribution data belonging to old classes and OOD data. The proposed method, called CEDL, is evaluated on CIFAR-100 considering two settings consisting of 5 and 10 tasks, respectively. From the obtained results, we could appreciate that the proposed method, in addition to provide comparable results in object classification with respect to the baseline, largely outperforms OOD detection compared to several posthoc methods on three evaluation metrics: AUROC, AUPR and FPR95.

arXiv:2309.02072공식 코드 · Papers with Code

Global Neural Networks and The Data Scaling Effect in Financial Time Series Forecasting

Neural networks have revolutionized many empirical fields, yet their application to financial time series forecasting remains controversial. In this study, we demonstrate that the conventional practice of estimating models locally in data-scarce environments may underlie the mixed empirical performance observed in prior work. By focusing on volatility forecasting, we employ a dataset comprising over 10,000 global stocks and implement a global estimation strategy that pools information across cross-sections. Our econometric analysis reveals that forecasting accuracy improves markedly as the training dataset becomes larger and more heterogeneous. Notably, even with as little as 12 months of data, globally trained networks deliver robust predictions for individual stocks and portfolios that are not even in the training dataset. Furthermore, our interpretation of the model dynamics shows that these networks not only capture key stylized facts of volatility but also exhibit resilience to outliers and rapid adaptation to market regime changes. These findings underscore the importance of leveraging extensive and diverse datasets in financial forecasting and advocate for a shift from traditional local training approaches to integrated global estimation methods.

arXiv:2309.03058공식 코드 · Papers with Code

Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter

Recent years have witnessed a growing interest in tracking algorithms that augment Kalman Filters (KFs) with Deep Neural Networks (DNNs). By transforming KFs into trainable deep learning models, one can learn from data to reliably track a latent state in complex and partially known dynamics. However, unlike classic KFs, conventional DNN-based systems do not naturally provide an uncertainty measure, such as error covariance, alongside their estimates, which is crucial in various applications that rely on KF-type tracking. This work bridges this gap by studying error covariance extraction in DNN-aided KFs. We begin by characterizing how uncertainty can be extracted from existing DNN-aided algorithms and distinguishing between approaches by their ability to associate internal features with meaningful KF quantities, such as the Kalman Gain (KG) and prior covariance. We then identify that uncertainty extraction from existing architectures necessitates additional domain knowledge not required for state estimation. Based on this insight, we propose Bayesian KalmanNet, a novel DNN-aided KF that integrates Bayesian deep learning techniques with the recently proposed KalmanNet and transforms the KF into a stochastic machine learning architecture. This architecture employs sampling techniques to predict error covariance reliably without requiring additional domain knowledge, while retaining KalmanNet's ability to accurately track in partially known dynamics. Our numerical study demonstrates that Bayesian KalmanNet provides accurate and reliable tracking in various scenarios representing partially known dynamic systems.

arXiv:2309.00612공식 코드 · Papers with Code

Bayesian deep learning for cosmic volumes with modified gravity

The new generation of galaxy surveys will provide unprecedented data allowing us to test gravity at cosmological scales. A robust cosmological analysis of the large-scale structure demands exploiting the nonlinear information encoded in the cosmic web. Machine Learning techniques provide such tools, however, do not provide a priori assessment of uncertainties. This study aims at extracting cosmological parameters from modified gravity (MG) simulations through deep neural networks endowed with uncertainty estimations. We implement Bayesian neural networks (BNNs) with an enriched approximate posterior distribution considering two cases: one with a single Bayesian last layer (BLL), and another one with Bayesian layers at all levels (FullB). We train both BNNs with real-space density fields and power-spectra from a suite of 2000 dark matter only particle mesh $N$-body simulations including modified gravity models relying on MG-PICOLA covering 256 $h^{-1}$ Mpc side cubical volumes with 128$^3$ particles. BNNs excel in accurately predicting parameters for $\Omega_m$ and $\sigma_8$ and their respective correlation with the MG parameter. We find out that BNNs yield well-calibrated uncertainty estimates overcoming the over- and under-estimation issues in traditional neural networks. We observe that the presence of MG parameter leads to a significant degeneracy with $\sigma_8$ being one of the possible explanations of the poor MG predictions. Ignoring MG, we obtain a deviation of the relative errors in $\Omega_m$ and $\sigma_8$ by at least $30\%$. Moreover, we report consistent results from the density field and power spectra analysis, and comparable results between BLL and FullB experiments which permits us to save computing time by a factor of two. This work contributes in setting the path to extract cosmological parameters from complete small cosmic volumes towards the highly nonlinear regime.

arXiv:2308.15457공식 코드 · Papers with Code

From SMOTE to Mixup for Deep Imbalanced Classification

Given imbalanced data, it is hard to train a good classifier using deep learning because of the poor generalization of minority classes. Traditionally, the well-known synthetic minority oversampling technique (SMOTE) for data augmentation, a data mining approach for imbalanced learning, has been used to improve this generalization. However, it is unclear whether SMOTE also benefits deep learning. In this work, we study why the original SMOTE is insufficient for deep learning, and enhance SMOTE using soft labels. Connecting the resulting soft SMOTE with Mixup, a modern data augmentation technique, leads to a unified framework that puts traditional and modern data augmentation techniques under the same umbrella. A careful study within this framework shows that Mixup improves generalization by implicitly achieving uneven margins between majority and minority classes. We then propose a novel margin-aware Mixup technique that more explicitly achieves uneven margins. Extensive experimental results demonstrate that our proposed technique yields state-of-the-art performance on deep imbalanced classification while achieving superior performance on extremely imbalanced data. The code is open-sourced in our developed package https://github.com/ntucllab/imbalanced-DL to foster future research in this direction.

arXiv:2308.13816공식 코드 · Papers with Code

Homological Convolutional Neural Networks

Deep learning methods have demonstrated outstanding performances on classification and regression tasks on homogeneous data types (e.g., image, audio, and text data). However, tabular data still pose a challenge, with classic machine learning approaches being often computationally cheaper and equally effective than increasingly complex deep learning architectures. The challenge arises from the fact that, in tabular data, the correlation among features is weaker than the one from spatial or semantic relationships in images or natural language, and the dependency structures need to be modeled without any prior information. In this work, we propose a novel deep learning architecture that exploits the data structural organization through topologically constrained network representations to gain relational information from sparse tabular inputs. The resulting model leverages the power of convolution and is centered on a limited number of concepts from network topology to guarantee: (i) a data-centric and deterministic building pipeline; (ii) a high level of interpretability over the inference process; and (iii) an adequate room for scalability. We test our model on 18 benchmark datasets against 5 classic machine learning and 3 deep learning models, demonstrating that our approach reaches state-of-the-art performances on these challenging datasets. The code to reproduce all our experiments is provided at https://github.com/FinancialComputingUCL/HomologicalCNN.

arXiv:2308.13174공식 코드 · Papers with Code

Deep learning-based interactive segmentation in remote sensing

Interactive segmentation, a computer vision technique where a user provides guidance to help an algorithm segment a feature of interest in an image, has achieved outstanding accuracy and efficient human-computer interaction. However, few studies have discussed its application to remote sensing imagery, where click-based interactive segmentation could greatly facilitate the analysis of complicated landscapes. This study aims to bridge the gap between click-based interactive segmentation and remote sensing image analysis by conducting a benchmark study on various click-based interactive segmentation models. We assessed the performance of five state-of-the-art interactive segmentation methods (Reviving Iterative Training with Mask Guidance for Interactive Segmentation (RITM), FocalClick, SimpleClick, Iterative Click Loss (ICL), and Segment Anything (SAM)) on two high-resolution aerial imagery datasets. The Cascade-Forward Refinement (CFR) approach, an innovative inference strategy for interactive segmentation, was also introduced to enhance the segmentation results without requiring manual efforts. We further integrated CFR into all models for comparison. The performance of these methods on various land cover types, different object sizes, and multiple band combinations in the datasets was evaluated. The SimpleClick-CFR model consistently outperformed the other methods in our experiments. Building upon these findings, we developed a dedicated online tool called SegMap for interactive segmentation of remote sensing data. SegMap incorporates a well-performing interactive model that is fine-tuned with remote sensing data. Unlike existing interactive segmentation tools, SegMap offers robust interactivity, modifiability, and adaptability to analyze remote sensing imagery.

arXiv:2308.12871공식 코드 · Papers with Code

IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency

Efficiently optimizing multi-model inference pipelines for fast, accurate, and cost-effective inference is a crucial challenge in machine learning production systems, given their tight end-to-end latency requirements. To simplify the exploration of the vast and intricate trade-off space of latency, accuracy, and cost in inference pipelines, providers frequently opt to consider one of them. However, the challenge lies in reconciling latency, accuracy, and cost trade-offs. To address this challenge and propose a solution to efficiently manage model variants in inference pipelines, we present IPA, an online deep learning Inference Pipeline Adaptation system that efficiently leverages model variants for each deep learning task. Model variants are different versions of pre-trained models for the same deep learning task with variations in resource requirements, latency, and accuracy. IPA dynamically configures batch size, replication, and model variants to optimize accuracy, minimize costs, and meet user-defined latency Service Level Agreements (SLAs) using Integer Programming. It supports multi-objective settings for achieving different trade-offs between accuracy and cost objectives while remaining adaptable to varying workloads and dynamic traffic patterns. Navigating a wider variety of configurations allows \namex{} to achieve better trade-offs between cost and accuracy objectives compared to existing methods. Extensive experiments in a Kubernetes implementation with five real-world inference pipelines demonstrate that IPA improves end-to-end accuracy by up to 21% with a minimal cost increase. The code and data for replications are available at https://github.com/reconfigurable-ml-pipeline/ipa.

arXiv:2308.11991공식 코드 · Papers with Code

Relational Concept Bottleneck Models

The design of interpretable deep learning models working in relational domains poses an open challenge: interpretable deep learning methods, such as Concept Bottleneck Models (CBMs), are not designed to solve relational problems, while relational deep learning models, such as Graph Neural Networks (GNNs), are not as interpretable as CBMs. To overcome these limitations, we propose Relational Concept Bottleneck Models (R-CBMs), a family of relational deep learning methods providing interpretable task predictions. As special cases, we show that R-CBMs are capable of both representing standard CBMs and message-passing GNNs. To evaluate the effectiveness and versatility of these models, we designed a class of experimental problems, ranging from image classification to link prediction in knowledge graphs. In particular we show that R-CBMs (i) match generalization performance of existing relational black-boxes, (ii) support the generation of quantified concept-based explanations, (iii) effectively respond to test-time interventions, and (iv) withstand demanding settings including out-of-distribution scenarios, limited training data regimes, and scarce concept supervisions.

arXiv:2308.10282공식 코드 · Papers with Code

Enhancing Spatiotemporal Traffic Prediction through Urban Human Activity Analysis

Traffic prediction is one of the key elements to ensure the safety and convenience of citizens. Existing traffic prediction models primarily focus on deep learning architectures to capture spatial and temporal correlation. They often overlook the underlying nature of traffic. Specifically, the sensor networks in most traffic datasets do not accurately represent the actual road network exploited by vehicles, failing to provide insights into the traffic patterns in urban activities. To overcome these limitations, we propose an improved traffic prediction method based on graph convolution deep learning algorithms. We leverage human activity frequency data from National Household Travel Survey to enhance the inference capability of a causal relationship between activity and traffic patterns. Despite making minimal modifications to the conventional graph convolutional recurrent networks and graph convolutional transformer architectures, our approach achieves state-of-the-art performance without introducing excessive computational overhead.

arXiv:2308.08906공식 코드 · Papers with Code

Towards a Practical Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via Randomized Smoothing

Malware detectors based on deep learning (DL) have been shown to be susceptible to malware examples that have been deliberately manipulated in order to evade detection, a.k.a. adversarial malware examples. More specifically, it has been show that deep learning detectors are vulnerable to small changes on the input file. Given this vulnerability of deep learning detectors, we propose a practical defense against adversarial malware examples inspired by randomized smoothing. In our work, instead of employing Gaussian or Laplace noise when randomizing inputs, we propose a randomized ablation-based smoothing scheme that ablates a percentage of the bytes within an executable. During training, our randomized ablation-based smoothing scheme trains a base classifier based on ablated versions of the executable files. At test time, the final classification for a given input executable is taken as the class most commonly predicted by the classifier on a set of ablated versions of the original executable. To demonstrate the suitability of our approach we have empirically evaluated the proposed ablation-based model against various state-of-the-art evasion attacks on the BODMAS dataset. Results show greater robustness and generalization capabilities to adversarial malware examples in comparison to a non-smoothed classifier.