PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2110.04598

Self-explaining Neural Network with Concept-based Explanations for ICU Mortality Prediction

Complex deep learning models show high prediction tasks in various clinical prediction tasks but their inherent complexity makes it more challenging to explain model predictions for clinicians and healthcare providers. Existing research on explainability of deep learning models in healthcare have two major limitations: using post-hoc explanations and using raw clinical variables as units of explanation, both of which are often difficult for human interpretation. In this work, we designed a self-explaining deep learning framework using the expert-knowledge driven clinical concepts or intermediate features as units of explanation. The self-explaining nature of our proposed model comes from generating both explanations and predictions within the same architectural framework via joint training. We tested our proposed approach on a publicly available Electronic Health Records (EHR) dataset for predicting patient mortality in the ICU. In order to analyze the performance-interpretability trade-off, we compared our proposed model with a baseline having the same set-up but without the explanation components. Experimental results suggest that adding explainability components to a deep learning framework does not impact prediction performance and the explanations generated by the model can provide insights to the clinicians to understand the possible reasons behind patient mortality.

arXiv:2110.04466

ProductAE: Towards Training Larger Channel Codes based on Neural Product Codes

There have been significant research activities in recent years to automate the design of channel encoders and decoders via deep learning. Due the dimensionality challenge in channel coding, it is prohibitively complex to design and train relatively large neural channel codes via deep learning techniques. Consequently, most of the results in the literature are limited to relatively short codes having less than 100 information bits. In this paper, we construct ProductAEs, a computationally efficient family of deep-learning driven (encoder, decoder) pairs, that aim at enabling the training of relatively large channel codes (both encoders and decoders) with a manageable training complexity. We build upon the ideas from classical product codes, and propose constructing large neural codes using smaller code components. More specifically, instead of directly training the encoder and decoder for a large neural code of dimension $k$ and blocklength $n$, we provide a framework that requires training neural encoders and decoders for the code parameters $(n_1,k_1)$ and $(n_2,k_2)$ such that $n_1 n_2=n$ and $k_1 k_2=k$. Our training results show significant gains, over all ranges of signal-to-noise ratio (SNR), for a code of parameters $(225,100)$ and a moderate-length code of parameters $(441,196)$, over polar codes under successive cancellation (SC) decoder. Moreover, our results demonstrate meaningful gains over Turbo Autoencoder (TurboAE) and state-of-the-art classical codes. This is the first work to design product autoencoders and a pioneering work on training large channel codes.

arXiv:2110.04301공식 코드 · Papers with Code

Salient ImageNet: How to discover spurious features in Deep Learning?

Deep neural networks can be unreliable in the real world especially when they heavily use {\it spurious} features for their predictions. Focusing on image classifications, we define {\it core features} as the set of visual features that are always a part of the object definition while {\it spurious features} are the ones that are likely to {\it co-occur} with the object but not a part of it (e.g., attribute "fingers" for class "band aid"). Traditional methods for discovering spurious features either require extensive human annotations (thus, not scalable), or are useful on specific models. In this work, we introduce a {\it general} framework to discover a subset of spurious and core visual features used in inferences of a general model and localize them on a large number of images with minimal human supervision. Our methodology is based on this key idea: to identify spurious or core \textit{visual features} used in model predictions, we identify spurious or core \textit{neural features} (penultimate layer neurons of a robust model) via limited human supervision (e.g., using top 5 activating images per feature). We then show that these neural feature annotations {\it generalize} extremely well to many more images {\it without} any human supervision. We use the activation maps for these neural features as the soft masks to highlight spurious or core visual features. Using this methodology, we introduce the {\it Salient Imagenet} dataset containing core and spurious masks for a large set of samples from Imagenet. Using this dataset, we show that several popular Imagenet models rely heavily on various spurious features in their predictions, indicating the standard accuracy alone is not sufficient to fully assess model performance. Code and dataset for reproducing all experiments in the paper is available at \url{https://github.com/singlasahil14/salient_imagenet}.

arXiv:2110.05086

Deep Video Anomaly Detection: Opportunities and Challenges

Anomaly detection is a popular and vital task in various research contexts, which has been studied for several decades. To ensure the safety of people's lives and assets, video surveillance has been widely deployed in various public spaces, such as crossroads, elevators, hospitals, banks, and even in private homes. Deep learning has shown its capacity in a number of domains, ranging from acoustics, images, to natural language processing. However, it is non-trivial to devise intelligent video anomaly detection systems cause anomalies significantly differ from each other in different application scenarios. There are numerous advantages if such intelligent systems could be realised in our daily lives, such as saving human resources in a large degree, reducing financial burden on the government, and identifying the anomalous behaviours timely and accurately. Recently, many studies on extending deep learning models for solving anomaly detection problems have emerged, resulting in beneficial advances in deep video anomaly detection techniques. In this paper, we present a comprehensive review of deep learning-based methods to detect the video anomalies from a new perspective. Specifically, we summarise the opportunities and challenges of deep learning models on video anomaly detection tasks, respectively. We put forth several potential future research directions of intelligent video anomaly detection system in various application domains. Moreover, we summarise the characteristics and technical problems in current deep learning methods for video anomaly detection.

arXiv:2110.04764

Deep learning-based person re-identification methods: A survey and outlook of recent works

In recent years, with the increasing demand for public safety and the rapid development of intelligent surveillance networks, person re-identification (Re-ID) has become one of the hot research topics in the computer vision field. The main research goal of person Re-ID is to retrieve persons with the same identity from different cameras. However, traditional person Re-ID methods require manual marking of person targets, which consumes a lot of labor cost. With the widespread application of deep neural networks, many deep learning-based person Re-ID methods have emerged. Therefore, this paper is to facilitate researchers to understand the latest research results and the future trends in the field. Firstly, we summarize the studies of several recently published person Re-ID surveys and complement the latest research methods to systematically classify deep learning-based person Re-ID methods. Secondly, we propose a multi-dimensional taxonomy that classifies current deep learning-based person Re-ID methods into four categories according to metric and representation learning, including methods for deep metric learning, local feature learning, generative adversarial learning and sequence feature learning. Furthermore, we subdivide the above four categories according to their methodologies and motivations, discussing the advantages and limitations of part subcategories. Finally, we discuss some challenges and possible research directions for person Re-ID.

arXiv:2110.04427

Harnessing Unlabeled Data to Improve Generalization of Biometric Gender and Age Classifiers

With significant advances in deep learning, many computer vision applications have reached the inflection point. However, these deep learning models need large amount of labeled data for model training and optimum parameter estimation. Limited labeled data for model training results in over-fitting and impacts their generalization performance. However, the collection and annotation of large amount of data is a very time consuming and expensive operation. Further, due to privacy and security concerns, the large amount of labeled data could not be collected for certain applications such as those involving medical field. Self-training, Co-training, and Self-ensemble methods are three types of semi-supervised learning methods that can be used to exploit unlabeled data. In this paper, we propose self-ensemble based deep learning model that along with limited labeled data, harness unlabeled data for improving the generalization performance. We evaluated the proposed self-ensemble based deep-learning model for soft-biometric gender and age classification. Experimental evaluation on CelebA and VISOB datasets suggest gender classification accuracy of 94.46% and 81.00%, respectively, using only 1000 labeled samples and remaining 199k samples as unlabeled samples for CelebA dataset and similarly,1000 labeled samples with remaining 107k samples as unlabeled samples for VISOB dataset. Comparative evaluation suggest that there is $5.74\%$ and $8.47\%$ improvement in the accuracy of the self-ensemble model when compared with supervised model trained on the entire CelebA and VISOB dataset, respectively. We also evaluated the proposed learning method for age-group prediction on Adience dataset and it outperformed the baseline supervised deep-learning learning model with a better exact accuracy of 55.55 $\pm$ 4.28 which is 3.92% more than the baseline.

arXiv:2110.04425공식 코드 · Papers with Code

Arabic Speech Emotion Recognition Employing Wav2vec2.0 and HuBERT Based on BAVED Dataset

Recently, there have been tremendous research outcomes in the fields of speech recognition and natural language processing. This is due to the well-developed multi-layers deep learning paradigms such as wav2vec2.0, Wav2vecU, WavBERT, and HuBERT that provide better representation learning and high information capturing. Such paradigms run on hundreds of unlabeled data, then fine-tuned on a small dataset for specific tasks. This paper introduces a deep learning constructed emotional recognition model for Arabic speech dialogues. The developed model employs the state of the art audio representations include wav2vec2.0 and HuBERT. The experiment and performance results of our model overcome the previous known outcomes.

arXiv:2110.04369

A Loss Curvature Perspective on Training Instability in Deep Learning

In this work, we study the evolution of the loss Hessian across many classification tasks in order to understand the effect the curvature of the loss has on the training dynamics. Whereas prior work has focused on how different learning rates affect the loss Hessian observed during training, we also analyze the effects of model initialization, architectural choices, and common training heuristics such as gradient clipping and learning rate warmup. Our results demonstrate that successful model and hyperparameter choices allow the early optimization trajectory to either avoid -- or navigate out of -- regions of high curvature and into flatter regions that tolerate a higher learning rate. Our results suggest a unifying perspective on how disparate mitigation strategies for training instability ultimately address the same underlying failure mode of neural network optimization, namely poor conditioning. Inspired by the conditioning perspective, we show that learning rate warmup can improve training stability just as much as batch normalization, layer normalization, MetaInit, GradInit, and Fixup initialization.

arXiv:2110.05290공식 코드 · Papers with Code

Homogeneous Learning: Self-Attention Decentralized Deep Learning

Federated learning (FL) has been facilitating privacy-preserving deep learning in many walks of life such as medical image classification, network intrusion detection, and so forth. Whereas it necessitates a central parameter server for model aggregation, which brings about delayed model communication and vulnerability to adversarial attacks. A fully decentralized architecture like Swarm Learning allows peer-to-peer communication among distributed nodes, without the central server. One of the most challenging issues in decentralized deep learning is that data owned by each node are usually non-independent and identically distributed (non-IID), causing time-consuming convergence of model training. To this end, we propose a decentralized learning model called Homogeneous Learning (HL) for tackling non-IID data with a self-attention mechanism. In HL, training performs on each round's selected node, and the trained model of a node is sent to the next selected node at the end of each round. Notably, for the selection, the self-attention mechanism leverages reinforcement learning to observe a node's inner state and its surrounding environment's state, and find out which node should be selected to optimize the training. We evaluate our method with various scenarios for an image classification task. The result suggests that HL can produce a better performance compared with standalone learning and greatly reduce both the total training rounds by 50.8% and the communication cost by 74.6% compared with random policy-based decentralized learning for training on non-IID data.

arXiv:2110.04442

A Primer on Deep Learning for Causal Inference

This review systematizes the emerging literature for causal inference using deep neural networks under the potential outcomes framework. It provides an intuitive introduction on how deep learning can be used to estimate/predict heterogeneous treatment effects and extend causal inference to settings where confounding is non-linear, time varying, or encoded in text, networks, and images. To maximize accessibility, we also introduce prerequisite concepts from causal inference and deep learning. The survey differs from other treatments of deep learning and causal inference in its sharp focus on observational causal estimation, its extended exposition of key algorithms, and its detailed tutorials for implementing, training, and selecting among deep estimators in Tensorflow 2 available at github.com/kochbj/Deep-Learning-for-Causal-Inference.

arXiv:2110.04316

COVID-19 Face Mask Recognition with Advanced Face Cut Algorithm for Human Safety Measures

In the last year, the outbreak of COVID-19 has deployed computer vision and machine learning algorithms in various fields to enhance human life interactions. COVID-19 is a highly contaminated disease that affects mainly the respiratory organs of the human body. We must wear a mask in this situation as the virus can be contaminated through the air and a non-masked person can be affected. Our proposal deploys a computer vision and deep learning framework to recognize face masks from images or videos. We have implemented a Boundary dependent face cut recognition algorithm that can cut the face from the image using 27 landmarks and then the preprocessed image can further be sent to the deep learning ResNet50 model. The experimental result shows a significant advancement of 3.4 percent compared to the YOLOV3 mask recognition architecture in just 10 epochs.

arXiv:2110.04151

Text analysis and deep learning: A network approach

Much information available to applied researchers is contained within written language or spoken text. Deep language models such as BERT have achieved unprecedented success in many applications of computational linguistics. However, much less is known about how these models can be used to analyze existing text. We propose a novel method that combines transformer models with network analysis to form a self-referential representation of language use within a corpus of interest. Our approach produces linguistic relations strongly consistent with the underlying model as well as mathematically well-defined operations on them, while reducing the amount of discretionary choices of representation and distance measures. It represents, to the best of our knowledge, the first unsupervised method to extract semantic networks directly from deep language models. We illustrate our approach in a semantic analysis of the term "founder". Using the entire corpus of Harvard Business Review from 1980 to 2020, we find that ties in our network track the semantics of discourse over time, and across contexts, identifying and relating clusters of semantic and syntactic relations. Finally, we discuss how this method can also complement and inform analyses of the behavior of deep learning models.

arXiv:2110.04130

Learning post-processing for QRS detection using Recurrent Neural Network

Deep-learning based QRS-detection algorithms often require essential post-processing to refine the prediction streams for R-peak localisation. The post-processing performs signal-processing tasks from as simple as, removing isolated 0s or 1s in the prediction-stream to sophisticated steps, which require domain-specific knowledge, including the minimum threshold of a QRS-complex extent or R-R interval. Often these thresholds vary among QRS-detection studies and are empirically determined for the target dataset, which may have implications if the target dataset differs. Moreover, these studies, in general, fail to identify the relative strengths of deep-learning models and post-processing to weigh them appropriately. This study classifies post-processing, as found in the QRS-detection literature, into two levels - moderate, and advanced - and advocates that the thresholds be learned by an appropriate deep-learning module, called a Gated Recurrent Unit (GRU), to avoid explicitly setting post-processing thresholds. This is done by utilising the same philosophy of shifting from hand-crafted feature-engineering to deep-learning-based feature-extraction. The results suggest that GRU learns the post-processing level and the QRS detection performance using GRU-based post-processing marginally follows the domain-specific manual post-processing, without requiring usage of domain-specific threshold parameters. To the best of our knowledge, the use of GRU to learn QRS-detection post-processing from CNN model generated prediction streams is the first of its kind. The outcome was used to recommend a modular design for a QRS-detection system, where the level of complexity of the CNN model and post-processing can be tuned based on the deployment environment.

arXiv:2110.03689

DeepECMP: Predicting Extracellular Matrix Proteins using Deep Learning

Introduction: The extracellular matrix (ECM) is a networkof proteins and carbohydrates that has a structural and bio-chemical function. The ECM plays an important role in dif-ferentiation, migration and signaling. Several studies havepredicted ECM proteins using machine learning algorithmssuch as Random Forests, K-nearest neighbours and supportvector machines but is yet to be explored using deep learn-ing. Method: DeepECMP was developed using several previ-ously used ECM datasets, asymmetric undersampling andan ensemble of 11 feed-forward neural networks. Results: The performance of DeepECMP was 83.6% bal-anced accuracy which outperformed several algorithms. Inaddition, the pipeline of DeepECMP has been shown to behighly efficient. Conclusion: This paper is the first to focus on utilizingdeep learning for ECM prediction. Several limitations areovercome by DeepECMP such as computational expense,availability to the public and usability outside of the humanspecies

arXiv:2110.04175공식 코드 · Papers with Code

RelaySum for Decentralized Deep Learning on Heterogeneous Data

In decentralized machine learning, workers compute model updates on their local data. Because the workers only communicate with few neighbors without central coordination, these updates propagate progressively over the network. This paradigm enables distributed training on networks without all-to-all connectivity, helping to protect data privacy as well as to reduce the communication cost of distributed training in data centers. A key challenge, primarily in decentralized deep learning, remains the handling of differences between the workers' local data distributions. To tackle this challenge, we introduce the RelaySum mechanism for information propagation in decentralized learning. RelaySum uses spanning trees to distribute information exactly uniformly across all workers with finite delays depending on the distance between nodes. In contrast, the typical gossip averaging mechanism only distributes data uniformly asymptotically while using the same communication volume per step as RelaySum. We prove that RelaySGD, based on this mechanism, is independent of data heterogeneity and scales to many workers, enabling highly accurate decentralized deep learning on heterogeneous data. Our code is available at http://github.com/epfml/relaysgd.

arXiv:2110.04079

A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection

Accurate and reliable lane detection is vital for the safe performance of lane-keeping assistance and lane departure warning systems. However, under certain challenging circumstances, it is difficult to get satisfactory performance in accurately detecting the lanes from one single image as mostly done in current literature. Since lane markings are continuous lines, the lanes that are difficult to be accurately detected in the current single image can potentially be better deduced if information from previous frames is incorporated. This study proposes a novel hybrid spatial-temporal (ST) sequence-to-one deep learning architecture. This architecture makes full use of the ST information in multiple continuous image frames to detect the lane markings in the very last frame. Specifically, the hybrid model integrates the following aspects: (a) the single image feature extraction module equipped with the spatial convolutional neural network; (b) the ST feature integration module constructed by ST recurrent neural network; (c) the encoder-decoder structure, which makes this image segmentation problem work in an end-to-end supervised learning format. Extensive experiments reveal that the proposed model architecture can effectively handle challenging driving scenes and outperforms available state-of-the-art methods.

arXiv:2110.03999

Graphs as Tools to Improve Deep Learning Methods

In recent years, deep neural networks (DNNs) have known an important rise in popularity. However, although they are state-of-the-art in many machine learning challenges, they still suffer from several limitations. For example, DNNs require a lot of training data, which might not be available in some practical applications. In addition, when small perturbations are added to the inputs, DNNs are prone to misclassification errors. DNNs are also viewed as black-boxes and as such their decisions are often criticized for their lack of interpretability. In this chapter, we review recent works that aim at using graphs as tools to improve deep learning methods. These graphs are defined considering a specific layer in a deep learning architecture. Their vertices represent distinct samples, and their edges depend on the similarity of the corresponding intermediate representations. These graphs can then be leveraged using various methodologies, many of which built on top of graph signal processing. This chapter is composed of four main parts: tools for visualizing intermediate layers in a DNN, denoising data representations, optimizing graph objective functions and regularizing the learning process.

arXiv:2110.03423

Efficient GPU implementation of randomized SVD and its applications

Matrix decompositions are ubiquitous in machine learning, including applications in dimensionality reduction, data compression and deep learning algorithms. Typical solutions for matrix decompositions have polynomial complexity which significantly increases their computational cost and time. In this work, we leverage efficient processing operations that can be run in parallel on modern Graphical Processing Units (GPUs), predominant computing architecture used e.g. in deep learning, to reduce the computational burden of computing matrix decompositions. More specifically, we reformulate the randomized decomposition problem to incorporate fast matrix multiplication operations (BLAS-3) as building blocks. We show that this formulation, combined with fast random number generators, allows to fully exploit the potential of parallel processing implemented in GPUs. Our extensive evaluation confirms the superiority of this approach over the competing methods and we release the results of this research as a part of the official CUDA implementation (https://docs.nvidia.com/cuda/cusolver/index.html).

arXiv:2110.03528

Decoding ECoG signal into 3D hand translation using deep learning

Motor brain-computer interfaces (BCIs) are a promising technology that may enable motor-impaired people to interact with their environment. Designing real-time and accurate BCI is crucial to make such devices useful, safe, and easy to use by patients in a real-life environment. Electrocorticography (ECoG)-based BCIs emerge as a good compromise between invasiveness of the recording device and good spatial and temporal resolution of the recorded signal. However, most ECoG signal decoders used to predict continuous hand movements are linear models. These models have a limited representational capacity and may fail to capture the relationship between ECoG signal and continuous hand movements. Deep learning (DL) models, which are state-of-the-art in many problems, could be a solution to better capture this relationship. In this study, we tested several DL-based architectures to predict imagined 3D continuous hand translation using time-frequency features extracted from ECoG signals. The dataset used in the analysis is a part of a long-term clinical trial (ClinicalTrials.gov identifier: NCT02550522) and was acquired during a closed-loop experiment with a tetraplegic subject. The proposed architectures include multilayer perceptron (MLP), convolutional neural networks (CNN), and long short-term memory networks (LSTM). The accuracy of the DL-based and multilinear models was compared offline using cosine similarity. Our results show that CNN-based architectures outperform the current state-of-the-art multilinear model. The best architecture exploited the spatial correlation between neighboring electrodes with CNN and benefited from the sequential character of the desired hand trajectory by using LSTMs. Overall, DL increased the average cosine similarity, compared to the multilinear model, by up to 60%, from 0.189 to 0.302 and from 0.157 to 0.249 for the left and right hand, respectively.

arXiv:2110.03393

Multivariate Anomaly Detection based on Prediction Intervals Constructed using Deep Learning

It has been shown that deep learning models can under certain circumstances outperform traditional statistical methods at forecasting. Furthermore, various techniques have been developed for quantifying the forecast uncertainty (prediction intervals). In this paper, we utilize prediction intervals constructed with the aid of artificial neural networks to detect anomalies in the multivariate setting. Challenges with existing deep learning-based anomaly detection approaches include $(i)$ large sets of parameters that may be computationally intensive to tune, $(ii)$ returning too many false positives rendering the techniques impractical for use, $(iii)$ requiring labeled datasets for training which are often not prevalent in real life. Our approach overcomes these challenges. We benchmark our approach against the oft-preferred well-established statistical models. We focus on three deep learning architectures, namely, cascaded neural networks, reservoir computing and long short-term memory recurrent neural networks. Our finding is deep learning outperforms (or at the very least is competitive to) the latter.