PyTorchKR Papers

최신 논문

총 2,847편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2012.01740

Sparse Semi-Supervised Action Recognition with Active Learning

Current state-of-the-art methods for skeleton-based action recognition are supervised and rely on labels. The reliance is limiting the performance due to the challenges involved in annotation and mislabeled data. Unsupervised methods have been introduced, however, they organize sequences into clusters and still require labels to associate clusters with actions. In this paper, we propose a novel approach for skeleton-based action recognition, called SESAR, that connects these approaches. SESAR leverages the information from both unlabeled data and a handful of sequences actively selected for labeling, combining unsupervised training with sparsely supervised guidance. SESAR is composed of two main components, where the first component learns a latent representation for unlabeled action sequences through an Encoder-Decoder RNN which reconstructs the sequences, and the second component performs active learning to select sequences to be labeled based on cluster and classification uncertainty. When the two components are simultaneously trained on skeleton-based action sequences, they correspond to a robust system for action recognition with only a handful of labeled samples. We evaluate our system on common datasets with multiple sequences and actions, such as NW UCLA, NTU RGB+D 60, and UWA3D. Our results outperform standalone skeleton-based supervised, unsupervised with cluster identification, and active-learning methods for action recognition when applied to sparse labeled samples, as low as 1% of the data.

arXiv:2010.13340

What can be learned from satisfaction assessments?

Companies survey their customers to measure their satisfaction levels with the company and its services. The received responses are crucial as they allow companies to assess their respective performances and find ways to make needed improvements. This study focuses on the non-systematic bias that arises when customers assign numerical values in ordinal surveys. Using real customer satisfaction survey data of a large retail bank, we show that the common practice of segmenting ordinal survey responses into uneven segments limit the value that can be extracted from the data. We then show that it is possible to assess the magnitude of the irreducible error under simple assumptions, even in real surveys, and place the achievable modeling goal in perspective. We finish the study by suggesting that a thoughtful survey design, which uses either a careful binning strategy or proper calibration, can reduce the compounding non-systematic error even in elaborated ordinal surveys. A possible application of the calibration method we propose is efficiently conducting targeted surveys using active learning.

arXiv:2007.00126

Functional MRI applications for psychiatric disease subtyping: a review

Psychiatric disorders have historically been classified using symptom information alone. With the advent of new technologies that allowed researchers to investigate brain mechanisms more directly, interest in the mechanistic rationale behind defined pathologies and aetiology redefinition has greatly increased. This is particularly appealing for the field of personalised medicine, which searches for data-driven approaches to improve individual diagnosis, prognosis and treatment selection. Here we intend to systematically analyse the usage of functional MRI on both the elucidation of psychiatric disease biotypes and the interpretation of subtypes obtained via unsupervised learning applied to symptom or biomarker data. We searched the existing literature for functional MRI applications to the obtention or interpretation of psychiatric disease subtypes. The PRISMA guidelines were applied to filter the retrieved studies, and the active learning framework ASReviews was applied for article prioritization. From the 20 studies that met the inclusion criteria, 5 used functional MRI data to interpret symptom-derived disease clusters, 4 used it for the interpretation of clusters derived from biomarker data other than fMRI itself, and 11 applied clustering to fMRI directly. Major depression disorder and schizophrenia were the two most studied pathologies, followed by ADHD, psychosis, autism disorder, and early violence. No trans-diagnostic studies were retrieved. While interest in personalised medicine and data-driven disease subtyping is on the rise and psychiatry is not the exception, unsupervised analyses of functional MRI data are inconsistent to date, and much remains to be done in terms of gathering and centralising data, standardising pipelines and model validation, and method refinement. The usage of fMRI in the field of trans-diagnostic psychiatry remains vastly unexplored.

arXiv:2006.14684

Active Learning Pipeline for Brain Mapping in a High Performance Computing Environment

This paper describes a scalable active learning pipeline prototype for large-scale brain mapping that leverages high performance computing power. It enables high-throughput evaluation of algorithm results, which, after human review, are used for iterative machine learning model training. Image processing and machine learning are performed in a batch layer. Benchmark testing of image processing using pMATLAB shows that a 100$\times$ increase in throughput (10,000%) can be achieved while total processing time only increases by 9% on Xeon-G6 CPUs and by 22% on Xeon-E5 CPUs, indicating robust scalability. The images and algorithm results are provided through a serving layer to a browser-based user interface for interactive review. This pipeline has the potential to greatly reduce the manual annotation burden and improve the overall performance of machine learning-based brain mapping.

arXiv:1911.12635

Learning switched systems from simulation models

The design of decision and control strategies for switched systems typically requires complete knowledge of (i) mathematical models of the subsystems and (ii) restrictions on admissible switches between the subsystems. We propose an active learning algorithm that infers (i) and (ii) for discrete-time switched systems whose subsystems dynamics are governed by sets of scalar polynomials and switching signals are constrained by automata. We collect data from gray-box simulation models of the switched systems for this purpose. Our technique for learning (i) involves linear algebraic tools, while for learning (ii) we employ a modified version of the well-known $L^*$-algorithm from machine learning literature. A numerical example is presented to demonstrate our learning algorithm.

arXiv:1810.10323

Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments

Object detection in streaming images is a major step in different detection-based applications, such as object tracking, action recognition, robot navigation, and visual surveillance applications. In mostcases, image quality is noisy and biased, and as a result, the data distributions are disturbed and imbalanced. Most object detection approaches, such as the faster region-based convolutional neural network (Faster RCNN), Single Shot Multibox Detector with 300x300 inputs (SSD300), and You Only Look Once version 2 (YOLOv2), rely on simple sampling without considering distortions and noise under real-world changing environments, despite poor object labeling. In this paper, we propose an Incremental active semi-supervised learning (IASSL) technology for unseen object detection. It combines batch-based active learning (AL) and bin-based semi-supervised learning (SSL) to leverage the strong points of AL's exploration and SSL's exploitation capabilities. A collaborative sampling method is also adopted to measure the uncertainty and diversity of AL and the confidence in SSL. Batch-based AL allows us to select more informative, confident, and representative samples with low cost. Bin-based SSL divides streaming image samples into several bins, and each bin repeatedly transfers the discriminative knowledge of convolutional neural network (CNN) deep learning to the next bin until the performance criterion is reached. IASSL can overcome noisy and biased labels in unknown, cluttered data distributions. We obtain superior performance, compared to state-of-the-art technologies such as Faster RCNN, SSD300, and YOLOv2.

arXiv:1810.07778

Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice

Active learning aims to reduce annotation cost by predicting which samples are useful for a human teacher to label. However it has become clear there is no best active learning algorithm. Inspired by various philosophies about what constitutes a good criteria, different algorithms perform well on different datasets. This has motivated research into ensembles of active learners that learn what constitutes a good criteria in a given scenario, typically via multi-armed bandit algorithms. Though algorithm ensembles can lead to better results, they overlook the fact that not only does algorithm efficacy vary across datasets, but also during a single active learning session. That is, the best criteria is non-stationary. This breaks existing algorithms' guarantees and hampers their performance in practice. In this paper, we propose dynamic ensemble active learning as a more general and promising research direction. We develop a dynamic ensemble active learner based on a non-stationary multi-armed bandit with expert advice algorithm. Our dynamic ensemble selects the right criteria at each step of active learning. It has theoretical guarantees, and shows encouraging results on $13$ popular datasets.

arXiv:1810.05414공식 코드 · Papers with Code

Technology Assisted Reviews: Finding the Last Few Relevant Documents by Asking Yes/No Questions to Reviewers

The goal of a technology-assisted review is to achieve high recall with low human effort. Continuous active learning algorithms have demonstrated good performance in locating the majority of relevant documents in a collection, however their performance is reaching a plateau when 80\%-90\% of them has been found. Finding the last few relevant documents typically requires exhaustively reviewing the collection. In this paper, we propose a novel method to identify these last few, but significant, documents efficiently. Our method makes the hypothesis that entities carry vital information in documents, and that reviewers can answer questions about the presence or absence of an entity in the missing relevance documents. Based on this we devise a sequential Bayesian search method that selects the optimal sequence of questions to ask. The experimental results show that our proposed method can greatly improve performance requiring less reviewing effort.

arXiv:1810.01240

Efficient Seismic fragility curve estimation by Active Learning on Support Vector Machines

Fragility curves which express the failure probability of a structure, or critical components, as function of a loading intensity measure are nowadays widely used (i) in Seismic Probabilistic Risk Assessment studies, (ii) to evaluate impact of construction details on the structural performance of installations under seismic excitations or under other loading sources such as wind. To avoid the use of parametric models such as lognormal model to estimate fragility curves from a reduced number of numerical calculations, a methodology based on Support Vector Machines coupled with an active learning algorithm is proposed in this paper. In practice, input excitation is reduced to some relevant parameters and, given these parameters, SVMs are used for a binary classification of the structural responses relative to a limit threshold of exceedance. Since the output is not only binary, this is a score, a probabilistic interpretation of the output is exploited to estimate very efficiently fragility curves as score functions or as functions of classical seismic intensity measures.

arXiv:1807.03257

Data Efficient Lithography Modeling with Transfer Learning and Active Data Selection

Lithography simulation is one of the key steps in physical verification, enabled by the substantial optical and resist models. A resist model bridges the aerial image simulation to printed patterns. While the effectiveness of learning-based solutions for resist modeling has been demonstrated, they are considerably data-demanding. Meanwhile, a set of manufactured data for a specific lithography configuration is only valid for the training of one single model, indicating low data efficiency. Due to the complexity of the manufacturing process, obtaining enough data for acceptable accuracy becomes very expensive in terms of both time and cost, especially during the evolution of technology generations when the design space is intensively explored. In this work, we propose a new resist modeling framework for contact layers, utilizing existing data from old technology nodes and active selection of data in a target technology node, to reduce the amount of data required from the target lithography configuration. Our framework based on transfer learning and active learning techniques is effective within a competitive range of accuracy, i.e., 3-10X reduction on the amount of training data with comparable accuracy to the state-of-the-art learning approach.

arXiv:1801.05881

A Pipeline for Post-Crisis Twitter Data Acquisition

Due to instant availability of data on social media platforms like Twitter, and advances in machine learning and data management technology, real-time crisis informatics has emerged as a prolific research area in the last decade. Although several benchmarks are now available, especially on portals like CrisisLex, an important, practical problem that has not been addressed thus far is the rapid acquisition and benchmarking of data from free, publicly available streams like the Twitter API. In this paper, we present ongoing work on a pipeline for facilitating immediate post-crisis data collection, curation and relevance filtering from the Twitter API. The pipeline is minimally supervised, alleviating the need for feature engineering by including a judicious mix of data preprocessing and fast text embeddings, along with an active learning framework. We illustrate the utility of the pipeline by describing a recent case study wherein it was used to collect and analyze millions of tweets in the immediate aftermath of the Las Vegas shootings.

arXiv:1709.01024

Payoff Information and Learning in Signaling Games

We add the assumption that players know their opponents' payoff functions and rationality to a model of non-equilibrium learning in signaling games. Agents are born into player roles and play against random opponents every period. Inexperienced agents are uncertain about the prevailing distribution of opponents' play, but believe that opponents never choose conditionally dominated strategies. Agents engage in active learning and update beliefs based on personal observations. Payoff information can refine or expand learning predictions, since patient young senders' experimentation incentives depend on which receiver responses they deem plausible. We show that with payoff knowledge, the limiting set of long-run learning outcomes is bounded above by rationality-compatible equilibria (RCE), and bounded below by uniform RCE. RCE refine the Intuitive Criterion (Cho and Kreps, 1987) and include all divine equilibria (Banks and Sobel, 1987). Uniform RCE sometimes but not always exists, and implies universally divine equilibrium.

arXiv:2012.01227

Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning

Active learning is widely used to reduce labeling effort and training time by repeatedly querying only the most beneficial samples from unlabeled data. In real-world problems where data cannot be stored indefinitely due to limited storage or privacy issues, the query selection and the model update should be performed as soon as a new data sample is observed. Various online active learning methods have been studied to deal with these challenges; however, there are difficulties in selecting representative query samples and updating the model efficiently without forgetting. In this study, we propose Message Passing Adaptive Resonance Theory (MPART) that learns the distribution and topology of input data online. Through message passing on the topological graph, MPART actively queries informative and representative samples, and continuously improves the classification performance using both labeled and unlabeled data. We evaluate our model in stream-based selective sampling scenarios with comparable query selection strategies, showing that MPART significantly outperforms competitive models.

arXiv:2012.00901

Deep Multi-Fidelity Active Learning of High-dimensional Outputs

Many applications, such as in physical simulation and engineering design, demand we estimate functions with high-dimensional outputs. The training examples can be collected with different fidelities to allow a cost/accuracy trade-off. In this paper, we consider the active learning task that identifies both the fidelity and input to query new training examples so as to achieve the best benefit-cost ratio. To this end, we propose DMFAL, a Deep Multi-Fidelity Active Learning approach. We first develop a deep neural network-based multi-fidelity model for learning with high-dimensional outputs, which can flexibly, efficiently capture all kinds of complex relationships across the outputs and fidelities to improve prediction. We then propose a mutual information-based acquisition function that extends the predictive entropy principle. To overcome the computational challenges caused by large output dimensions, we use multi-variate Delta's method and moment-matching to estimate the output posterior, and Weinstein-Aronszajn identity to calculate and optimize the acquisition function. The computation is tractable, reliable and efficient. We show the advantage of our method in several applications of computational physics and engineering design.

arXiv:2012.00452공식 코드 · Papers with Code

Counting People by Estimating People Flows

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness constraints across consecutive frames. In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing them. This enables us to impose much stronger constraints encoding the conservation of the number of people. As a result, it significantly boosts performance without requiring a more complex architecture. Furthermore, it allows us to exploit the correlation between people flow and optical flow to further improve the results. We also show that leveraging people conservation constraints in both a spatial and temporal manner makes it possible to train a deep crowd counting model in an active learning setting with much fewer annotations. This significantly reduces the annotation cost while still leading to similar performance to the full supervision case.

arXiv:2011.14015공식 코드 · Papers with Code

Active Learning in CNNs via Expected Improvement Maximization

Deep learning models such as Convolutional Neural Networks (CNNs) have demonstrated high levels of effectiveness in a variety of domains, including computer vision and more recently, computational biology. However, training effective models often requires assembling and/or labeling large datasets, which may be prohibitively time-consuming or costly. Pool-based active learning techniques have the potential to mitigate these issues, leveraging models trained on limited data to selectively query unlabeled data points from a pool in an attempt to expedite the learning process. Here we present "Dropout-based Expected IMprOvementS" (DEIMOS), a flexible and computationally-efficient approach to active learning that queries points that are expected to maximize the model's improvement across a representative sample of points. The proposed framework enables us to maintain a prediction covariance matrix capturing model uncertainty, and to dynamically update this matrix in order to generate diverse batches of points in the batch-mode setting. Our active learning results demonstrate that DEIMOS outperforms several existing baselines across multiple regression and classification tasks taken from computer vision and genomics.

arXiv:2011.14370

A smartphone based multi input workflow for non-invasive estimation of haemoglobin levels using machine learning techniques

We suggest a low cost, non invasive healthcare system that measures haemoglobin levels in patients and can be used as a preliminary diagnostic test for anaemia. A combination of image processing, machine learning and deep learning techniques are employed to develop predictive models to measure haemoglobin levels. This is achieved through the color analysis of the fingernail beds, palpebral conjunctiva and tongue of the patients. This predictive model is then encapsulated in a healthcare application. This application expedites data collection and facilitates active learning of the model. It also incorporates personalized calibration of the model for each patient, assisting in the continual monitoring of the haemoglobin levels of the patient. Upon validating this framework using data, it can serve as a highly accurate preliminary diagnostic test for anaemia.

arXiv:2011.14307

Active Output Selection Strategies for Multiple Learning Regression Models

Active learning shows promise to decrease test bench time for model-based drivability calibration. This paper presents a new strategy for active output selection, which suits the needs of calibration tasks. The strategy is actively learning multiple outputs in the same input space. It chooses the output model with the highest cross-validation error as leading. The presented method is applied to three different toy examples with noise in a real world range and to a benchmark dataset. The results are analyzed and compared to other existing strategies. In a best case scenario, the presented strategy is able to decrease the number of points by up to 30% compared to a sequential space-filling design while outperforming other existing active learning strategies. The results are promising but also show that the algorithm has to be improved to increase robustness for noisy environments. Further research will focus on improving the algorithm and applying it to a real-world example.

arXiv:2011.14696공식 코드 · Papers with Code

On Initial Pools for Deep Active Learning

Active Learning (AL) techniques aim to minimize the training data required to train a model for a given task. Pool-based AL techniques start with a small initial labeled pool and then iteratively pick batches of the most informative samples for labeling. Generally, the initial pool is sampled randomly and labeled to seed the AL iterations. While recent studies have focused on evaluating the robustness of various query functions in AL, little to no attention has been given to the design of the initial labeled pool for deep active learning. Given the recent successes of learning representations in self-supervised/unsupervised ways, we study if an intelligently sampled initial labeled pool can improve deep AL performance. We investigate the effect of intelligently sampled initial labeled pools, including the use of self-supervised and unsupervised strategies, on deep AL methods. The setup, hypotheses, methodology, and implementation details were evaluated by peer review before experiments were conducted. Experimental results could not conclusively prove that intelligently sampled initial pools are better for AL than random initial pools in the long run, although a Variational Autoencoder-based initial pool sampling strategy showed interesting trends that merit deeper investigation.

arXiv:2011.15001

Variance based sensitivity analysis for Monte Carlo and importance sampling reliability assessment with Gaussian processes

Running a reliability analysis on engineering problems involving complex numerical models can be computationally very expensive, requiring advanced simulation methods to reduce the overall numerical cost. Gaussian process based active learning methods for reliability analysis have emerged as a promising way for reducing this computational cost. The learning phase of these methods consists in building a Gaussian process surrogate model of the performance function and using the uncertainty structure of the Gaussian process to enrich iteratively this surrogate model. For that purpose a learning criterion has to be defined. Then, the estimation of the probability of failure is typically obtained by a classification of a population evaluated on the final surrogate model. Hence, the estimator of the probability of failure holds two different uncertainty sources related to the surrogate model approximation and to the sampling based integration technique. In this paper, we propose a methodology to quantify the sensitivity of the probability of failure estimator to both uncertainty sources. This analysis also enables to control the whole error associated to the failure probability estimate and thus provides an accuracy criterion on the estimation. Thus, an active learning approach integrating this analysis to reduce the main source of error and stopping when the global variability is sufficiently low is introduced. The approach is proposed for both a Monte Carlo based method as well as an importance sampling based method, seeking to improve the estimation of rare event probabilities. Performance of the proposed strategy is then assessed on several examples.