PyTorchKR Papers

최신 논문

총 367편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1806.10457

Physics-based Scene-level Reasoning for Object Pose Estimation in Clutter

This paper focuses on vision-based pose estimation for multiple rigid objects placed in clutter, especially in cases involving occlusions and objects resting on each other. Progress has been achieved recently in object recognition given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their applicability in robotics, where solutions must scale to a large number of objects and variety of conditions. Moreover, the combinatorial nature of the scenes that could arise from the placement of multiple objects is hard to capture in the training dataset. Thus, the learned models might not produce the desired level of precision required for tasks, such as robotic manipulation. This work proposes an autonomous process for pose estimation that spans from data generation to scene-level reasoning and self-learning. In particular, the proposed framework first generates a labeled dataset for training a Convolutional Neural Network (CNN) for object detection in clutter. These detections are used to guide a scene-level optimization process, which considers the interactions between the different objects present in the clutter to output pose estimates of high precision. Furthermore, confident estimates are used to label online real images from multiple views and re-train the process in a self-learning pipeline. Experimental results indicate that this process is quickly able to identify in cluttered scenes physically-consistent object poses that are more precise than the ones found by reasoning over individual instances of objects. Furthermore, the quality of pose estimates increases over time given the self-learning process.

arXiv:1307.7198

Self-Learning for Player Localization in Sports Video

This paper introduces a novel self-learning framework that automates the label acquisition process for improving models for detecting players in broadcast footage of sports games. Unlike most previous self-learning approaches for improving appearance-based object detectors from videos, we allow an unknown, unconstrained number of target objects in a more generalized video sequence with non-static camera views. Our self-learning approach uses a latent SVM learning algorithm and deformable part models to represent the shape and colour information of players, constraining their motions, and learns the colour of the playing field by a gentle Adaboost algorithm. We combine those image cues and discover additional labels automatically from unlabelled data. In our experiments, our approach exploits both labelled and unlabelled data in sparsely labelled videos of sports games, providing a mean performance improvement of over 20% in the average precision for detecting sports players and improved tracking, when videos contain very few labelled images.

arXiv:1312.4132

An introduction to synchronous self-learning Pareto strategy

In last decades optimization and control of complex systems that possessed various conflicted objectives simultaneously attracted an incremental interest of scientists. This is because of the vast applications of these systems in various fields of real life engineering phenomena that are generally multi modal, non convex and multi criterion. Hence, many researchers utilized versatile intelligent models such as Pareto based techniques, game theory (cooperative and non cooperative games), neuro evolutionary systems, fuzzy logic and advanced neural networks for handling these types of problems. In this paper a novel method called Synchronous Self Learning Pareto Strategy Algorithm (SSLPSA) is presented which utilizes Evolutionary Computing (EC), Swarm Intelligence (SI) techniques and adaptive Classical Self Organizing Map (CSOM) simultaneously incorporating with a data shuffling behavior. Evolutionary Algorithms (EA) which attempt to simulate the phenomenon of natural evolution are powerful numerical optimization algorithms that reach an approximate global maximum of a complex multi variable function over a wide search space and swarm base technique can improved the intensity and the robustness in EA. CSOM is a neural network capable of learning and can improve the quality of obtained optimal Pareto front. To prove the efficient performance of proposed algorithm, authors utilized some well known benchmark test functions. Obtained results indicate that the cited method is best suit in the case of vector optimization.

arXiv:1401.4589

miRNA and Gene Expression based Cancer Classification using Self- Learning and Co-Training Approaches

miRNA and gene expression profiles have been proved useful for classifying cancer samples. Efficient classifiers have been recently sought and developed. A number of attempts to classify cancer samples using miRNA/gene expression profiles are known in literature. However, the use of semi-supervised learning models have been used recently in bioinformatics, to exploit the huge corpuses of publicly available sets. Using both labeled and unlabeled sets to train sample classifiers, have not been previously considered when gene and miRNA expression sets are used. Moreover, there is a motivation to integrate both miRNA and gene expression for a semi-supervised cancer classification as that provides more information on the characteristics of cancer samples. In this paper, two semi-supervised machine learning approaches, namely self-learning and co-training, are adapted to enhance the quality of cancer sample classification. These approaches exploit the huge public corpuses to enrich the training data. In self-learning, miRNA and gene based classifiers are enhanced independently. While in co-training, both miRNA and gene expression profiles are used simultaneously to provide different views of cancer samples. To our knowledge, it is the first attempt to apply these learning approaches to cancer classification. The approaches were evaluated using breast cancer, hepatocellular carcinoma (HCC) and lung cancer expression sets. Results show up to 20% improvement in F1-measure over Random Forests and SVM classifiers. Co-Training also outperforms Low Density Separation (LDS) approach by around 25% improvement in F1-measure in breast cancer.

arXiv:1406.4296

Self-Learning Camera: Autonomous Adaptation of Object Detectors to Unlabeled Video Streams

Learning object detectors requires massive amounts of labeled training samples from the specific data source of interest. This is impractical when dealing with many different sources (e.g., in camera networks), or constantly changing ones such as mobile cameras (e.g., in robotics or driving assistant systems). In this paper, we address the problem of self-learning detectors in an autonomous manner, i.e. (i) detectors continuously updating themselves to efficiently adapt to streaming data sources (contrary to transductive algorithms), (ii) without any labeled data strongly related to the target data stream (contrary to self-paced learning), and (iii) without manual intervention to set and update hyper-parameters. To that end, we propose an unsupervised, on-line, and self-tuning learning algorithm to optimize a multi-task learning convex objective. Our method uses confident but laconic oracles (high-precision but low-recall off-the-shelf generic detectors), and exploits the structure of the problem to jointly learn on-line an ensemble of instance-level trackers, from which we derive an adapted category-level object detector. Our approach is validated on real-world publicly available video object datasets.

arXiv:1406.6854

A Fully Automated Latent Fingerprint Matcher with Embedded Self-learning Segmentation Module

Latent fingerprint has the practical value to identify the suspects who have unintentionally left a trace of fingerprint in the crime scenes. However, designing a fully automated latent fingerprint matcher is a very challenging task as it needs to address many challenging issues including the separation of overlapping structured patterns over the partial and poor quality latent fingerprint image, and finding a match against a large background database that would have different resolutions. Currently there is no fully automated latent fingerprint matcher available to the public and most literature reports have utilized a specialized latent fingerprint matcher COTS3 which is not accessible to the public. This will make it infeasible to assess and compare the relevant research work which is vital for this research community. In this study, we target to develop a fully automated latent matcher for adaptive detection of the region of interest and robust matching of latent prints. Unlike the manually conducted matching procedure, the proposed latent matcher can run like a sealed black box without any manual intervention. This matcher consists of the following two modules: (i) the dictionary learning-based region of interest (ROI) segmentation scheme; and (ii) the genetic algorithm-based minutiae set matching unit. Experimental results on NIST SD27 latent fingerprint database demonstrates that the proposed matcher outperforms the currently public state-of-art latent fingerprint matcher.

arXiv:1505.00835

A novel plasticity rule can explain the development of sensorimotor intelligence

Grounding autonomous behavior in the nervous system is a fundamental challenge for neuroscience. In particular, the self-organized behavioral development provides more questions than answers. Are there special functional units for curiosity, motivation, and creativity? This paper argues that these features can be grounded in synaptic plasticity itself, without requiring any higher level constructs. We propose differential extrinsic plasticity (DEP) as a new synaptic rule for self-learning systems and apply it to a number of complex robotic systems as a test case. Without specifying any purpose or goal, seemingly purposeful and adaptive behavior is developed, displaying a certain level of sensorimotor intelligence. These surprising results require no system specific modifications of the DEP rule but arise rather from the underlying mechanism of spontaneous symmetry breaking due to the tight brain-body-environment coupling. The new synaptic rule is biologically plausible and it would be an interesting target for a neurobiolocal investigation. We also argue that this neuronal mechanism may have been a catalyst in natural evolution.

arXiv:1507.00567공식 코드 · Papers with Code

Self-Learning Cloud Controllers: Fuzzy Q-Learning for Knowledge Evolution

Cloud controllers aim at responding to application demands by automatically scaling the compute resources at runtime to meet performance guarantees and minimize resource costs. Existing cloud controllers often resort to scaling strategies that are codified as a set of adaptation rules. However, for a cloud provider, applications running on top of the cloud infrastructure are more or less black-boxes, making it difficult at design time to define optimal or pre-emptive adaptation rules. Thus, the burden of taking adaptation decisions often is delegated to the cloud application. Yet, in most cases, application developers in turn have limited knowledge of the cloud infrastructure. In this paper, we propose learning adaptation rules during runtime. To this end, we introduce FQL4KE, a self-learning fuzzy cloud controller. In particular, FQL4KE learns and modifies fuzzy rules at runtime. The benefit is that for designing cloud controllers, we do not have to rely solely on precise design-time knowledge, which may be difficult to acquire. FQL4KE empowers users to specify cloud controllers by simply adjusting weights representing priorities in system goals instead of specifying complex adaptation rules. The applicability of FQL4KE has been experimentally assessed as part of the cloud application framework ElasticBench. The experimental results indicate that FQL4KE outperforms our previously developed fuzzy controller without learning mechanisms and the native Azure auto-scaling.

arXiv:1509.00714

Dictionary based Approach to Edge Detection

Edge detection is a very essential part of image processing, as quality and accuracy of detection determines the success of further processing. We have developed a new self learning technique for edge detection using dictionary comprised of eigenfilters constructed using features of the input image. The dictionary based method eliminates the need of pre or post processing of the image and accounts for noise, blurriness, class of image and variation of illumination during the detection process itself. Since, this method depends on the characteristics of the image, the new technique can detect edges more accurately and capture greater detail than existing algorithms such as Sobel, Prewitt Laplacian of Gaussian, Canny method etc which use generic filters and operators. We have demonstrated its application on various classes of images such as text, face, barcodes, traffic and cell images. An application of this technique to cell counting in a microscopic image is also presented.

arXiv:1603.08108

Support Driven Wavelet Frame-based Image Deblurring

The wavelet frame systems have been playing an active role in image restoration and many other image processing fields over the past decades, owing to the good capability of sparsely approximating piece-wise smooth functions such as images. In this paper, we propose a novel wavelet frame based sparse recovery model called \textit{Support Driven Sparse Regularization} (SDSR) for image deblurring, where the partial support information of frame coefficients is attained via a self-learning strategy and exploited via the proposed truncated $\ell_0$ regularization. Moreover, the state-of-the-art image restoration methods can be naturally incorporated into our proposed wavelet frame based sparse recovery framework. In particular, in order to achieve reliable support estimation of the frame coefficients, we make use of the state-of-the-art image restoration result such as that from the IDD-BM3D method as the initial reference image for support estimation. Our extensive experimental results have shown convincing improvements over existing state-of-the-art deblurring methods.

arXiv:1606.05572

Learning Interpretable Musical Compositional Rules and Traces

Throughout music history, theorists have identified and documented interpretable rules that capture the decisions of composers. This paper asks, "Can a machine behave like a music theorist?" It presents MUS-ROVER, a self-learning system for automatically discovering rules from symbolic music. MUS-ROVER performs feature learning via $n$-gram models to extract compositional rules --- statistical patterns over the resulting features. We evaluate MUS-ROVER on Bach's (SATB) chorales, demonstrating that it can recover known rules, as well as identify new, characteristic patterns for further study. We discuss how the extracted rules can be used in both machine and human composition.

arXiv:1610.03713

Optimistic Semi-supervised Least Squares Classification

The goal of semi-supervised learning is to improve supervised classifiers by using additional unlabeled training examples. In this work we study a simple self-learning approach to semi-supervised learning applied to the least squares classifier. We show that a soft-label and a hard-label variant of self-learning can be derived by applying block coordinate descent to two related but slightly different objective functions. The resulting soft-label approach is related to an idea about dealing with missing data that dates back to the 1930s. We show that the soft-label variant typically outperforms the hard-label variant on benchmark datasets and partially explain this behaviour by studying the relative difficulty of finding good local minima for the corresponding objective functions.

arXiv:1610.06488

An Evolving Neuro-Fuzzy System with Online Learning/Self-learning

An architecture of a new neuro-fuzzy system is proposed. The basic idea of this approach is to tune both synaptic weights and membership functions with the help of the supervised learning and self-learning paradigms. The approach to solving the problem has to do with evolving online neuro-fuzzy systems that can process data under uncertainty conditions. The results prove the effectiveness of the developed architecture and the learning procedure.

arXiv:1610.07857

Hybrid clustering-classification neural network in the medical diagnostics of reactive arthritis

The hybrid clustering-classification neural network is proposed. This network allows increasing a quality of information processing under the condition of overlapping classes due to the rational choice of a learning rate parameter and introducing a special procedure of fuzzy reasoning in the clustering process, which occurs both with an external learning signal (supervised) and without the one (unsupervised). As similarity measure neighborhood function or membership one, cosine structures are used, which allow to provide a high flexibility due to self-learning-learning process and to provide some new useful properties. Many realized experiments have confirmed the efficiency of proposed hybrid clustering-classification neural network; also, this network was used for solving diagnostics task of reactive arthritis.

arXiv:1611.06939

Predicting 1p19q Chromosomal Deletion of Low-Grade Gliomas from MR Images using Deep Learning

Objective: Several studies have associated codeletion of chromosome arms 1p/19q in low-grade gliomas (LGG) with positive response to treatment and longer progression free survival. Therefore, predicting 1p/19q status is crucial for effective treatment planning of LGG. In this study, we predict the 1p/19q status from MR images using convolutional neural networks (CNN), which could be a noninvasive alternative to surgical biopsy and histopathological analysis. Method: Our method consists of three main steps: image registration, tumor segmentation, and classification of 1p/19q status using CNN. We included a total of 159 LGG with 3 image slices each who had biopsy-proven 1p/19q status (57 nondeleted and 102 codeleted) and preoperative postcontrast-T1 (T1C) and T2 images. We divided our data into training, validation, and test sets. The training data was balanced for equal class probability and then augmented with iterations of random translational shift, rotation, and horizontal and vertical flips to increase the size of the training set. We shuffled and augmented the training data to counter overfitting in each epoch. Finally, we evaluated several configurations of a multi-scale CNN architecture until training and validation accuracies became consistent. Results: The results of the best performing configuration on the unseen test set were 93.3% (sensitivity), 82.22% (specificity), and 87.7% (accuracy). Conclusion: Multi-scale CNN with their self-learning capability provides promising results for predicting 1p/19q status noninvasively based on T1C and T2 images. Significance: Predicting 1p/19q status noninvasively from MR images would allow selecting effective treatment strategies for LGG patients without the need for surgical biopsy.

arXiv:1611.07544

Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model

In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved. The self-learning approach is deployed as progressive steps of object discovery, object enforcement, and label propagation. In the learning procedure, object locations in each frame are treated as latent variables that are solved with a progressive latent model (PLM). Compared with conventional latent models, the proposed PLM incorporates a spatial regularization term to reduce ambiguities in object proposals and to enforce object localization, and also a graph-based label propagation to discover harder instances in adjacent frames. With the difference of convex (DC) objective functions, PLM can be efficiently optimized with a concave-convex programming and thus guaranteeing the stability of self-learning. Extensive experiments demonstrate that even without annotation the proposed self-learning approach outperforms weakly supervised learning approaches, while achieving comparable performance with transfer learning and fully supervised approaches.

arXiv:1710.11446

Clothing Retrieval with Visual Attention Model

Clothing retrieval is a challenging problem in computer vision. With the advance of Convolutional Neural Networks (CNNs), the accuracy of clothing retrieval has been significantly improved. FashionNet[1], a recent study, proposes to employ a set of artificial features in the form of landmarks for clothing retrieval, which are shown to be helpful for retrieval. However, the landmark detection module is trained with strong supervision which requires considerable efforts to obtain. In this paper, we propose a self-learning Visual Attention Model (VAM) to extract attention maps from clothing images. The VAM is further connected to a global network to form an end-to-end network structure through Impdrop connection which randomly Dropout on the feature maps with the probabilities given by the attention map. Extensive experiments on several widely used benchmark clothing retrieval data sets have demonstrated the promise of the proposed method. We also show that compared to the trivial Product connection, the Impdrop connection makes the network structure more robust when training sets of limited size are used.

arXiv:1711.07915

10Sent: A Stable Sentiment Analysis Method Based on the Combination of Off-The-Shelf Approaches

Sentiment analysis has become a very important tool for analysis of social media data. There are several methods developed for this research field, many of them working very differently from each other, covering distinct aspects of the problem and disparate strategies. Despite the large number of existent techniques, there is no single one which fits well in all cases or for all data sources. Supervised approaches may be able to adapt to specific situations but they require manually labeled training, which is very cumbersome and expensive to acquire, mainly for a new application. In this context, in here, we propose to combine several very popular and effective state-of-the-practice sentiment analysis methods, by means of an unsupervised bootstrapped strategy for polarity classification. One of our main goals is to reduce the large variability (lack of stability) of the unsupervised methods across different domains (datasets). Our solution was thoroughly tested considering thirteen different datasets in several domains such as opinions, comments, and social media. The experimental results demonstrate that our combined method (aka, 10SENT) improves the effectiveness of the classification task, but more importantly, it solves a key problem in the field. It is consistently among the best methods in many data types, meaning that it can produce the best (or close to best) results in almost all considered contexts, without any additional costs (e.g., manual labeling). Our self-learning approach is also very independent of the base methods, which means that it is highly extensible to incorporate any new additional method that can be envisioned in the future. Finally, we also investigate a transfer learning approach for sentiment analysis as a means to gather additional (unsupervised) information for the proposed approach and we show the potential of this technique to improve our results.

arXiv:1801.08486

Self-Learning to Detect and Segment Cysts in Lung CT Images without Manual Annotation

Image segmentation is a fundamental problem in medical image analysis. In recent years, deep neural networks achieve impressive performances on many medical image segmentation tasks by supervised learning on large manually annotated data. However, expert annotations on big medical datasets are tedious, expensive or sometimes unavailable. Weakly supervised learning could reduce the effort for annotation but still required certain amounts of expertise. Recently, deep learning shows a potential to produce more accurate predictions than the original erroneous labels. Inspired by this, we introduce a very weakly supervised learning method, for cystic lesion detection and segmentation in lung CT images, without any manual annotation. Our method works in a self-learning manner, where segmentation generated in previous steps (first by unsupervised segmentation then by neural networks) is used as ground truth for the next level of network learning. Experiments on a cystic lung lesion dataset show that the deep learning could perform better than the initial unsupervised annotation, and progressively improve itself after self-learning.

arXiv:1802.01115공식 코드 · Papers with Code

End2You -- The Imperial Toolkit for Multimodal Profiling by End-to-End Learning

We introduce End2You -- the Imperial College London toolkit for multimodal profiling by end-to-end deep learning. End2You is an open-source toolkit implemented in Python and is based on Tensorflow. It provides capabilities to train and evaluate models in an end-to-end manner, i.e., using raw input. It supports input from raw audio, visual, physiological or other types of information or combination of those, and the output can be of an arbitrary representation, for either classification or regression tasks. To our knowledge, this is the first toolkit that provides generic end-to-end learning for profiling capabilities in either unimodal or multimodal cases. To test our toolkit, we utilise the RECOLA database as was used in the AVEC 2016 challenge. Experimental results indicate that End2You can provide comparable results to state-of-the-art methods despite no need of expert-alike feature representations, but self-learning these from the data "end to end".