PyTorchKR Papers

최신 논문

총 11,809편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1911.10301

Learning a Representation with the Block-Diagonal Structure for Pattern Classification

Sparse-representation-based classification (SRC) has been widely studied and developed for various practical signal classification applications. However, the performance of a SRC-based method is degraded when both the training and test data are corrupted. To counteract this problem, we propose an approach that learns Representation with Block-Diagonal Structure (RBDS) for robust image recognition. To be more specific, we first introduce a regularization term that captures the block-diagonal structure of the target representation matrix of the training data. The resulting problem is then solved by an optimizer. Last, based on the learned representation, a simple yet effective linear classifier is used for the classification task. The experimental results obtained on several benchmarking datasets demonstrate the efficacy of the proposed RBDS method.

arXiv:1911.10800

Random projections: data perturbation for classification problems

Random projections offer an appealing and flexible approach to a wide range of large-scale statistical problems. They are particularly useful in high-dimensional settings, where we have many covariates recorded for each observation. In classification problems there are two general techniques using random projections. The first involves many projections in an ensemble -- the idea here is to aggregate the results after applying different random projections, with the aim of achieving superior statistical accuracy. The second class of methods include hashing and sketching techniques, which are straightforward ways to reduce the complexity of a problem, perhaps therefore with a huge computational saving, while approximately preserving the statistical efficiency.

arXiv:1911.10720공식 코드 · Papers with Code

Non-parametric Uni-modality Constraints for Deep Ordinal Classification

We propose a new constrained-optimization formulation for deep ordinal classification, in which uni-modality of the label distribution is enforced implicitly via a set of inequality constraints over all the pairs of adjacent labels. Based on (c-1) constraints for c labels, our model is non-parametric and, therefore, more flexible than the existing deep ordinal classification techniques. Unlike these, it does not restrict the learned representation to a single and specific parametric model (or penalty) imposed on all the labels. Therefore, it enables the training to explore larger spaces of solutions, while removing the need for ad hoc choices and scaling up to large numbers of labels. It can be used in conjunction with any standard classification loss and any deep architecture. To tackle the ensuing challenging optimization problem, we solve a sequence of unconstrained losses based on a powerful extension of the log-barrier method. This handles effectively competing constraints and accommodates standard SGD for deep networks, while avoiding computationally expensive Lagrangian dual steps and outperforming substantially penalty methods. Furthermore, we propose a new performance metric for ordinal classification, as a proxy to measure distribution uni-modality, referred to as the Sides Order Index (SOI). We report comprehensive evaluations and comparisons to state-of-the-art methods on benchmark public datasets for several ordinal classification tasks, showing the merits of our approach in terms of label consistency, classification accuracy and scalability. Importantly, enforcing label consistency with our model does not incur higher classification errors, unlike many existing ordinal classification methods. A public reproducible PyTorch implementation is provided. (https://github.com/sbelharbi/unimodal-prob-deep-oc-free-distribution)

arXiv:1911.10688공식 코드 · Papers with Code

Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator

Mutual information is widely applied to learn latent representations of observations, whilst its implication in classification neural networks remain to be better explained. We show that optimising the parameters of classification neural networks with softmax cross-entropy is equivalent to maximising the mutual information between inputs and labels under the balanced data assumption. Through experiments on synthetic and real datasets, we show that softmax cross-entropy can estimate mutual information approximately. When applied to image classification, this relation helps approximate the point-wise mutual information between an input image and a label without modifying the network structure. To this end, we propose infoCAM, informative class activation map, which highlights regions of the input image that are the most relevant to a given label based on differences in information. The activation map helps localise the target object in an input image. Through experiments on the semi-supervised object localisation task with two real-world datasets, we evaluate the effectiveness of our information-theoretic approach.

arXiv:1911.10599

Latent space conditioning for improved classification and anomaly detection

We propose a new type of variational autoencoder to perform improved pre-processing for clustering and anomaly detection on data with a given label. Anomalies however are not known or labeled. We call our method conditional latent space variational autonencoder since it separates the latent space by conditioning on information within the data. The method fits one prior distribution to each class in the dataset, effectively expanding the prior distribution to include a Gaussian mixture model. Our approach is compared against the capabilities of a typical variational autoencoder by measuring their V-score during cluster formation with respect to the k-means and EM algorithms. For anomaly detection, we use a new metric composed of the mass-volume and excess-mass curves which can work in an unsupervised setting. We compare the results between established methods such as as isolation forest, local outlier factor and one-class support vector machine.

arXiv:1911.10558공식 코드 · Papers with Code

Fast Polynomial Kernel Classification for Massive Data

In the era of big data, it is desired to develop efficient machine learning algorithms to tackle massive data challenges such as storage bottleneck, algorithmic scalability, and interpretability. In this paper, we develop a novel efficient classification algorithm, called fast polynomial kernel classification (FPC), to conquer the scalability and storage challenges. Our main tools are a suitable selected feature mapping based on polynomial kernels and an alternating direction method of multipliers (ADMM) algorithm for a related non-smooth convex optimization problem. Fast learning rates as well as feasibility verifications including the efficiency of an ADMM solver with convergence guarantees and the selection of center points are established to justify theoretical behaviors of FPC. Our theoretical assertions are verified by a series of simulations and real data applications. Numerical results demonstrate that FPC significantly reduces the computational burden and storage memory of existing learning schemes such as support vector machines, Nystr\"{o}m and random feature methods, without sacrificing their generalization abilities much.

arXiv:1911.10182

Universal adversarial examples in speech command classification

Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human. Although this topic has been intensively studied in the image domain, classification tasks in the audio domain have received less attention. In this paper we address the existence of universal perturbations for speech command classification. We provide evidence that universal attacks can be generated for speech command classification tasks, which are able to generalize across different models to a significant extent. Additionally, a novel analytical framework is proposed for the evaluation of universal perturbations under different levels of universality, demonstrating that the feasibility of generating effective perturbations decreases as the universality level increases. Finally, we propose a more detailed and rigorous framework to measure the amount of distortion introduced by the perturbations, demonstrating that the methods employed by convention are not realistic in audio-based problems.

arXiv:1911.10022

Direct Classification of Type 2 Diabetes From Retinal Fundus Images in a Population-based Sample From The Maastricht Study

Type 2 Diabetes (T2D) is a chronic metabolic disorder that can lead to blindness and cardiovascular disease. Information about early stage T2D might be present in retinal fundus images, but to what extent these images can be used for a screening setting is still unknown. In this study, deep neural networks were employed to differentiate between fundus images from individuals with and without T2D. We investigated three methods to achieve high classification performance, measured by the area under the receiver operating curve (ROC-AUC). A multi-target learning approach to simultaneously output retinal biomarkers as well as T2D works best (AUC = 0.746 [$\pm$0.001]). Furthermore, the classification performance can be improved when images with high prediction uncertainty are referred to a specialist. We also show that the combination of images of the left and right eye per individual can further improve the classification performance (AUC = 0.758 [$\pm$0.003]), using a simple averaging approach. The results are promising, suggesting the feasibility of screening for T2D from retinal fundus images.

arXiv:1911.10003공식 코드 · Papers with Code

Locality Constraint Dictionary Learning with Support Vector for Pattern Classification

Discriminative dictionary learning (DDL) has recently gained significant attention due to its impressive performance in various pattern classification tasks. However, the locality of atoms is not fully explored in conventional DDL approaches which hampers their classification performance. In this paper, we propose a locality constraint dictionary learning with support vector discriminative term (LCDL-SV), in which the locality information is preserved by employing the graph Laplacian matrix of the learned dictionary. To jointly learn a classifier during the training phase, a support vector discriminative term is incorporated into the proposed objective function. Moreover, in the classification stage, the identity of test data is jointly determined by the regularized residual and the learned multi-class support vector machine. Finally, the resulting optimization problem is solved by utilizing the alternative strategy. Experimental results on benchmark databases demonstrate the superiority of our proposed method over previous dictionary learning approaches on both hand-crafted and deep features. The source code of our proposed LCDL-SV is accessible at https://github.com/yinhefeng/LCDL-SV

arXiv:1911.09996공식 코드 · Papers with Code

Orderless Recurrent Models for Multi-label Classification

Recurrent neural networks (RNN) are popular for many computer vision tasks, including multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered for the multi-label classification task. Current approaches sort labels according to their frequency, typically ordering them in either rare-first or frequent-first. These imposed orderings do not take into account that the natural order to generate the labels can change for each image, e.g.\ first the dominant object before summing up the smaller objects in the image. Therefore, in this paper, we propose ways to dynamically order the ground truth labels with the predicted label sequence. This allows for the faster training of more optimal LSTM models for multi-label classification. Analysis evidences that our method does not suffer from duplicate generation, something which is common for other models. Furthermore, it outperforms other CNN-RNN models, and we show that a standard architecture of an image encoder and language decoder trained with our proposed loss obtains the state-of-the-art results on the challenging MS-COCO, WIDER Attribute and PA-100K and competitive results on NUS-WIDE.

arXiv:1911.09977

Artificial neural networks in action for an automated cell-type classification of biological neural networks

Identification of different neuronal cell types is critical for understanding their contribution to brain functions. Yet, automated and reliable classification of neurons remains a challenge, primarily because of their biological complexity. Typical approaches include laborious and expensive immunohistochemical analysis while feature extraction algorithms based on cellular characteristics have recently been proposed. The former rely on molecular markers, which are often expressed in many cell types, while the latter suffer from similar issues: finding features that are distinctive for each class has proven to be equally challenging. Moreover, both approaches are time consuming and demand a lot of human intervention. In this work we establish the first, automated cell-type classification method that relies on neuronal activity rather than molecular or cellular features. We test our method on a real-world dataset comprising of raw calcium activity signals for four neuronal types. We compare the performance of three different deep learning models and demonstrate that our method can achieve automated classification of neuronal cell types with unprecedented accuracy.

arXiv:1911.09953공식 코드 · Papers with Code

Class-specific residual constraint non-negative representation for pattern classification

Representation based classification method (RBCM) remains one of the hottest topics in the community of pattern recognition, and the recently proposed non-negative representation based classification (NRC) achieved impressive recognition results in various classification tasks. However, NRC ignores the relationship between the coding and classification stages. Moreover, there is no regularization term other than the reconstruction error term in the formulation of NRC, which may result in unstable solution leading to misclassification. To overcome these drawbacks of NRC, in this paper, we propose a class-specific residual constraint non-negative representation (CRNR) for pattern classification. CRNR introduces a class-specific residual constraint into the formulation of NRC, which encourages training samples from different classes to competitively represent the test sample. Based on the proposed CRNR, we develop a CRNR based classifier (CRNRC) for pattern classification. Experimental results on several benchmark datasets demonstrate the superiority of CRNRC over conventional RBCM as well as the recently proposed NRC. Moreover, CRNRC works better or comparable to some state-of-the-art deep approaches on diverse challenging pattern classification tasks. The source code of our proposed CRNRC is accessible at https://github.com/yinhefeng/CRNRC.

arXiv:1911.09389

Classification-driven Single Image Dehazing

Most existing dehazing algorithms often use hand-crafted features or Convolutional Neural Networks (CNN)-based methods to generate clear images using pixel-level Mean Square Error (MSE) loss. The generated images generally have better visual appeal, but not always have better performance for high-level vision tasks, e.g. image classification. In this paper, we investigate a new point of view in addressing this problem. Instead of focusing only on achieving good quantitative performance on pixel-based metrics such as Peak Signal to Noise Ratio (PSNR), we also ensure that the dehazed image itself does not degrade the performance of the high-level vision tasks such as image classification. To this end, we present an unified CNN architecture that includes three parts: a dehazing sub-network (DNet), a classification-driven Conditional Generative Adversarial Networks sub-network (CCGAN) and a classification sub-network (CNet) related to image classification, which has better performance both on visual appeal and image classification. We conduct comprehensive experiments on two challenging benchmark datasets for fine-grained and object classification: CUB-200-2011 and Caltech-256. Experimental results demonstrate that the proposed method outperforms many recent state-of-the-art single image dehazing methods in terms of image dehazing metrics and classification accuracy.

arXiv:1911.09359

Multi-Scale RCNN Model for Financial Time-series Classification

Financial time-series classification (FTC) is extremely valuable for investment management. In past decades, it draws a lot of attention from a wide extent of research areas, especially Artificial Intelligence (AI). Existing researches majorly focused on exploring the effects of the Multi-Scale (MS) property or the Temporal Dependency (TD) within financial time-series. Unfortunately, most previous researches fail to combine these two properties effectively and often fall short of accuracy and profitability. To effectively combine and utilize both properties of financial time-series, we propose a Multi-Scale Temporal Dependent Recurrent Convolutional Neural Network (MSTD-RCNN) for FTC. In the proposed method, the MS features are simultaneously extracted by convolutional units to precisely describe the state of the financial market. Moreover, the TD and complementary across different scales are captured through a Recurrent Neural Network. The proposed method is evaluated on three financial time-series datasets which source from the Chinese stock market. Extensive experimental results indicate that our model achieves the state-of-the-art performance in trend classification and simulated trading, compared with classical and advanced baseline models.

arXiv:1911.09349

An End-to-End Audio Classification System based on Raw Waveforms and Mix-Training Strategy

Audio classification can distinguish different kinds of sounds, which is helpful for intelligent applications in daily life. However, it remains a challenging task since the sound events in an audio clip is probably multiple, even overlapping. This paper introduces an end-to-end audio classification system based on raw waveforms and mix-training strategy. Compared to human-designed features which have been widely used in existing research, raw waveforms contain more complete information and are more appropriate for multi-label classification. Taking raw waveforms as input, our network consists of two variants of ResNet structure which can learn a discriminative representation. To explore the information in intermediate layers, a multi-level prediction with attention structure is applied in our model. Furthermore, we design a mix-training strategy to break the performance limitation caused by the amount of training data. Experiments show that the mean average precision of the proposed audio classification system on Audio Set dataset is 37.2%. Without using extra training data, our system exceeds the state-of-the-art multi-level attention model.

arXiv:1911.09243

Multi-Label Classification with Label Graph Superimposing

Images or videos always contain multiple objects or actions. Multi-label recognition has been witnessed to achieve pretty performance attribute to the rapid development of deep learning technologies. Recently, graph convolution network (GCN) is leveraged to boost the performance of multi-label recognition. However, what is the best way for label correlation modeling and how feature learning can be improved with label system awareness are still unclear. In this paper, we propose a label graph superimposing framework to improve the conventional GCN+CNN framework developed for multi-label recognition in the following two aspects. Firstly, we model the label correlations by superimposing label graph built from statistical co-occurrence information into the graph constructed from knowledge priors of labels, and then multi-layer graph convolutions are applied on the final superimposed graph for label embedding abstraction. Secondly, we propose to leverage embedding of the whole label system for better representation learning. In detail, lateral connections between GCN and CNN are added at shallow, middle and deep layers to inject information of label system into backbone CNN for label-awareness in the feature learning process. Extensive experiments are carried out on MS-COCO and Charades datasets, showing that our proposed solution can greatly improve the recognition performance and achieves new state-of-the-art recognition performance.

arXiv:1911.08589

Machine Learning Classification Informed by a Functional Biophysical System

We present a novel machine learning architecture for classification suggested by experiments on olfactory systems. The network separates input stimuli, represented as spatially distinct currents, via winnerless competition---a process based on the intrinsic sequential dynamics of the neural system---then uses a support vector machine (SVM) to provide precision to the space-time separation of the output. The combined network uses biophysical models of neurons and shows high discrimination among inputs and robustness to noise. While using the SVM alone does not permit determination of the components of mixtures of classified inputs, the combined network is able to tell the precise concentrations of the constituent parts.

arXiv:1911.08556

Towards Reducing Bias in Gender Classification

Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant representations of human faces with an adversarially trained autoencoder model. We show that such representations help us achieve less biased performance in gender classification. We use variance in classification accuracy across different races as a surrogate for the racial bias of the model and achieve a drop of over 40% in variance with race invariant representations.

arXiv:1911.08554

Classification as Decoder: Trading Flexibility for Control in Medical Dialogue

Generative seq2seq dialogue systems are trained to predict the next word in dialogues that have already occurred. They can learn from large unlabeled conversation datasets, build a deeper understanding of conversational context, and generate a wide variety of responses. This flexibility comes at the cost of control, a concerning tradeoff in doctor/patient interactions. Inaccuracies, typos, or undesirable content in the training data will be reproduced by the model at inference time. We trade a small amount of labeling effort and some loss of response variety in exchange for quality control. More specifically, a pretrained language model encodes the conversational context, and we finetune a classification head to map an encoded conversational context to a response class, where each class is a noisily labeled group of interchangeable responses. Experts can update these exemplar responses over time as best practices change without retraining the classifier or invalidating old training data. Expert evaluation of 775 unseen doctor/patient conversations shows that only 12% of the discriminative model's responses are worse than the what the doctor ended up writing, compared to 18% for the generative model.

arXiv:1911.09008

Learning Embeddings from Cancer Mutation Sets for Classification Tasks

Analysis of somatic mutation profiles from cancer patients is essential in the development of cancer research. However, the low frequency of most mutations and the varying rates of mutations across patients makes the data extremely challenging to statistically analyze as well as difficult to use in classification problems, for clustering, visualization or for learning useful information. Thus, the creation of low dimensional representations of somatic mutation profiles that hold useful information about the DNA of cancer cells will facilitate the use of such data in applications that will progress precision medicine. In this paper, we talk about the open problem of learning from somatic mutations, and present Flatsomatic: a solution that utilizes variational autoencoders (VAEs) to create latent representations of somatic profiles. The work done in this paper shows great potential for this method, with the VAE embeddings performing better than PCA for a clustering task, and performing equally well to the raw high dimensional data for a classification task. We believe the methods presented herein can be of great value in future research and in bringing data-driven models into precision oncology.