PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1611.01462

Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling

Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against one-hot targets, and each word is represented both as an input and as an output in isolation. This causes inefficiencies in learning both in terms of utilizing all of the information and in terms of the number of parameters needed to train. We introduce a novel theoretical framework that facilitates better learning in language modeling, and show that our framework leads to tying together the input embedding and the output projection matrices, greatly reducing the number of trainable variables. Our framework leads to state of the art performance on the Penn Treebank with a variety of network models.

arXiv:1703.05148

Random Forests and VGG-NET: An Algorithm for the ISIC 2017 Skin Lesion Classification Challenge

This manuscript briefly describes an algorithm developed for the ISIC 2017 Skin Lesion Classification Competition. In this task, participants are asked to complete two independent binary image classification tasks that involve three unique diagnoses of skin lesions (melanoma, nevus, and seborrheic keratosis). In the first binary classification task, participants are asked to distinguish between (a) melanoma and (b) nevus and seborrheic keratosis. In the second binary classification task, participants are asked to distinguish between (a) seborrheic keratosis and (b) nevus and melanoma. The other phases of the competition are not considered. Our proposed algorithm consists of three steps: preprocessing, classification using VGG-NET and Random Forests, and calculation of a final score.

arXiv:1703.04980

Classification of COPD with Multiple Instance Learning

Chronic obstructive pulmonary disease (COPD) is a lung disease where early detection benefits the survival rate. COPD can be quantified by classifying patches of computed tomography images, and combining patch labels into an overall diagnosis for the image. As labeled patches are often not available, image labels are propagated to the patches, incorrectly labeling healthy patches in COPD patients as being affected by the disease. We approach quantification of COPD from lung images as a multiple instance learning (MIL) problem, which is more suitable for such weakly labeled data. We investigate various MIL assumptions in the context of COPD and show that although a concept region with COPD-related disease patterns is present, considering the whole distribution of lung tissue patches improves the performance. The best method is based on averaging instances and obtains an AUC of 0.742, which is higher than the previously reported best of 0.713 on the same dataset. Using the full training set further increases performance to 0.776, which is significantly higher (DeLong test) than previous results.

arXiv:1703.04879

Sparse Named Entity Classification using Factorization Machines

Named entity classification is the task of classifying text-based elements into various categories, including places, names, dates, times, and monetary values. A bottleneck in named entity classification, however, is the data problem of sparseness, because new named entities continually emerge, making it rather difficult to maintain a dictionary for named entity classification. Thus, in this paper, we address the problem of named entity classification using matrix factorization to overcome the problem of feature sparsity. Experimental results show that our proposed model, with fewer features and a smaller size, achieves competitive accuracy to state-of-the-art models.

arXiv:1703.04823

Classification in biological networks with hypergraphlet kernels

Biological and cellular systems are often modeled as graphs in which vertices represent objects of interest (genes, proteins, drugs) and edges represent relational ties among these objects (binds-to, interacts-with, regulates). This approach has been highly successful owing to the theory, methodology and software that support analysis and learning on graphs. Graphs, however, often suffer from information loss when modeling physical systems due to their inability to accurately represent multiobject relationships. Hypergraphs, a generalization of graphs, provide a framework to mitigate information loss and unify disparate graph-based methodologies. In this paper, we present a hypergraph-based approach for modeling physical systems and formulate vertex classification, edge classification and link prediction problems on (hyper)graphs as instances of vertex classification on (extended, dual) hypergraphs in a semi-supervised setting. We introduce a novel kernel method on vertex- and edge-labeled (colored) hypergraphs for analysis and learning. The method is based on exact and inexact (via hypergraph edit distances) enumeration of small simple hypergraphs, referred to as hypergraphlets, rooted at a vertex of interest. We extensively evaluate this method and show its potential use in a positive-unlabeled setting to estimate the number of missing and false positive links in protein-protein interaction networks.

arXiv:1703.04819공식 코드 · Papers with Code

RECOD Titans at ISIC Challenge 2017

This extended abstract describes the participation of RECOD Titans in parts 1 and 3 of the ISIC Challenge 2017 "Skin Lesion Analysis Towards Melanoma Detection" (ISBI 2017). Although our team has a long experience with melanoma classification, the ISIC Challenge 2017 was the very first time we worked on skin-lesion segmentation. For part 1 (segmentation), our final submission used four of our models: two trained with all 2000 samples, without a validation split, for 250 and for 500 epochs respectively; and other two trained and validated with two different 1600/400 splits, for 220 epochs. Those four models, individually, achieved between 0.780 and 0.783 official validation scores. Our final submission averaged the output of those four models achieved a score of 0.793. For part 3 (classification), the submitted test run as well as our last official validation run were the result from a meta-model that assembled seven base deep-learning models: three based on Inception-V4 trained on our largest dataset; three based on Inception trained on our smallest dataset; and one based on ResNet-101 trained on our smaller dataset. The results of those component models were stacked in a meta-learning layer based on an SVM trained on the validation set of our largest dataset.

arXiv:1703.04818

Neural Graph Machines: Learning Neural Networks Using Graphs

Label propagation is a powerful and flexible semi-supervised learning technique on graphs. Neural networks, on the other hand, have proven track records in many supervised learning tasks. In this work, we propose a training framework with a graph-regularised objective, namely "Neural Graph Machines", that can combine the power of neural networks and label propagation. This work generalises previous literature on graph-augmented training of neural networks, enabling it to be applied to multiple neural architectures (Feed-forward NNs, CNNs and LSTM RNNs) and a wide range of graphs. The new objective allows the neural networks to harness both labeled and unlabeled data by: (a) allowing the network to train using labeled data as in the supervised setting, (b) biasing the network to learn similar hidden representations for neighboring nodes on a graph, in the same vein as label propagation. Such architectures with the proposed objective can be trained efficiently using stochastic gradient descent and scaled to large graphs, with a runtime that is linear in the number of edges. The proposed joint training approach convincingly outperforms many existing methods on a wide range of tasks (multi-label classification on social graphs, news categorization, document classification and semantic intent classification), with multiple forms of graph inputs (including graphs with and without node-level features) and using different types of neural networks.

arXiv:1703.04697

On the benefits of output sparsity for multi-label classification

The multi-label classification framework, where each observation can be associated with a set of labels, has generated a tremendous amount of attention over recent years. The modern multi-label problems are typically large-scale in terms of number of observations, features and labels, and the amount of labels can even be comparable with the amount of observations. In this context, different remedies have been proposed to overcome the curse of dimensionality. In this work, we aim at exploiting the output sparsity by introducing a new loss, called the sparse weighted Hamming loss. This proposed loss can be seen as a weighted version of classical ones, where active and inactive labels are weighted separately. Leveraging the influence of sparsity in the loss function, we provide improved generalization bounds for the empirical risk minimizer, a suitable property for large-scale problems. For this new loss, we derive rates of convergence linear in the underlying output-sparsity rather than linear in the number of labels. In practice, minimizing the associated risk can be performed efficiently by using convex surrogates and modern convex optimization algorithms. We provide experiments on various real-world datasets demonstrating the pertinence of our approach when compared to non-weighted techniques.

arXiv:1703.04559

Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features

The presence of certain clinical dermoscopic features within a skin lesion may indicate melanoma, and automatically detecting these features may lead to more quantitative and reproducible diagnoses. We reformulate the task of classifying clinical dermoscopic features within superpixels as a segmentation problem, and propose a fully convolutional neural network to detect clinical dermoscopic features from dermoscopy skin lesion images. Our neural network architecture uses interpolated feature maps from several intermediate network layers, and addresses imbalanced labels by minimizing a negative multi-label Dice-F$_1$ score, where the score is computed across the mini-batch for each label. Our approach ranked first place in the 2017 ISIC-ISBI Part 2: Dermoscopic Feature Classification Task challenge over both the provided validation and test datasets, achieving a 0.895% area under the receiver operator characteristic curve score. We show how simple baseline models can outrank state-of-the-art approaches when using the official metrics of the challenge, and propose to use a fuzzy Jaccard Index that ignores the empty set (i.e., masks devoid of positive pixels) when ranking models. Our results suggest that (i) the classification of clinical dermoscopic features can be effectively approached as a segmentation problem, and (ii) the current metrics used to rank models may not well capture the efficacy of the model. We plan to make our trained model and code publicly available.

arXiv:1703.04496

Comparison of echo state network output layer classification methods on noisy data

Echo state networks are a recently developed type of recurrent neural network where the internal layer is fixed with random weights, and only the output layer is trained on specific data. Echo state networks are increasingly being used to process spatiotemporal data in real-world settings, including speech recognition, event detection, and robot control. A strength of echo state networks is the simple method used to train the output layer - typically a collection of linear readout weights found using a least squares approach. Although straightforward to train and having a low computational cost to use, this method may not yield acceptable accuracy performance on noisy data. This study compares the performance of three echo state network output layer methods to perform classification on noisy data: using trained linear weights, using sparse trained linear weights, and using trained low-rank approximations of reservoir states. The methods are investigated experimentally on both synthetic and natural datasets. The experiments suggest that using regularized least squares to train linear output weights is superior on data with low noise, but using the low-rank approximations may significantly improve accuracy on datasets contaminated with higher noise levels.

arXiv:1703.04418

Improving LBP and its variants using anisotropic diffusion

The main purpose of this paper is to propose a new preprocessing step in order to improve local feature descriptors and texture classification. Preprocessing is implemented by using transformations which help highlight salient features that play a significant role in texture recognition. We evaluate and compare four different competing methods: three different anisotropic diffusion methods including the classical anisotropic Perona-Malik diffusion and two subsequent regularizations of it and the application of a Gaussian kernel, which is the classical multiscale approach in texture analysis. The combination of the transformed images and the original ones are analyzed. The results show that the use of the preprocessing step does lead to improved texture recognition.

arXiv:1703.04364

Deep Learning for Skin Lesion Classification

Melanoma, a malignant form of skin cancer is very threatening to life. Diagnosis of melanoma at an earlier stage is highly needed as it has a very high cure rate. Benign and malignant forms of skin cancer can be detected by analyzing the lesions present on the surface of the skin using dermoscopic images. In this work, an automated skin lesion detection system has been developed which learns the representation of the image using Google's pretrained CNN model known as Inception-v3 \cite{cnn}. After obtaining the representation vector for our input dermoscopic images we have trained two layer feed forward neural network to classify the images as malignant or benign. The system also classifies the images based on the cause of the cancer either due to melanocytic or non-melanocytic cells using a different neural network. These classification tasks are part of the challenge organized by International Skin Imaging Collaboration (ISIC) 2017. Our system learns to classify the images based on the model built using the training images given in the challenge and the experimental results were evaluated using validation and test sets. Our system has achieved an overall accuracy of 65.8\% for the validation set.

arXiv:1703.02180공식 코드 · Papers with Code

Sharing Residual Units Through Collective Tensor Factorization in Deep Neural Networks

Residual units are wildly used for alleviating optimization difficulties when building deep neural networks. However, the performance gain does not well compensate the model size increase, indicating low parameter efficiency in these residual units. In this work, we first revisit the residual function in several variations of residual units and demonstrate that these residual functions can actually be explained with a unified framework based on generalized block term decomposition. Then, based on the new explanation, we propose a new architecture, Collective Residual Unit (CRU), which enhances the parameter efficiency of deep neural networks through collective tensor factorization. CRU enables knowledge sharing across different residual units using shared factors. Experimental results show that our proposed CRU Network demonstrates outstanding parameter efficiency, achieving comparable classification performance to ResNet-200 with the model size of ResNet-50. By building a deeper network using CRU, we can achieve state-of-the-art single model classification accuracy on ImageNet-1k and Places365-Standard benchmark datasets. (Code and trained models are available on GitHub)

arXiv:1702.07025

Convolutional Neural Network Committees for Melanoma Classification with Classical And Expert Knowledge Based Image Transforms Data Augmentation

Skin cancer is a major public health problem, as is the most common type of cancer and represents more than half of cancer diagnoses worldwide. Early detection influences the outcome of the disease and motivates our work. We investigate the composition of CNN committees and data augmentation for the the ISBI 2017 Melanoma Classification Challenge (named Skin Lesion Analysis towards Melanoma Detection) facing the peculiarities of dealing with such a small, unbalanced, biological database. For that, we explore committees of Convolutional Neural Networks trained over the ISBI challenge training dataset artificially augmented by both classical image processing transforms and image warping guided by specialist knowledge about the lesion axis and improve the final classifier invariance to common melanoma variations.

arXiv:1610.02242공식 코드 · Papers with Code

Temporal Ensembling for Semi-Supervised Learning

In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a consensus prediction of the unknown labels using the outputs of the network-in-training on different epochs, and most importantly, under different regularization and input augmentation conditions. This ensemble prediction can be expected to be a better predictor for the unknown labels than the output of the network at the most recent training epoch, and can thus be used as a target for training. Using our method, we set new records for two standard semi-supervised learning benchmarks, reducing the (non-augmented) classification error rate from 18.44% to 7.05% in SVHN with 500 labels and from 18.63% to 16.55% in CIFAR-10 with 4000 labels, and further to 5.12% and 12.16% by enabling the standard augmentations. We additionally obtain a clear improvement in CIFAR-100 classification accuracy by using random images from the Tiny Images dataset as unlabeled extra inputs during training. Finally, we demonstrate good tolerance to incorrect labels.

arXiv:1703.05913

Computer Aided Detection of Anemia-like Pallor

Paleness or pallor is a manifestation of blood loss or low hemoglobin concentrations in the human blood that can be caused by pathologies such as anemia. This work presents the first automated screening system that utilizes pallor site images, segments, and extracts color and intensity-based features for multi-class classification of patients with high pallor due to anemia-like pathologies, normal patients and patients with other abnormalities. This work analyzes the pallor sites of conjunctiva and tongue for anemia screening purposes. First, for the eye pallor site images, the sclera and conjunctiva regions are automatically segmented for regions of interest. Similarly, for the tongue pallor site images, the inner and outer tongue regions are segmented. Then, color-plane based feature extraction is performed followed by machine learning algorithms for feature reduction and image level classification for anemia. In this work, a suite of classification algorithms image-level classifications for normal (class 0), pallor (class 1) and other abnormalities (class 2). The proposed method achieves 86% accuracy, 85% precision and 67% recall in eye pallor site images and 98.2% accuracy and precision with 100% recall in tongue pallor site images for classification of images with pallor. The proposed pallor screening system can be further fine-tuned to detect the severity of anemia-like pathologies using controlled set of local images that can then be used for future benchmarking purposes.

arXiv:1703.05841

Adaptivity to Noise Parameters in Nonparametric Active Learning

This work addresses various open questions in the theory of active learning for nonparametric classification. Our contributions are both statistical and algorithmic: -We establish new minimax-rates for active learning under common \textit{noise conditions}. These rates display interesting transitions -- due to the interaction between noise \textit{smoothness and margin} -- not present in the passive setting. Some such transitions were previously conjectured, but remained unconfirmed. -We present a generic algorithmic strategy for adaptivity to unknown noise smoothness and margin; our strategy achieves optimal rates in many general situations; furthermore, unlike in previous work, we avoid the need for \textit{adaptive confidence sets}, resulting in strictly milder distributional requirements.

arXiv:1703.05571

From visual words to a visual grammar: using language modelling for image classification

The Bag--of--Visual--Words (BoVW) is a visual description technique that aims at shortening the semantic gap by partitioning a low--level feature space into regions of the feature space that potentially correspond to visual concepts and by giving more value to this space. In this paper we present a conceptual analysis of three major properties of language grammar and how they can be adapted to the computer vision and image understanding domain based on the bag of visual words paradigm. Evaluation of the visual grammar shows that a positive impact on classification accuracy and/or descriptor size is obtained when the technique are applied when the proposed techniques are applied.

arXiv:1703.05537

Shift Aggregate Extract Networks

We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in kernel methods, enabling nested part-of-part relations. Unlike recursive neural networks, which unroll a template on input graphs directly, we unroll a neural network template over the decomposition hierarchy, allowing us to deal with the high degree variability that typically characterize social network graphs. Deep hierarchical decompositions are also amenable to domain compression, a technique that reduces both space and time complexity by exploiting symmetries. We show empirically that our approach is able to outperform current state-of-the-art graph classification methods on large social network datasets, while at the same time being competitive on small chemobiological benchmark datasets.

arXiv:1703.05530

Convolutional Neural Network on Three Orthogonal Planes for Dynamic Texture Classification

Dynamic Textures (DTs) are sequences of images of moving scenes that exhibit certain stationarity properties in time such as smoke, vegetation and fire. The analysis of DT is important for recognition, segmentation, synthesis or retrieval for a range of applications including surveillance, medical imaging and remote sensing. Deep learning methods have shown impressive results and are now the new state of the art for a wide range of computer vision tasks including image and video recognition and segmentation. In particular, Convolutional Neural Networks (CNNs) have recently proven to be well suited for texture analysis with a design similar to a filter bank approach. In this paper, we develop a new approach to DT analysis based on a CNN method applied on three orthogonal planes x y , xt and y t . We train CNNs on spatial frames and temporal slices extracted from the DT sequences and combine their outputs to obtain a competitive DT classifier. Our results on a wide range of commonly used DT classification benchmark datasets prove the robustness of our approach. Significant improvement of the state of the art is shown on the larger datasets.