PyTorchKR Papers

최신 논문

총 12,307편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1911.07320

Sparse $\ell_1$ and $\ell_2$ Center Classifiers

The nearest-centroid classifier is a simple linear-time classifier based on computing the centroids of the data classes in the training phase, and then assigning a new datum to the class corresponding to its nearest centroid. Thanks to its very low computational cost, the nearest-centroid classifier is still widely used in machine learning, despite the development of many other more sophisticated classification methods. In this paper, we propose two sparse variants of the nearest-centroid classifier, based respectively on $\ell_1$ and $\ell_2$ distance criteria. The proposed sparse classifiers perform simultaneous classification and feature selection, by detecting the features that are most relevant for the classification purpose. We show that training of the proposed sparse models, with both distance criteria, can be performed exactly (i.e., the globally optimal set of features is selected) and at a quasi-linear computational cost. The experimental results show that the proposed methods are competitive in accuracy with state-of-the-art feature selection techniques, while having a significantly lower computational cost.

arXiv:1911.07257

Learning with Hierarchical Complement Objective

Label hierarchies widely exist in many vision-related problems, ranging from explicit label hierarchies existed in image classification to latent label hierarchies existed in semantic segmentation. Nevertheless, state-of-the-art methods often deploy cross-entropy loss that implicitly assumes class labels to be exclusive and thus independence from each other. Motivated by the fact that classes from the same parental category usually share certain similarity, we design a new training diagram called Hierarchical Complement Objective Training (HCOT) that leverages the information from label hierarchy. HCOT maximizes the probability of the ground truth class, and at the same time, neutralizes the probabilities of rest of the classes in a hierarchical fashion, making the model take advantage of the label hierarchy explicitly. The proposed HCOT is evaluated on both image classification and semantic segmentation tasks. Experimental results confirm that HCOT outperforms state-of-the-art models in CIFAR-100, ImageNet-2012, and PASCAL-Context. The study further demonstrates that HCOT can be applied on tasks with latent label hierarchies, which is a common characteristic in many machine learning tasks.

arXiv:1911.07241공식 코드 · Papers with Code

SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking

By decomposing the visual tracking task into two subproblems as classification for pixel category and regression for object bounding box at this pixel, we propose a novel fully convolutional Siamese network to solve visual tracking end-to-end in a per-pixel manner. The proposed framework SiamCAR consists of two simple subnetworks: one Siamese subnetwork for feature extraction and one classification-regression subnetwork for bounding box prediction. Our framework takes ResNet-50 as backbone. Different from state-of-the-art trackers like Siamese-RPN, SiamRPN++ and SPM, which are based on region proposal, the proposed framework is both proposal and anchor free. Consequently, we are able to avoid the tricky hyper-parameter tuning of anchors and reduce human intervention. The proposed framework is simple, neat and effective. Extensive experiments and comparisons with state-of-the-art trackers are conducted on many challenging benchmarks like GOT-10K, LaSOT, UAV123 and OTB-50. Without bells and whistles, our SiamCAR achieves the leading performance with a considerable real-time speed.

arXiv:1911.07223

Deep Learning versus Traditional Classifiers on Vietnamese Students' Feedback Corpus

Student's feedback is an important source of collecting students' opinions to improve the quality of training activities. Implementing sentiment analysis into student feedback data, we can determine sentiments polarities which express all problems in the institution since changes necessary will be applied to improve the quality of teaching and learning. This study focused on machine learning and natural language processing techniques (NaiveBayes, Maximum Entropy, Long Short-Term Memory, Bi-Directional Long Short-Term Memory) on the VietnameseStudents' Feedback Corpus collected from a university. The final results were compared and evaluated to find the most effective model based on different evaluation criteria. The experimental results show that the Bi-Directional LongShort-Term Memory algorithm outperformed than three other algorithms in terms of the F1-score measurement with 92.0% on the sentiment classification task and 89.6% on the topic classification task. In addition, we developed a sentiment analysis application analyzing student feedback. The application will help the institution to recognize students' opinions about a problem and identify shortcomings that still exist. With the use of this application, the institution can propose an appropriate method to improve the quality of training activities in the future.

arXiv:1911.06996공식 코드 · Papers with Code

Selective sampling for accelerating training of deep neural networks

We present a selective sampling method designed to accelerate the training of deep neural networks. To this end, we introduce a novel measurement, the minimal margin score (MMS), which measures the minimal amount of displacement an input should take until its predicted classification is switched. For multi-class linear classification, the MMS measure is a natural generalization of the margin-based selection criterion, which was thoroughly studied in the binary classification setting. In addition, the MMS measure provides an interesting insight into the progress of the training process and can be useful for designing and monitoring new training regimes. Empirically we demonstrate a substantial acceleration when training commonly used deep neural network architectures for popular image classification tasks. The efficiency of our method is compared against the standard training procedures, and against commonly used selective sampling alternatives: Hard negative mining selection, and Entropy-based selection. Finally, we demonstrate an additional speedup when we adopt a more aggressive learning drop regime while using the MMS selective sampling method.

arXiv:1911.06993

Automatic Design of CNNs via Differentiable Neural Architecture Search for PolSAR Image Classification

Convolutional neural networks (CNNs) have shown good performance in polarimetric synthetic aperture radar (PolSAR) image classification due to the automation of feature engineering. Excellent hand-crafted architectures of CNNs incorporated the wisdom of human experts, which is an important reason for CNN's success. However, the design of the architectures is a difficult problem, which needs a lot of professional knowledge as well as computational resources. Moreover, the architecture designed by hand might be suboptimal, because it is only one of thousands of unobserved but objective existed paths. Considering that the success of deep learning is largely due to its automation of the feature engineering process, how to design automatic architecture searching methods to replace the hand-crafted ones is an interesting topic. In this paper, we explore the application of neural architecture search (NAS) in PolSAR area for the first time. Different from the utilization of existing NAS methods, we propose a differentiable architecture search (DAS) method which is customized for PolSAR classification. The proposed DAS is equipped with a PolSAR tailored search space and an improved one-shot search strategy. By DAS, the weights parameters and architecture parameters (corresponds to the hyperparameters but not the topologies) can be optimized by stochastic gradient descent method during the training. The optimized architecture parameters should be transformed into corresponding CNN architecture and re-train to achieve high-precision PolSAR classification. In addition, complex-valued DAS is developed to take into account the characteristics of PolSAR images so as to further improve the performance. Experiments on three PolSAR benchmark datasets show that the CNNs obtained by searching have better classification performance than the hand-crafted ones.

arXiv:1911.07757공식 코드 · Papers with Code

Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention

Satellite image time series, bolstered by their growing availability, are at the forefront of an extensive effort towards automated Earth monitoring by international institutions. In particular, large-scale control of agricultural parcels is an issue of major political and economic importance. In this regard, hybrid convolutional-recurrent neural architectures have shown promising results for the automated classification of satellite image time series.We propose an alternative approach in which the convolutional layers are advantageously replaced with encoders operating on unordered sets of pixels to exploit the typically coarse resolution of publicly available satellite images. We also propose to extract temporal features using a bespoke neural architecture based on self-attention instead of recurrent networks. We demonstrate experimentally that our method not only outperforms previous state-of-the-art approaches in terms of precision, but also significantly decreases processing time and memory requirements. Lastly, we release a large open-access annotated dataset as a benchmark for future work on satellite image time series.

arXiv:1911.07683

Radar Emitter Classification with Attribute-specific Recurrent Neural Networks

Radar pulse streams exhibit increasingly complex temporal patterns and can no longer rely on a purely value-based analysis of the pulse attributes for the purpose of emitter classification. In this paper, we employ Recurrent Neural Networks (RNNs) to efficiently model and exploit the temporal dependencies present inside pulse streams. With the purpose of enhancing the network prediction capability, we introduce two novel techniques: a per-sequence normalization, able to mine the useful temporal patterns; and attribute-specific RNN processing, capable of processing the extracted information effectively. The new techniques are evaluated with an ablation study and the proposed solution is compared to previous Deep Learning (DL) approaches. Finally, a comparative study on the robustness of the same approaches is conducted and its results are presented.

arXiv:1911.07605

Commit2Vec: Learning Distributed Representations of Code Changes

Deep learning methods, which have found successful applications in fields like image classification and natural language processing, have recently been applied to source code analysis too, due to the enormous amount of freely available source code (e.g., from open-source software repositories). In this work, we elaborate upon a state-of-the-art approach to the representation of source code that uses information about its syntactic structure, and we adapt it to represent source changes (i.e., commits). We use this representation to classify security-relevant commits. Because our method uses transfer learning (that is, we train a network on a "pretext task" for which abundant labeled data is available, and then we use such network for the target task of commit classification, for which fewer labeled instances are available), we studied the impact of pre-training the network using two different pretext tasks versus a randomly initialized model. Our results indicate that representations that leverage the structural information obtained through code syntax outperform token-based representations. Furthermore, the performance metrics obtained when pre-training on a loosely related pretext task with a very large dataset ($>10^6$ samples) were surpassed when pretraining on a smaller dataset ($>10^4$ samples) but for a pretext task that is more closely related to the target task.

arXiv:1911.07518공식 코드 · Papers with Code

Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features

Multi-task learning (MTL) has received considerable attention, and numerous deep learning applications benefit from MTL with multiple objectives. However, constructing multiple related tasks is difficult, and sometimes only a single task is available for training in a dataset. To tackle this problem, we explored the idea of using unsupervised clustering to construct a variety of auxiliary tasks from unlabeled data or existing labeled data. We found that some of these newly constructed tasks could exhibit semantic meanings corresponding to certain human-specific attributes, but some were non-ideal. In order to effectively reduce the impact of non-ideal auxiliary tasks on the main task, we further proposed a novel meta-learning-based multi-task learning approach, which trained the shared hidden layers on auxiliary tasks, while the meta-optimization objective was to minimize the loss on the main task, ensuring that the optimizing direction led to an improvement on the main task. Experimental results across five image datasets demonstrated that the proposed method significantly outperformed existing single task learning, semi-supervised learning, and some data augmentation methods, including an improvement of more than 9% on the Omniglot dataset.

arXiv:1911.07511

Benchmarking time series classification -- Functional data vs machine learning approaches

Time series classification problems have drawn increasing attention in the machine learning and statistical community. Closely related is the field of functional data analysis (FDA): it refers to the range of problems that deal with the analysis of data that is continuously indexed over some domain. While often employing different methods, both fields strive to answer similar questions, a common example being classification or regression problems with functional covariates. We study methods from functional data analysis, such as functional generalized additive models, as well as functionality to concatenate (functional-) feature extraction or basis representations with traditional machine learning algorithms like support vector machines or classification trees. In order to assess the methods and implementations, we run a benchmark on a wide variety of representative (time series) data sets, with in-depth analysis of empirical results, and strive to provide a reference ranking for which method(s) to use for non-expert practitioners. Additionally, we provide a software framework in R for functional data analysis for supervised learning, including machine learning and more linear approaches from statistics. This allows convenient access, and in connection with the machine-learning toolbox mlr, those methods can now also be tuned and benchmarked.

arXiv:1911.07344

ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding

The task of fine-grained visual classification (FGVC) deals with classification problems that display a small inter-class variance such as distinguishing between different bird species or car models. State-of-the-art approaches typically tackle this problem by integrating an elaborate attention mechanism or (part-) localization method into a standard convolutional neural network (CNN). Also in this work the aim is to enhance the performance of a backbone CNN such as ResNet by including three efficient and lightweight components specifically designed for FGVC. This is achieved by using global k-max pooling, a discriminative embedding layer trained by optimizing class means and an efficient bounding box estimator that only needs class labels for training. The resulting model achieves new best state-of-the-art recognition accuracies on the Stanford cars and FGVC-Aircraft datasets.

arXiv:1911.07819

Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies

More than 200 generic drugs approved by the U.S. Food and Drug Administration for non-cancer indications have shown promise for treating cancer. Due to their long history of safe patient use, low cost, and widespread availability, repurposing of generic drugs represents a major opportunity to rapidly improve outcomes for cancer patients and reduce healthcare costs worldwide. Evidence on the efficacy of non-cancer generic drugs being tested for cancer exists in scientific publications, but trying to manually identify and extract such evidence is intractable. In this paper, we introduce a system to automate this evidence extraction from PubMed abstracts. Our primary contribution is to define the natural language processing pipeline required to obtain such evidence, comprising the following modules: querying, filtering, cancer type entity extraction, therapeutic association classification, and study type classification. Using the subject matter expertise on our team, we create our own datasets for these specialized domain-specific tasks. We obtain promising performance in each of the modules by utilizing modern language modeling techniques and plan to treat them as baseline approaches for future improvement of individual components.

arXiv:1911.07817

Skin Lesion Classification Using Deep Neural Network

This paper reports the methods and techniques we have developed for classify dermoscopic images (task 1) of the ISIC 2019 challenge dataset for skin lesion classification, our approach aims to use ensemble deep neural network with some powerful techniques to deal with unbalance data sets as its the main problem for this challenge in a move to increase the performance of CNNs model.

arXiv:1911.06777

TinyCNN: A Tiny Modular CNN Accelerator for Embedded FPGA

In recent years, Convolutional Neural Network (CNN) based methods have achieved great success in a large number of applications and have been among the most powerful and widely used techniques in computer vision. However, CNN-based methods are computational-intensive and resource-consuming, and thus are hard to be integrated into embedded systems such as smart phones, smart glasses, and robots. FPGA is one of the most promising platforms for accelerating CNN, but the limited on-chip memory size limit the performance of FPGA accelerator for CNN. In this paper, we propose a framework for designing CNN accelerator on embedded FPGA for image classification. The proposed framework provides a tool for FPGA resource-aware design space exploration of CNNs and automatically generates the hardware description of the CNN to be programmed on a target FPGA. The framework consists of three main backends; software, hardware generation, and simulation/precision adjustment. The software backend serves as an API to the designer to design the CNN and train it according to the hardware resources that are available. Using the CNN model, hardware backend generates the necessary hardware components and integrates them to generate the hardware description of the CNN. Finaly, Simulation/precision adjustment backend adjusts the inter-layer precision units to minimize the classification error. We used 16-bit fixed-point data in a CNN accelerator (FPGA) and compared it to the exactly similar software version running on an ARM processor (32-bit floating point data). We encounter about 3% accuracy loss in classification of the accelerated (FPGA) version. In return, we got up to 15.75x speedup by classifying with the accelerated version on the FPGA.

arXiv:1911.06687

Deep radiomic features from MRI scans predict survival outcome of recurrent glioblastoma

This paper proposes to use deep radiomic features (DRFs) from a convolutional neural network (CNN) to model fine-grained texture signatures in the radiomic analysis of recurrent glioblastoma (rGBM). We use DRFs to predict survival of rGBM patients with preoperative T1-weighted post-contrast MR images (n=100). DRFs are extracted from regions of interest labelled by a radiation oncologist and used to compare between short-term and long-term survival patient groups. Random forest (RF) classification is employed to predict survival outcome (i.e., short or long survival), as well as to identify highly group-informative descriptors. Classification using DRFs results in an area under the ROC curve (AUC) of 89.15% (p<0.01) in predicting rGBM patient survival, compared to 78.07% (p<0.01) when using standard radiomic features (SRF). These results indicate the potential of DRFs as a prognostic marker for patients with rGBM.

arXiv:1911.06673

Bootstrapping NLU Models with Multi-task Learning

Bootstrapping natural language understanding (NLU) systems with minimal training data is a fundamental challenge of extending digital assistants like Alexa and Siri to a new language. A common approach that is adapted in digital assistants when responding to a user query is to process the input in a pipeline manner where the first task is to predict the domain, followed by the inference of intent and slots. However, this cascaded approach instigates error propagation and prevents information sharing among these tasks. Further, the use of words as the atomic units of meaning as done in many studies might lead to coverage problems for morphologically rich languages such as German and French when data is limited. We address these issues by introducing a character-level unified neural architecture for joint modeling of the domain, intent, and slot classification. We compose word-embeddings from characters and jointly optimize all classification tasks via multi-task learning. In our results, we show that the proposed architecture is an optimal choice for bootstrapping NLU systems in low-resource settings thus saving time, cost and human effort.

arXiv:1911.06502공식 코드 · Papers with Code

Simple iterative method for generating targeted universal adversarial perturbations

Deep neural networks (DNNs) are vulnerable to adversarial attacks. In particular, a single perturbation known as the universal adversarial perturbation (UAP) can foil most classification tasks conducted by DNNs. Thus, different methods for generating UAPs are required to fully evaluate the vulnerability of DNNs. A realistic evaluation would be with cases that consider targeted attacks; wherein the generated UAP causes DNN to classify an input into a specific class. However, the development of UAPs for targeted attacks has largely fallen behind that of UAPs for non-targeted attacks. Therefore, we propose a simple iterative method to generate UAPs for targeted attacks. Our method combines the simple iterative method for generating non-targeted UAPs and the fast gradient sign method for generating a targeted adversarial perturbation for an input. We applied the proposed method to state-of-the-art DNN models for image classification and proved the existence of almost imperceptible UAPs for targeted attacks; further, we demonstrated that such UAPs are easily generatable.

arXiv:1911.06455공식 코드 · Papers with Code

Graph Transformer Networks

Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. In this paper, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which involve identifying useful connections between unconnected nodes on the original graph, while learning effective node representation on the new graphs in an end-to-end fashion. Graph Transformer layer, a core layer of GTNs, learns a soft selection of edge types and composite relations for generating useful multi-hop connections so-called meta-paths. Our experiments show that GTNs learn new graph structures, based on data and tasks without domain knowledge, and yield powerful node representation via convolution on the new graphs. Without domain-specific graph preprocessing, GTNs achieved the best performance in all three benchmark node classification tasks against the state-of-the-art methods that require pre-defined meta-paths from domain knowledge.

arXiv:1911.06395

Contrast Phase Classification with a Generative Adversarial Network

Dynamic contrast enhanced computed tomography (CT) is an imaging technique that provides critical information on the relationship of vascular structure and dynamics in the context of underlying anatomy. A key challenge for image processing with contrast enhanced CT is that phase discrepancies are latent in different tissues due to contrast protocols, vascular dynamics, and metabolism variance. Previous studies with deep learning frameworks have been proposed for classifying contrast enhancement with networks inspired by computer vision. Here, we revisit the challenge in the context of whole abdomen contrast enhanced CTs. To capture and compensate for the complex contrast changes, we propose a novel discriminator in the form of a multi-domain disentangled representation learning network. The goal of this network is to learn an intermediate representation that separates contrast enhancement from anatomy and enables classification of images with varying contrast time. Briefly, our unpaired contrast disentangling GAN(CD-GAN) Discriminator follows the ResNet architecture to classify a CT scan from different enhancement phases. To evaluate the approach, we trained the enhancement phase classifier on 21060 slices from two clinical cohorts of 230 subjects. Testing was performed on 9100 slices from 30 independent subjects who had been imaged with CT scans from all contrast phases. Performance was quantified in terms of the multi-class normalized confusion matrix. The proposed network significantly improved correspondence over baseline UNet, ResNet50 and StarGAN performance of accuracy scores 0.54. 0.55, 0.62 and 0.91, respectively. The proposed discriminator from the disentangled network presents a promising technique that may allow deeper modeling of dynamic imaging against patient specific anatomies.