PyTorchKR Papers

최신 논문

총 1,314편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1707.07465

Building Graph Representations of Deep Vector Embeddings

Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network representations are implemented within vector embedding spaces, which enables the use of traditional machine learning algorithms on top of them. In this short paper we propose the construction of a graph embedding space instead, introducing a methodology to transform the knowledge coded within a deep convolutional network into a topological space (i.e. a network). We outline how such graph can hold data instances, data features, relations between instances and features, and relations among features. Finally, we introduce some preliminary experiments to illustrate how the resultant graph embedding space can be exploited through graph analytics algorithms.

arXiv:1708.04366

Deep Edge-Aware Saliency Detection

There has been profound progress in visual saliency thanks to the deep learning architectures, however, there still exist three major challenges that hinder the detection performance for scenes with complex compositions, multiple salient objects, and salient objects of diverse scales. In particular, output maps of the existing methods remain low in spatial resolution causing blurred edges due to the stride and pooling operations, networks often neglect descriptive statistical and handcrafted priors that have potential to complement saliency detection results, and deep features at different layers stay mainly desolate waiting to be effectively fused to handle multi-scale salient objects. In this paper, we tackle these issues by a new fully convolutional neural network that jointly learns salient edges and saliency labels in an end-to-end fashion. Our framework first employs convolutional layers that reformulate the detection task as a dense labeling problem, then integrates handcrafted saliency features in a hierarchical manner into lower and higher levels of the deep network to leverage available information for multi-scale response, and finally refines the saliency map through dilated convolutions by imposing context. In this way, the salient edge priors are efficiently incorporated and the output resolution is significantly improved while keeping the memory requirements low, leading to cleaner and sharper object boundaries. Extensive experimental analyses on ten benchmarks demonstrate that our framework achieves consistently superior performance and attains robustness for complex scenes in comparison to the very recent state-of-the-art approaches.

arXiv:1708.09321

Adversarial nets with perceptual losses for text-to-image synthesis

Recent approaches in generative adversarial networks (GANs) can automatically synthesize realistic images from descriptive text. Despite the overall fair quality, the generated images often expose visible flaws that lack structural definition for an object of interest. In this paper, we aim to extend state of the art for GAN-based text-to-image synthesis by improving perceptual quality of generated images. Differentiated from previous work, our synthetic image generator optimizes on perceptual loss functions that measure pixel, feature activation, and texture differences against a natural image. We present visually more compelling synthetic images of birds and flowers generated from text descriptions in comparison to some of the most prominent existing work.

arXiv:1609.04117공식 코드 · Papers with Code

Network learning via multi-agent inverse transportation problems

Despite the ubiquity of transportation data, methods to infer the state parameters of a network either ignore sensitivity of route decisions, require route enumeration for parameterizing descriptive models of route selection, or require complex bilevel models of route assignment behavior. These limitations prevent modelers from fully exploiting ubiquitous data in monitoring transportation networks. Inverse optimization methods that capture network route choice behavior can address this gap, but they are designed to take observations of the same model to learn the parameters of that model, which is statistically inefficient (e.g. requires estimating population route and link flows). New inverse optimization models and supporting algorithms are proposed to learn the parameters of heterogeneous travelers' route behavior to infer shared network state parameters (e.g. link capacity dual prices). The inferred values are consistent with observations of each agent's optimization behavior. We prove that the method can obtain unique dual prices for a network shared by these agents in polynomial time. Four experiments are conducted. The first one, conducted on a 4-node network, verifies the methodology to obtain heterogeneous link cost parameters even when multinomial or mixed logit models would not be meaningfully estimated. The second is a parameter recovery test on the Nguyen-Dupuis network that shows that unique latent link capacity dual prices can be inferred using the proposed method. The third test on the same network demonstrates how a monitoring system in an online learning environment can be designed using this method. The last test demonstrates this learning on real data obtained from a freeway network in Queens, New York, using only real-time Google Maps queries.

arXiv:1709.04857

A New Semantic Theory of Natural Language

Formal Semantics and Distributional Semantics are two important semantic frameworks in Natural Language Processing (NLP). Cognitive Semantics belongs to the movement of Cognitive Linguistics, which is based on contemporary cognitive science. Each framework could deal with some meaning phenomena, but none of them fulfills all requirements proposed by applications. A unified semantic theory characterizing all important language phenomena has both theoretical and practical significance; however, although many attempts have been made in recent years, no existing theory has achieved this goal yet. This article introduces a new semantic theory that has the potential to characterize most of the important meaning phenomena of natural language and to fulfill most of the necessary requirements for philosophical analysis and for NLP applications. The theory is based on a unified representation of information, and constructs a kind of mathematical model called cognitive model to interpret natural language expressions in a compositional manner. It accepts the empirical assumption of Cognitive Semantics, and overcomes most shortcomings of Formal Semantics and of Distributional Semantics. The theory, however, is not a simple combination of existing theories, but an extensive generalization of classic logic and Formal Semantics. It inherits nearly all advantages of Formal Semantics, and also provides descriptive contents for objects and events as fine-gram as possible, descriptive contents which represent the results of human cognition.

arXiv:1709.04549

Ignoring Distractors in the Absence of Labels: Optimal Linear Projection to Remove False Positives During Anomaly Detection

In the anomaly detection setting, the native feature embedding can be a crucial source of bias. We present a technique, Feature Omission using Context in Unsupervised Settings (FOCUS) to learn a feature mapping that is invariant to changes exemplified in training sets while retaining as much descriptive power as possible. While this method could apply to many unsupervised settings, we focus on applications in anomaly detection, where little task-labeled data is available. Our algorithm requires only non-anomalous sets of data, and does not require that the contexts in the training sets match the context of the test set. By maximizing within-set variance and minimizing between-set variance, we are able to identify and remove distracting features while retaining fidelity to the descriptiveness needed at test time. In the linear case, our formulation reduces to a generalized eigenvalue problem that can be solved quickly and applied to test sets outside the context of the training sets. This technique allows us to align technical definitions of anomaly detection with human definitions through appropriate mappings of the feature space. We demonstrate that this method is able to remove uninformative parts of the feature space for the anomaly detection setting.

arXiv:1709.04491

Method for Aspect-Based Sentiment Annotation Using Rhetorical Analysis

This paper fills a gap in aspect-based sentiment analysis and aims to present a new method for preparing and analysing texts concerning opinion and generating user-friendly descriptive reports in natural language. We present a comprehensive set of techniques derived from Rhetorical Structure Theory and sentiment analysis to extract aspects from textual opinions and then build an abstractive summary of a set of opinions. Moreover, we propose aspect-aspect graphs to evaluate the importance of aspects and to filter out unimportant ones from the summary. Additionally, the paper presents a prototype solution of data flow with interesting and valuable results. The proposed method's results proved the high accuracy of aspect detection when applied to the gold standard dataset.

arXiv:1709.05379

Road Friction Estimation for Connected Vehicles using Supervised Machine Learning

In this paper, the problem of road friction prediction from a fleet of connected vehicles is investigated. A framework is proposed to predict the road friction level using both historical friction data from the connected cars and data from weather stations, and comparative results from different methods are presented. The problem is formulated as a classification task where the available data is used to train three machine learning models including logistic regression, support vector machine, and neural networks to predict the friction class (slippery or non-slippery) in the future for specific road segments. In addition to the friction values, which are measured by moving vehicles, additional parameters such as humidity, temperature, and rainfall are used to obtain a set of descriptive feature vectors as input to the classification methods. The proposed prediction models are evaluated for different prediction horizons (0 to 120 minutes in the future) where the evaluation shows that the neural networks method leads to more stable results in different conditions.

arXiv:1604.05800

A Deep Neural Network for Chinese Zero Pronoun Resolution

Existing approaches for Chinese zero pronoun resolution overlook semantic information. This is because zero pronouns have no descriptive information, which results in difficulty in explicitly capturing their semantic similarities with antecedents. Moreover, when dealing with candidate antecedents, traditional systems simply take advantage of the local information of a single candidate antecedent while failing to consider the underlying information provided by the other candidates from a global perspective. To address these weaknesses, we propose a novel zero pronoun-specific neural network, which is capable of representing zero pronouns by utilizing the contextual information at the semantic level. In addition, when dealing with candidate antecedents, a two-level candidate encoder is employed to explicitly capture both the local and global information of candidate antecedents. We conduct experiments on the Chinese portion of the OntoNotes 5.0 corpus. Experimental results show that our approach substantially outperforms the state-of-the-art method in various experimental settings.

arXiv:1710.00453

Visual Reasoning with Natural Language

Natural language provides a widely accessible and expressive interface for robotic agents. To understand language in complex environments, agents must reason about the full range of language inputs and their correspondence to the world. Such reasoning over language and vision is an open problem that is receiving increasing attention. While existing data sets focus on visual diversity, they do not display the full range of natural language expressions, such as counting, set reasoning, and comparisons. We propose a simple task for natural language visual reasoning, where images are paired with descriptive statements. The task is to predict if a statement is true for the given scene. This abstract describes our existing synthetic images corpus and our current work on collecting real vision data.

arXiv:1710.05221

An Adaptive Framework for Missing Depth Inference Using Joint Bilateral Filter

Depth imaging has largely focused on sensor and intrinsics properties. However, the accuracy of acquire pixel is largely dependent on the capture. We propose a new depth estimation and approximation algorithm which takes an arbitrary 3D point cloud as input, with potentially complex geometric structures, and generates automatically a bounding box which is used to clamp the 3D distribution into a valid range. We then infer the desired compact geometric network from complex 3D geometries by using a series of adaptive joint bilateral filters. Our approach leverages these input depth in the construction of a compact descriptive adaptive filter framework. The built system that allows a user to control the result of capture depth map to fit the target geometry. In addition, it is desirable to visualize structurally problematic areas of the depth data in a dynamic environment. To provide this feature, we investigate a fast update algorithm for the fragility of each pixel's corresponding 3D point using machine learning. We present a new for of feature vector analysis and demonstrate the effectiveness in the dataset. In our experiment, we demonstrate the practicality and benefits of our proposed method by computing accurate solutions captured depth map from different types of sensors and shows better results than existing methods.

arXiv:1710.06231

3D Object Discovery and Modeling Using Single RGB-D Images Containing Multiple Object Instances

Unsupervised object modeling is important in robotics, especially for handling a large set of objects. We present a method for unsupervised 3D object discovery, reconstruction, and localization that exploits multiple instances of an identical object contained in a single RGB-D image. The proposed method does not rely on segmentation, scene knowledge, or user input, and thus is easily scalable. Our method aims to find recurrent patterns in a single RGB-D image by utilizing appearance and geometry of the salient regions. We extract keypoints and match them in pairs based on their descriptors. We then generate triplets of the keypoints matching with each other using several geometric criteria to minimize false matches. The relative poses of the matched triplets are computed and clustered to discover sets of triplet pairs with similar relative poses. Triplets belonging to the same set are likely to belong to the same object and are used to construct an initial object model. Detection of remaining instances with the initial object model using RANSAC allows to further expand and refine the model. The automatically generated object models are both compact and descriptive. We show quantitative and qualitative results on RGB-D images with various objects including some from the Amazon Picking Challenge. We also demonstrate the use of our method in an object picking scenario with a robotic arm.

arXiv:1705.03572

Discovery Radiomics via Evolutionary Deep Radiomic Sequencer Discovery for Pathologically-Proven Lung Cancer Detection

While lung cancer is the second most diagnosed form of cancer in men and women, a sufficiently early diagnosis can be pivotal in patient survival rates. Imaging-based, or radiomics-driven, detection methods have been developed to aid diagnosticians, but largely rely on hand-crafted features which may not fully encapsulate the differences between cancerous and healthy tissue. Recently, the concept of discovery radiomics was introduced, where custom abstract features are discovered from readily available imaging data. We propose a novel evolutionary deep radiomic sequencer discovery approach based on evolutionary deep intelligence. Motivated by patient privacy concerns and the idea of operational artificial intelligence, the evolutionary deep radiomic sequencer discovery approach organically evolves increasingly more efficient deep radiomic sequencers that produce significantly more compact yet similarly descriptive radiomic sequences over multiple generations. As a result, this framework improves operational efficiency and enables diagnosis to be run locally at the radiologist's computer while maintaining detection accuracy. We evaluated the evolved deep radiomic sequencer (EDRS) discovered via the proposed evolutionary deep radiomic sequencer discovery framework against state-of-the-art radiomics-driven and discovery radiomics methods using clinical lung CT data with pathologically-proven diagnostic data from the LIDC-IDRI dataset. The evolved deep radiomic sequencer shows improved sensitivity (93.42%), specificity (82.39%), and diagnostic accuracy (88.78%) relative to previous radiomics approaches.

arXiv:1711.03230

An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks

Reading comprehension (RC) is a challenging task that requires synthesis of information across sentences and multiple turns of reasoning. Using a state-of-the-art RC model, we empirically investigate the performance of single-turn and multiple-turn reasoning on the SQuAD and MS MARCO datasets. The RC model is an end-to-end neural network with iterative attention, and uses reinforcement learning to dynamically control the number of turns. We find that multiple-turn reasoning outperforms single-turn reasoning for all question and answer types; further, we observe that enabling a flexible number of turns generally improves upon a fixed multiple-turn strategy. %across all question types, and is particularly beneficial to questions with lengthy, descriptive answers. We achieve results competitive to the state-of-the-art on these two datasets.

arXiv:1711.06396

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To interface a highly sparse LiDAR point cloud with a region proposal network (RPN), most existing efforts have focused on hand-crafted feature representations, for example, a bird's eye view projection. In this work, we remove the need of manual feature engineering for 3D point clouds and propose VoxelNet, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network. Specifically, VoxelNet divides a point cloud into equally spaced 3D voxels and transforms a group of points within each voxel into a unified feature representation through the newly introduced voxel feature encoding (VFE) layer. In this way, the point cloud is encoded as a descriptive volumetric representation, which is then connected to a RPN to generate detections. Experiments on the KITTI car detection benchmark show that VoxelNet outperforms the state-of-the-art LiDAR based 3D detection methods by a large margin. Furthermore, our network learns an effective discriminative representation of objects with various geometries, leading to encouraging results in 3D detection of pedestrians and cyclists, based on only LiDAR.

arXiv:1711.07414

The Promise and Peril of Human Evaluation for Model Interpretability

Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications. This alone presents a challenge in many areas of artificial intelligence. In this position paper, we propose a distinction between descriptive and persuasive explanations. We discuss reasoning suggesting that functional interpretability may be correlated with cognitive function and user preferences. If this is indeed the case, evaluation and optimization using functional metrics could perpetuate implicit cognitive bias in explanations that threaten transparency. Finally, we propose two potential research directions to disambiguate cognitive function and explanation models, retaining control over the tradeoff between accuracy and interpretability.

arXiv:1711.10317

Classification of entities via their descriptive sentences

Hypernym identification of open-domain entities is crucial for taxonomy construction as well as many higher-level applications. Current methods suffer from either low precision or low recall. To decrease the difficulty of this problem, we adopt a classification-based method. We pre-define a concept taxonomy and classify an entity to one of its leaf concept, based on the name and description information of the entity. A convolutional neural network classifier and a K-means clustering module are adopted for classification. We applied this system to 2.1 million Baidu Baike entities, and 1.1 million of them were successfully identified with a precision of 99.36%.

arXiv:1706.09076

A Pig, an Angel and a Cactus Walk Into a Blender: A Descriptive Approach to Visual Blending

A descriptive approach for automatic generation of visual blends is presented. The implemented system, the Blender, is composed of two components: the Mapper and the Visual Blender. The approach uses structured visual representations along with sets of visual relations which describe how the elements (in which the visual representation can be decomposed) relate among each other. Our system is a hybrid blender, as the blending process starts at the Mapper (conceptual level) and ends at the Visual Blender (visual representation level). The experimental results show that the Blender is able to create analogies from input mental spaces and produce well-composed blends, which follow the rules imposed by its base-analogy and its relations. The resulting blends are visually interesting and some can be considered as unexpected.

arXiv:1711.08097

Integrating both Visual and Audio Cues for Enhanced Video Caption

Video caption refers to generating a descriptive sentence for a specific short video clip automatically, which has achieved remarkable success recently. However, most of the existing methods focus more on visual information while ignoring the synchronized audio cues. We propose three multimodal deep fusion strategies to maximize the benefits of visual-audio resonance information. The first one explores the impact on cross-modalities feature fusion from low to high order. The second establishes the visual-audio short-term dependency by sharing weights of corresponding front-end networks. The third extends the temporal dependency to long-term through sharing multimodal memory across visual and audio modalities. Extensive experiments have validated the effectiveness of our three cross-modalities fusion strategies on two benchmark datasets, including Microsoft Research Video to Text (MSRVTT) and Microsoft Video Description (MSVD). It is worth mentioning that sharing weight can coordinate visual-audio feature fusion effectively and achieve the state-of-art performance on both BELU and METEOR metrics. Furthermore, we first propose a dynamic multimodal feature fusion framework to deal with the part modalities missing case. Experimental results demonstrate that even in the audio absence mode, we can still obtain comparable results with the aid of the additional audio modality inference module.

arXiv:1712.03999

Eye In-Painting with Exemplar Generative Adversarial Networks

This paper introduces a novel approach to in-painting where the identity of the object to remove or change is preserved and accounted for at inference time: Exemplar GANs (ExGANs). ExGANs are a type of conditional GAN that utilize exemplar information to produce high-quality, personalized in painting results. We propose using exemplar information in the form of a reference image of the region to in-paint, or a perceptual code describing that object. Unlike previous conditional GAN formulations, this extra information can be inserted at multiple points within the adversarial network, thus increasing its descriptive power. We show that ExGANs can produce photo-realistic personalized in-painting results that are both perceptually and semantically plausible by applying them to the task of closed to-open eye in-painting in natural pictures. A new benchmark dataset is also introduced for the task of eye in-painting for future comparisons.