PyTorchKR Papers

최신 논문

총 1,314편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1601.00022

Event Specific Multimodal Pattern Mining with Image-Caption Pairs

In this paper we describe a novel framework and algorithms for discovering image patch patterns from a large corpus of weakly supervised image-caption pairs generated from news events. Current pattern mining techniques attempt to find patterns that are representative and discriminative, we stipulate that our discovered patterns must also be recognizable by humans and preferably with meaningful names. We propose a new multimodal pattern mining approach that leverages the descriptive captions often accompanying news images to learn semantically meaningful image patch patterns. The mutltimodal patterns are then named using words mined from the associated image captions for each pattern. A novel evaluation framework is provided that demonstrates our patterns are 26.2% more semantically meaningful than those discovered by the state of the art vision only pipeline, and that we can provide tags for the discovered images patches with 54.5% accuracy with no direct supervision. Our methods also discover named patterns beyond those covered by the existing image datasets like ImageNet. To the best of our knowledge this is the first algorithm developed to automatically mine image patch patterns that have strong semantic meaning specific to high-level news events, and then evaluate these patterns based on that criteria.

arXiv:1601.07714

Log-Normal Matrix Completion for Large Scale Link Prediction

The ubiquitous proliferation of online social networks has led to the widescale emergence of relational graphs expressing unique patterns in link formation and descriptive user node features. Matrix Factorization and Completion have become popular methods for Link Prediction due to the low rank nature of mutual node friendship information, and the availability of parallel computer architectures for rapid matrix processing. Current Link Prediction literature has demonstrated vast performance improvement through the utilization of sparsity in addition to the low rank matrix assumption. However, the majority of research has introduced sparsity through the limited L1 or Frobenius norms, instead of considering the more detailed distributions which led to the graph formation and relationship evolution. In particular, social networks have been found to express either Pareto, or more recently discovered, Log Normal distributions. Employing the convexity-inducing Lovasz Extension, we demonstrate how incorporating specific degree distribution information can lead to large scale improvements in Matrix Completion based Link prediction. We introduce Log-Normal Matrix Completion (LNMC), and solve the complex optimization problem by employing Alternating Direction Method of Multipliers. Using data from three popular social networks, our experiments yield up to 5% AUC increase over top-performing non-structured sparsity based methods.

arXiv:1603.01842

Proximal groupoid patterns In digital images

The focus of this article is on the detection and classification of patterns based on groupoids. The approach hinges on descriptive proximity of points in a set based on the neighborliness property. This approach lends support to image analysis and understanding and in studying nearness of image segments. A practical application of the approach is in terms of the analysis of natural images for pattern identification and classification.

arXiv:1511.06341

Communicating Semantics: Reference by Description

Messages often refer to entities such as people, places and events. Correct identification of the intended reference is an essential part of communication. Lack of shared unique names often complicates entity reference. Shared knowledge can be used to construct uniquely identifying descriptive references for entities with ambiguous names. We introduce a mathematical model for `Reference by Description', derive results on the conditions under which, with high probability, programs can construct unambiguous references to most entities in the domain of discourse and provide empirical validation of these results.

arXiv:1603.07839

Early Detection of Combustion Instabilities using Deep Convolutional Selective Autoencoders on Hi-speed Flame Video

This paper proposes an end-to-end convolutional selective autoencoder approach for early detection of combustion instabilities using rapidly arriving flame image frames. The instabilities arising in combustion processes cause significant deterioration and safety issues in various human-engineered systems such as land and air based gas turbine engines. These properties are described as self-sustaining, large amplitude pressure oscillations and show varying spatial scales periodic coherent vortex structure shedding. However, such instability is extremely difficult to detect before a combustion process becomes completely unstable due to its sudden (bifurcation-type) nature. In this context, an autoencoder is trained to selectively mask stable flame and allow unstable flame image frames. In that process, the model learns to identify and extract rich descriptive and explanatory flame shape features. With such a training scheme, the selective autoencoder is shown to be able to detect subtle instability features as a combustion process makes transition from stable to unstable region. As a consequence, the deep learning tool-chain can perform as an early detection framework for combustion instabilities that will have a transformative impact on the safety and performance of modern engines.

arXiv:1604.03099

Symbolic Knowledge Extraction using Łukasiewicz Logics

This work describes a methodology that combines logic-based systems and connectionist systems. Our approach uses finite truth-valued {\L}ukasiewicz logic, wherein every connective can be defined by a neuron in an artificial network. This allowed the injection of first-order formulas into a network architecture, and also simplified symbolic rule extraction. For that we trained a neural networks using the Levenderg-Marquardt algorithm, where we restricted the knowledge dissemination in the network structure. This procedure reduces neural network plasticity without drastically damaging the learning performance, thus making the descriptive power of produced neural networks similar to the descriptive power of {\L}ukasiewicz logic language and simplifying the translation between symbolic and connectionist structures. We used this method for reverse engineering truth table and in extraction of formulas from real data sets.

arXiv:1604.02780

Knowledge Extraction and Knowledge Integration governed by Łukasiewicz Logics

The development of machine learning in particular and artificial intelligent in general has been strongly conditioned by the lack of an appropriate interface layer between deduction, abduction and induction. In this work we extend traditional algebraic specification methods in this direction. Here we assume that such interface for AI emerges from an adequate Neural-Symbolic integration. This integration is made for universe of discourse described on a Topos governed by a many-valued {\L}ukasiewicz logic. Sentences are integrated in a symbolic knowledge base describing the problem domain, codified using a graphic-based language, wherein every logic connective is defined by a neuron in an artificial network. This allows the integration of first-order formulas into a network architecture as background knowledge, and simplifies symbolic rule extraction from trained networks. For the train of such neural networks we changed the Levenderg-Marquardt algorithm, restricting the knowledge dissemination in the network structure using soft crystallization. This procedure reduces neural network plasticity without drastically damaging the learning performance, allowing the emergence of symbolic patterns. This makes the descriptive power of produced neural networks similar to the descriptive power of {\L}ukasiewicz logic language, reducing the information lost on translation between symbolic and connectionist structures. We tested this method on the extraction of knowledge from specified structures. For it, we present the notion of fuzzy state automata, and we use automata behaviour to infer its structure. We use this type of automata on the generation of models for relations specified as symbolic background knowledge.

arXiv:1604.02774

Reverse Engineering and Symbolic Knowledge Extraction on Łukasiewicz Fuzzy Logics using Linear Neural Networks

This work describes a methodology to combine logic-based systems and connectionist systems. Our approach uses finite truth valued {\L}ukasiewicz logic, where we take advantage of fact what in this type of logics every connective can be define by a neuron in an artificial network having by activation function the identity truncated to zero and one. This allowed the injection of first-order formulas in a network architecture, and also simplified symbolic rule extraction. Our method trains a neural network using Levenderg-Marquardt algorithm, where we restrict the knowledge dissemination in the network structure. We show how this reduces neural networks plasticity without damage drastically the learning performance. Making the descriptive power of produced neural networks similar to the descriptive power of {\L}ukasiewicz logic language, simplifying the translation between symbolic and connectionist structures. This method is used in the reverse engineering problem of finding the formula used on generation of a truth table for a multi-valued {\L}ukasiewicz logic. For real data sets the method is particularly useful for attribute selection, on binary classification problems defined using nominal attribute. After attribute selection and possible data set completion in the resulting connectionist model: neurons are directly representable using a disjunctive or conjunctive formulas, in the {\L}ukasiewicz logic, or neurons are interpretations which can be approximated by symbolic rules. This fact is exemplified, extracting symbolic knowledge from connectionist models generated for the data set Mushroom from UCI Machine Learning Repository.

arXiv:1604.03968

Visual Storytelling

We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND v.1, includes 81,743 unique photos in 20,211 sequences, aligned to both descriptive (caption) and story language. We establish several strong baselines for the storytelling task, and motivate an automatic metric to benchmark progress. Modelling concrete description as well as figurative and social language, as provided in this dataset and the storytelling task, has the potential to move artificial intelligence from basic understandings of typical visual scenes towards more and more human-like understanding of grounded event structure and subjective expression.

arXiv:1604.07809

Entities as topic labels: Improving topic interpretability and evaluability combining Entity Linking and Labeled LDA

In order to create a corpus exploration method providing topics that are easier to interpret than standard LDA topic models, here we propose combining two techniques called Entity linking and Labeled LDA. Our method identifies in an ontology a series of descriptive labels for each document in a corpus. Then it generates a specific topic for each label. Having a direct relation between topics and labels makes interpretation easier; using an ontology as background knowledge limits label ambiguity. As our topics are described with a limited number of clear-cut labels, they promote interpretability, and this may help quantitative evaluation. We illustrate the potential of the approach by applying it in order to define the most relevant topics addressed by each party in the European Parliament's fifth mandate (1999-2004).

arXiv:1605.00420

An Enhanced Harmony Search Method for Bangla Handwritten Character Recognition Using Region Sampling

Identification of minimum number of local regions of a handwritten character image, containing well-defined discriminating features which are sufficient for a minimal but complete description of the character is a challenging task. A new region selection technique based on the idea of an enhanced Harmony Search methodology has been proposed here. The powerful framework of Harmony Search has been utilized to search the region space and detect only the most informative regions for correctly recognizing the handwritten character. The proposed method has been tested on handwritten samples of Bangla Basic, Compound and mixed (Basic and Compound characters) characters separately with SVM based classifier using a longest run based feature-set obtained from the image subregions formed by a CG based quad-tree partitioning approach. Applying this methodology on the above mentioned three types of datasets, respectively 43.75%, 12.5% and 37.5% gains have been achieved in terms of region reduction and 2.3%, 0.6% and 1.2% gains have been achieved in terms of recognition accuracy. The results show a sizeable reduction in the minimal number of descriptive regions as well a significant increase in recognition accuracy for all the datasets using the proposed technique. Thus the time and cost related to feature extraction is decreased without dampening the corresponding recognition accuracy.

arXiv:1605.00170

Enforcing Template Representability and Temporal Consistency for Adaptive Sparse Tracking

Sparse representation has been widely studied in visual tracking, which has shown promising tracking performance. Despite a lot of progress, the visual tracking problem is still a challenging task due to appearance variations over time. In this paper, we propose a novel sparse tracking algorithm that well addresses temporal appearance changes, by enforcing template representability and temporal consistency (TRAC). By modeling temporal consistency, our algorithm addresses the issue of drifting away from a tracking target. By exploring the templates' long-term-short-term representability, the proposed method adaptively updates the dictionary using the most descriptive templates, which significantly improves the robustness to target appearance changes. We compare our TRAC algorithm against the state-of-the-art approaches on 12 challenging benchmark image sequences. Both qualitative and quantitative results demonstrate that our algorithm significantly outperforms previous state-of-the-art trackers.

arXiv:1605.00052

InterActive: Inter-Layer Activeness Propagation

An increasing number of computer vision tasks can be tackled with deep features, which are the intermediate outputs of a pre-trained Convolutional Neural Network. Despite the astonishing performance, deep features extracted from low-level neurons are still below satisfaction, arguably because they cannot access the spatial context contained in the higher layers. In this paper, we present InterActive, a novel algorithm which computes the activeness of neurons and network connections. Activeness is propagated through a neural network in a top-down manner, carrying high-level context and improving the descriptive power of low-level and mid-level neurons. Visualization indicates that neuron activeness can be interpreted as spatial-weighted neuron responses. We achieve state-of-the-art classification performance on a wide range of image datasets.

arXiv:1604.08723공식 코드 · Papers with Code

Music transcription modelling and composition using deep learning

We apply deep learning methods, specifically long short-term memory (LSTM) networks, to music transcription modelling and composition. We build and train LSTM networks using approximately 23,000 music transcriptions expressed with a high-level vocabulary (ABC notation), and use them to generate new transcriptions. Our practical aim is to create music transcription models useful in particular contexts of music composition. We present results from three perspectives: 1) at the population level, comparing descriptive statistics of the set of training transcriptions and generated transcriptions; 2) at the individual level, examining how a generated transcription reflects the conventions of a music practice in the training transcriptions (Celtic folk); 3) at the application level, using the system for idea generation in music composition. We make our datasets, software and sound examples open and available: \url{https://github.com/IraKorshunova/folk-rnn}.

arXiv:1605.01242

Hierarchical Modeling of Multidimensional Data in Regularly Decomposed Spaces: Applications in Image Analysis

This last document is showing the gradual introduction of hierarchical modeling techniques in image analysis. The first chapter is dealing with the first works carried out in the field of industrial applications of pattern recognition. The second chapter is focusing on the usage of these techniques in satellite imagery and on the development of a satellite data archiving system in the aim of using it in digital geography. The third chapter is about face recognition based on planar image analysis and about the recognition of partially hidden patterns. The present publication is ending with the description of a future system of self-descriptive coding of still or moving pictures in relation with the current video coding standards. As in the previous documents, it will be found in annex algorithms targeted on image analysis according two complementary approaches: - boundary-based approach for the industrial applications of artificial vision; - region-based approach for satellite image analysis.

arXiv:1602.03001

A Convolutional Attention Network for Extreme Summarization of Source Code

Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension. Often there exist features that are locally translation invariant and would be valuable for directing the model's attention, but previous attentional architectures are not constructed to learn such features specifically. We introduce an attentional neural network that employs convolution on the input tokens to detect local time-invariant and long-range topical attention features in a context-dependent way. We apply this architecture to the problem of extreme summarization of source code snippets into short, descriptive function name-like summaries. Using those features, the model sequentially generates a summary by marginalizing over two attention mechanisms: one that predicts the next summary token based on the attention weights of the input tokens and another that is able to copy a code token as-is directly into the summary. We demonstrate our convolutional attention neural network's performance on 10 popular Java projects showing that it achieves better performance compared to previous attentional mechanisms.

arXiv:1605.08187

The Symbolic Interior Point Method

A recent trend in probabilistic inference emphasizes the codification of models in a formal syntax, with suitable high-level features such as individuals, relations, and connectives, enabling descriptive clarity, succinctness and circumventing the need for the modeler to engineer a custom solver. Unfortunately, bringing these linguistic and pragmatic benefits to numerical optimization has proven surprisingly challenging. In this paper, we turn to these challenges: we introduce a rich modeling language, for which an interior-point method computes approximate solutions in a generic way. While logical features easily complicates the underlying model, often yielding intricate dependencies, we exploit and cache local structure using algebraic decision diagrams (ADDs). Indeed, standard matrix-vector algebra is efficiently realizable in ADDs, but we argue and show that well-known optimization methods are not ideal for ADDs. Our engine, therefore, invokes a sophisticated matrix-free approach. We demonstrate the flexibility of the resulting symbolic-numeric optimizer on decision making and compressed sensing tasks with millions of non-zero entries.

arXiv:1606.05328

Conditional Image Generation with PixelCNN Decoders

This work explores conditional image generation with a new image density model based on the PixelCNN architecture. The model can be conditioned on any vector, including descriptive labels or tags, or latent embeddings created by other networks. When conditioned on class labels from the ImageNet database, the model is able to generate diverse, realistic scenes representing distinct animals, objects, landscapes and structures. When conditioned on an embedding produced by a convolutional network given a single image of an unseen face, it generates a variety of new portraits of the same person with different facial expressions, poses and lighting conditions. We also show that conditional PixelCNN can serve as a powerful decoder in an image autoencoder. Additionally, the gated convolutional layers in the proposed model improve the log-likelihood of PixelCNN to match the state-of-the-art performance of PixelRNN on ImageNet, with greatly reduced computational cost.

arXiv:1606.07287공식 코드 · Papers with Code

Picture It In Your Mind: Generating High Level Visual Representations From Textual Descriptions

In this paper we tackle the problem of image search when the query is a short textual description of the image the user is looking for. We choose to implement the actual search process as a similarity search in a visual feature space, by learning to translate a textual query into a visual representation. Searching in the visual feature space has the advantage that any update to the translation model does not require to reprocess the, typically huge, image collection on which the search is performed. We propose Text2Vis, a neural network that generates a visual representation, in the visual feature space of the fc6-fc7 layers of ImageNet, from a short descriptive text. Text2Vis optimizes two loss functions, using a stochastic loss-selection method. A visual-focused loss is aimed at learning the actual text-to-visual feature mapping, while a text-focused loss is aimed at modeling the higher-level semantic concepts expressed in language and countering the overfit on non-relevant visual components of the visual loss. We report preliminary results on the MS-COCO dataset.

arXiv:1607.00710

Automatic Generation of Probabilistic Programming from Time Series Data

Probabilistic programming languages represent complex data with intermingled models in a few lines of code. Efficient inference algorithms in probabilistic programming languages make possible to build unified frameworks to compute interesting probabilities of various large, real-world problems. When the structure of model is given, constructing a probabilistic program is rather straightforward. Thus, main focus have been to learn the best model parameters and compute marginal probabilities. In this paper, we provide a new perspective to build expressive probabilistic program from continue time series data when the structure of model is not given. The intuition behind of our method is to find a descriptive covariance structure of time series data in nonparametric Gaussian process regression. We report that such descriptive covariance structure efficiently derives a probabilistic programming description accurately.