Paper Group ANR 91
DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer. An Automated Compatibility Prediction Engine using DISC Theory Based Classification and Neural Networks. First Results from Using Game Refinement Measure and Learning Coefficient in Scrabble. A Simulator for Hedonic Games. Convolutional Low-Resolution Fine-Grained C …
DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer
| Title | DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer |
| Authors | Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang |
| Abstract | We have witnessed rapid evolution of deep neural network architecture design in the past years. These latest progresses greatly facilitate the developments in various areas such as computer vision and natural language processing. However, along with the extraordinary performance, these state-of-the-art models also bring in expensive computational cost. Directly deploying these models into applications with real-time requirement is still infeasible. Recently, Hinton etal. have shown that the dark knowledge within a powerful teacher model can significantly help the training of a smaller and faster student network. These knowledge are vastly beneficial to improve the generalization ability of the student model. Inspired by their work, we introduce a new type of knowledge – cross sample similarities for model compression and acceleration. This knowledge can be naturally derived from deep metric learning model. To transfer them, we bring the “learning to rank” technique into deep metric learning formulation. We test our proposed DarkRank method on various metric learning tasks including pedestrian re-identification, image retrieval and image clustering. The results are quite encouraging. Our method can improve over the baseline method by a large margin. Moreover, it is fully compatible with other existing methods. When combined, the performance can be further boosted. |
| Tasks | Image Clustering, Image Retrieval, Learning-To-Rank, Metric Learning, Model Compression |
| Published | 2017-07-05 |
| URL | http://arxiv.org/abs/1707.01220v2 |
| http://arxiv.org/pdf/1707.01220v2.pdf | |
| PWC | https://paperswithcode.com/paper/darkrank-accelerating-deep-metric-learning |
| Repo | |
| Framework | |
An Automated Compatibility Prediction Engine using DISC Theory Based Classification and Neural Networks
| Title | An Automated Compatibility Prediction Engine using DISC Theory Based Classification and Neural Networks |
| Authors | Chandrasekaran Anirudh Bhardwaj, Megha Mishra, Sweetlin Hemalatha |
| Abstract | Traditionally psychometric tests were used for profiling incoming workers. These methods use DISC profiling method to classify people into distinct personality types, which are further used to predict if a person may be a possible fit to the organizational culture. This concept is taken further by introducing a novel technique to predict if a particular pair of an incoming worker and the manager being assigned are compatible at a psychological scale. This is done using multilayer perceptron neural network which can be adaptively trained to showcase the true nature of the compatibility index. The proposed prototype model is used to quantify the relevant attributes, use them to train the prediction engine, and to define the data pipeline required for it. |
| Tasks | |
| Published | 2017-09-02 |
| URL | http://arxiv.org/abs/1709.00539v1 |
| http://arxiv.org/pdf/1709.00539v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-automated-compatibility-prediction-engine |
| Repo | |
| Framework | |
First Results from Using Game Refinement Measure and Learning Coefficient in Scrabble
| Title | First Results from Using Game Refinement Measure and Learning Coefficient in Scrabble |
| Authors | Kananat Suwanviwatana, Hiroyuki Iida |
| Abstract | This paper explores the entertainment experience and learning experience in Scrabble. It proposes a new measure from the educational point of view, which we call learning coefficient, based on the balance between the learner’s skill and the challenge in Scrabble. Scrabble variants, generated using different size of board and dictionary, are analyzed with two measures of game refinement and learning coefficient. The results show that 13x13 Scrabble yields the best entertainment experience and 15x15 (standard) Scrabble with 4% of original dictionary size yields the most effective environment for language learners. Moreover, 15x15 Scrabble with 10% of original dictionary size has a good balance between entertainment and learning experience. |
| Tasks | |
| Published | 2017-11-07 |
| URL | http://arxiv.org/abs/1711.03580v1 |
| http://arxiv.org/pdf/1711.03580v1.pdf | |
| PWC | https://paperswithcode.com/paper/first-results-from-using-game-refinement |
| Repo | |
| Framework | |
A Simulator for Hedonic Games
| Title | A Simulator for Hedonic Games |
| Authors | Luke Harold Miles |
| Abstract | Hedonic games are meant to model how coalitions of people form and break apart in the real world. However, it is difficult to run simulations when everything must be done by hand on paper. We present an online software that allows fast and visual simulation of several types of hedonic games. http://lukemiles.org/hedonic-games/ |
| Tasks | |
| Published | 2017-06-26 |
| URL | http://arxiv.org/abs/1706.08501v2 |
| http://arxiv.org/pdf/1706.08501v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-simulator-for-hedonic-games |
| Repo | |
| Framework | |
Convolutional Low-Resolution Fine-Grained Classification
| Title | Convolutional Low-Resolution Fine-Grained Classification |
| Authors | Dingding Cai, Ke Chen, Yanlin Qian, Joni-Kristian Kämäräinen |
| Abstract | Successful fine-grained image classification methods learn subtle details between visually similar (sub-)classes, but the problem becomes significantly more challenging if the details are missing due to low resolution. Encouraged by the recent success of Convolutional Neural Network (CNN) architectures in image classification, we propose a novel resolution-aware deep model which combines convolutional image super-resolution and convolutional fine-grained classification into a single model in an end-to-end manner. Extensive experiments on the Stanford Cars and Caltech-UCSD Birds 200-2011 benchmarks demonstrate that the proposed model consistently performs better than conventional convolutional net on classifying fine-grained object classes in low-resolution images. |
| Tasks | Fine-Grained Image Classification, Image Classification, Image Super-Resolution, Super-Resolution |
| Published | 2017-03-15 |
| URL | http://arxiv.org/abs/1703.05393v3 |
| http://arxiv.org/pdf/1703.05393v3.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-low-resolution-fine-grained |
| Repo | |
| Framework | |
Stochastic metamorphosis with template uncertainties
| Title | Stochastic metamorphosis with template uncertainties |
| Authors | Alexis Arnaudon, Darryl Holm, Stefan Sommer |
| Abstract | In this paper, we investigate two stochastic perturbations of the metamorphosis equations of image analysis, in the geometrical context of the Euler-Poincar'e theory. In the metamorphosis of images, the Lie group of diffeomorphisms deforms a template image that is undergoing its own internal dynamics as it deforms. This type of deformation allows more freedom for image matching and has analogies with complex fluids when the template properties are regarded as order parameters (coset spaces of broken symmetries). The first stochastic perturbation we consider corresponds to uncertainty due to random errors in the reconstruction of the deformation map from its vector field. We also consider a second stochastic perturbation, which compounds the uncertainty in of the deformation map with the uncertainty in the reconstruction of the template position from its velocity field. We apply this general geometric theory to several classical examples, including landmarks, images, and closed curves, and we discuss its use for functional data analysis. |
| Tasks | |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1711.07231v1 |
| http://arxiv.org/pdf/1711.07231v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-metamorphosis-with-template |
| Repo | |
| Framework | |
Learning a Target Sample Re-Generator for Cross-Database Micro-Expression Recognition
| Title | Learning a Target Sample Re-Generator for Cross-Database Micro-Expression Recognition |
| Authors | Yuan Zong, Xiaohua Huang, Wenming Zheng, Zhen Cui, Guoying Zhao |
| Abstract | In this paper, we investigate the cross-database micro-expression recognition problem, where the training and testing samples are from two different micro-expression databases. Under this setting, the training and testing samples would have different feature distributions and hence the performance of most existing micro-expression recognition methods may decrease greatly. To solve this problem, we propose a simple yet effective method called Target Sample Re-Generator (TSRG) in this paper. By using TSRG, we are able to re-generate the samples from target micro-expression database and the re-generated target samples would share same or similar feature distributions with the original source samples. For this reason, we can then use the classifier learned based on the labeled source samples to accurately predict the micro-expression categories of the unlabeled target samples. To evaluate the performance of the proposed TSRG method, extensive cross-database micro-expression recognition experiments designed based on SMIC and CASME II databases are conducted. Compared with recent state-of-the-art cross-database emotion recognition methods, the proposed TSRG achieves more promising results. |
| Tasks | Emotion Recognition |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08645v1 |
| http://arxiv.org/pdf/1707.08645v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-target-sample-re-generator-for |
| Repo | |
| Framework | |
Auto-clustering Output Layer: Automatic Learning of Latent Annotations in Neural Networks
| Title | Auto-clustering Output Layer: Automatic Learning of Latent Annotations in Neural Networks |
| Authors | Ozsel Kilinc, Ismail Uysal |
| Abstract | In this paper, we discuss a different type of semi-supervised setting: a coarse level of labeling is available for all observations but the model has to learn a fine level of latent annotation for each one of them. Problems in this setting are likely to be encountered in many domains such as text categorization, protein function prediction, image classification as well as in exploratory scientific studies such as medical and genomics research. We consider this setting as simultaneously performed supervised classification (per the available coarse labels) and unsupervised clustering (within each one of the coarse labels) and propose a novel output layer modification called auto-clustering output layer (ACOL) that allows concurrent classification and clustering based on Graph-based Activity Regularization (GAR) technique. As the proposed output layer modification duplicates the softmax nodes at the output layer for each class, GAR allows for competitive learning between these duplicates on a traditional error-correction learning framework to ultimately enable a neural network to learn the latent annotations in this partially supervised setup. We demonstrate how the coarse label supervision impacts performance and helps propagate useful clustering information between sub-classes. Comparative tests on three of the most popular image datasets MNIST, SVHN and CIFAR-100 rigorously demonstrate the effectiveness and competitiveness of the proposed approach. |
| Tasks | Image Classification, Protein Function Prediction, Text Categorization |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1702.08648v2 |
| http://arxiv.org/pdf/1702.08648v2.pdf | |
| PWC | https://paperswithcode.com/paper/auto-clustering-output-layer-automatic |
| Repo | |
| Framework | |
Creating New Language and Voice Components for the Updated MaryTTS Text-to-Speech Synthesis Platform
| Title | Creating New Language and Voice Components for the Updated MaryTTS Text-to-Speech Synthesis Platform |
| Authors | Ingmar Steiner, Sébastien Le Maguer |
| Abstract | We present a new workflow to create components for the MaryTTS text-to-speech synthesis platform, which is popular with researchers and developers, extending it to support new languages and custom synthetic voices. This workflow replaces the previous toolkit with an efficient, flexible process that leverages modern build automation and cloud-hosted infrastructure. Moreover, it is compatible with the updated MaryTTS architecture, enabling new features and state-of-the-art paradigms such as synthesis based on deep neural networks (DNNs). Like MaryTTS itself, the new tools are free, open source software (FOSS), and promote the use of open data. |
| Tasks | Speech Synthesis, Text-To-Speech Synthesis |
| Published | 2017-12-13 |
| URL | http://arxiv.org/abs/1712.04787v2 |
| http://arxiv.org/pdf/1712.04787v2.pdf | |
| PWC | https://paperswithcode.com/paper/creating-new-language-and-voice-components |
| Repo | |
| Framework | |
Application of Convolutional Neural Network to Predict Airfoil Lift Coefficient
| Title | Application of Convolutional Neural Network to Predict Airfoil Lift Coefficient |
| Authors | Yao Zhang, Woong-Je Sung, Dimitri Mavris |
| Abstract | The adaptability of the convolutional neural network (CNN) technique for aerodynamic meta-modeling tasks is probed in this work. The primary objective is to develop suitable CNN architecture for variable flow conditions and object geometry, in addition to identifying a sufficient data preparation process. Multiple CNN structures were trained to learn the lift coefficients of the airfoils with a variety of shapes in multiple flow Mach numbers, Reynolds numbers, and diverse angles of attack. This is conducted to illustrate the concept of the technique. A multi-layered perceptron (MLP) is also used for the training sets. The MLP results are compared with that of the CNN results. The newly proposed meta-modeling concept has been found to be comparable with the MLP in learning capability; and more importantly, our CNN model exhibits a competitive prediction accuracy with minimal constraints in a geometric representation. |
| Tasks | |
| Published | 2017-12-29 |
| URL | http://arxiv.org/abs/1712.10082v2 |
| http://arxiv.org/pdf/1712.10082v2.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-convolutional-neural-network-1 |
| Repo | |
| Framework | |
Morphognosis: the shape of knowledge in space and time
| Title | Morphognosis: the shape of knowledge in space and time |
| Authors | Thomas E. Portegys |
| Abstract | Artificial intelligence research to a great degree focuses on the brain and behaviors that the brain generates. But the brain, an extremely complex structure resulting from millions of years of evolution, can be viewed as a solution to problems posed by an environment existing in space and time. The environment generates signals that produce sensory events within an organism. Building an internal spatial and temporal model of the environment allows an organism to navigate and manipulate the environment. Higher intelligence might be the ability to process information coming from a larger extent of space-time. In keeping with nature’s penchant for extending rather than replacing, the purpose of the mammalian neocortex might then be to record events from distant reaches of space and time and render them, as though yet near and present, to the older, deeper brain whose instinctual roles have changed little over eons. Here this notion is embodied in a model called morphognosis (morpho = shape and gnosis = knowledge). Its basic structure is a pyramid of event recordings called a morphognostic. At the apex of the pyramid are the most recent and nearby events. Receding from the apex are less recent and possibly more distant events. A morphognostic can thus be viewed as a structure of progressively larger chunks of space-time knowledge. A set of morphognostics forms long-term memories that are learned by exposure to the environment. A cellular automaton is used as the platform to investigate the morphognosis model, using a simulated organism that learns to forage in its world for food, build a nest, and play the game of Pong. |
| Tasks | |
| Published | 2017-01-05 |
| URL | http://arxiv.org/abs/1701.02272v2 |
| http://arxiv.org/pdf/1701.02272v2.pdf | |
| PWC | https://paperswithcode.com/paper/morphognosis-the-shape-of-knowledge-in-space |
| Repo | |
| Framework | |
The True Destination of EGO is Multi-local Optimization
| Title | The True Destination of EGO is Multi-local Optimization |
| Authors | Simon Wessing, Mike Preuss |
| Abstract | Efficient global optimization is a popular algorithm for the optimization of expensive multimodal black-box functions. One important reason for its popularity is its theoretical foundation of global convergence. However, as the budgets in expensive optimization are very small, the asymptotic properties only play a minor role and the algorithm sometimes comes off badly in experimental comparisons. Many alternative variants have therefore been proposed over the years. In this work, we show experimentally that the algorithm instead has its strength in a setting where multiple optima are to be identified. |
| Tasks | |
| Published | 2017-04-19 |
| URL | http://arxiv.org/abs/1704.05724v1 |
| http://arxiv.org/pdf/1704.05724v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-true-destination-of-ego-is-multi-local |
| Repo | |
| Framework | |
Vision-based Real Estate Price Estimation
| Title | Vision-based Real Estate Price Estimation |
| Authors | Omid Poursaeed, Tomas Matera, Serge Belongie |
| Abstract | Since the advent of online real estate database companies like Zillow, Trulia and Redfin, the problem of automatic estimation of market values for houses has received considerable attention. Several real estate websites provide such estimates using a proprietary formula. Although these estimates are often close to the actual sale prices, in some cases they are highly inaccurate. One of the key factors that affects the value of a house is its interior and exterior appearance, which is not considered in calculating automatic value estimates. In this paper, we evaluate the impact of visual characteristics of a house on its market value. Using deep convolutional neural networks on a large dataset of photos of home interiors and exteriors, we develop a method for estimating the luxury level of real estate photos. We also develop a novel framework for automated value assessment using the above photos in addition to home characteristics including size, offered price and number of bedrooms. Finally, by applying our proposed method for price estimation to a new dataset of real estate photos and metadata, we show that it outperforms Zillow’s estimates. |
| Tasks | |
| Published | 2017-07-18 |
| URL | http://arxiv.org/abs/1707.05489v3 |
| http://arxiv.org/pdf/1707.05489v3.pdf | |
| PWC | https://paperswithcode.com/paper/vision-based-real-estate-price-estimation |
| Repo | |
| Framework | |
Local Geometry Inclusive Global Shape Representation
| Title | Local Geometry Inclusive Global Shape Representation |
| Authors | Somenath Das, Suchendra M. Bhandarkar |
| Abstract | Knowledge of shape geometry plays a pivotal role in many shape analysis applications. In this paper we introduce a local geometry-inclusive global representation of 3D shapes based on computation of the shortest quasi-geodesic paths between all possible pairs of points on the 3D shape manifold. In the proposed representation, the normal curvature along the quasi-geodesic paths between any two points on the shape surface is preserved. We employ the eigenspectrum of the proposed global representation to address the problems of determination of region-based correspondence between isometric shapes and characterization of self-symmetry in the absence of prior knowledge in the form of user-defined correspondence maps. We further utilize the commutative property of the resulting shape descriptor to extract stable regions between isometric shapes that differ from one another by a high degree of isometry transformation. We also propose various shape characterization metrics in terms of the eigenvector decomposition of the shape descriptor spectrum to quantify the correspondence and self-symmetry of 3D shapes. The performance of the proposed 3D shape descriptor is experimentally compared with the performance of other relevant state-of-the-art 3D shape descriptors. |
| Tasks | |
| Published | 2017-07-20 |
| URL | http://arxiv.org/abs/1707.06699v1 |
| http://arxiv.org/pdf/1707.06699v1.pdf | |
| PWC | https://paperswithcode.com/paper/local-geometry-inclusive-global-shape |
| Repo | |
| Framework | |
Visual art inspired by the collective feeding behavior of sand-bubbler crabs
| Title | Visual art inspired by the collective feeding behavior of sand-bubbler crabs |
| Authors | Hendrik Richter |
| Abstract | Sand–bubblers are crabs of the genera Dotilla and Scopimera which are known to produce remarkable patterns and structures at tropical beaches. From these pattern-making abilities, we may draw inspiration for digital visual art. A simple mathematical model is proposed and an algorithm is designed that may create such sand-bubbler patterns artificially. In addition, design parameters to modify the patterns are identified and analyzed by computational aesthetic measures. Finally, an extension of the algorithm is discussed that may enable controlling and guiding generative evolution of the art-making process. |
| Tasks | |
| Published | 2017-09-01 |
| URL | http://arxiv.org/abs/1709.00410v2 |
| http://arxiv.org/pdf/1709.00410v2.pdf | |
| PWC | https://paperswithcode.com/paper/visual-art-inspired-by-the-collective-feeding |
| Repo | |
| Framework | |
