Paper Group ANR 397
Acquiring Background Knowledge to Improve Moral Value Prediction. Controllable Generative Adversarial Network. Coupled Support Vector Machines for Supervised Domain Adaptation. Derivative Based Focal Plane Array Nonuniformity Correction. Tensors, Learning, and ‘Kolmogorov Extension’ for Finite-alphabet Random Vectors. Lensless Photography with only …
Acquiring Background Knowledge to Improve Moral Value Prediction
| Title | Acquiring Background Knowledge to Improve Moral Value Prediction |
| Authors | Ying Lin, Joe Hoover, Morteza Dehghani, Marlon Mooijman, Heng Ji |
| Abstract | In this paper, we address the problem of detecting expressions of moral values in tweets using content analysis. This is a particularly challenging problem because moral values are often only implicitly signaled in language, and tweets contain little contextual information due to length constraints. To address these obstacles, we present a novel approach to automatically acquire background knowledge from an external knowledge base to enrich input texts and thus improve moral value prediction. By combining basic text features with background knowledge, our overall context-aware framework achieves performance comparable to a single human annotator. To the best of our knowledge, this is the first attempt to incorporate background knowledge for the prediction of implicit psychological variables in the area of computational social science. |
| Tasks | |
| Published | 2017-09-16 |
| URL | http://arxiv.org/abs/1709.05467v1 |
| http://arxiv.org/pdf/1709.05467v1.pdf | |
| PWC | https://paperswithcode.com/paper/acquiring-background-knowledge-to-improve |
| Repo | |
| Framework | |
Controllable Generative Adversarial Network
| Title | Controllable Generative Adversarial Network |
| Authors | Minhyeok Lee, Junhee Seok |
| Abstract | Recently introduced generative adversarial network (GAN) has been shown numerous promising results to generate realistic samples. The essential task of GAN is to control the features of samples generated from a random distribution. While the current GAN structures, such as conditional GAN, successfully generate samples with desired major features, they often fail to produce detailed features that bring specific differences among samples. To overcome this limitation, here we propose a controllable GAN (ControlGAN) structure. By separating a feature classifier from a discriminator, the generator of ControlGAN is designed to learn generating synthetic samples with the specific detailed features. Evaluated with multiple image datasets, ControlGAN shows a power to generate improved samples with well-controlled features. Furthermore, we demonstrate that ControlGAN can generate intermediate features and opposite features for interpolated and extrapolated input labels that are not used in the training process. It implies that ControlGAN can significantly contribute to the variety of generated samples. |
| Tasks | |
| Published | 2017-08-02 |
| URL | http://arxiv.org/abs/1708.00598v5 |
| http://arxiv.org/pdf/1708.00598v5.pdf | |
| PWC | https://paperswithcode.com/paper/controllable-generative-adversarial-network |
| Repo | |
| Framework | |
Coupled Support Vector Machines for Supervised Domain Adaptation
| Title | Coupled Support Vector Machines for Supervised Domain Adaptation |
| Authors | Hemanth Venkateswara, Prasanth Lade, Jieping Ye, Sethuraman Panchanathan |
| Abstract | Popular domain adaptation (DA) techniques learn a classifier for the target domain by sampling relevant data points from the source and combining it with the target data. We present a Support Vector Machine (SVM) based supervised DA technique, where the similarity between source and target domains is modeled as the similarity between their SVM decision boundaries. We couple the source and target SVMs and reduce the model to a standard single SVM. We test the Coupled-SVM on multiple datasets and compare our results with other popular SVM based DA approaches. |
| Tasks | Domain Adaptation |
| Published | 2017-06-22 |
| URL | http://arxiv.org/abs/1706.07525v1 |
| http://arxiv.org/pdf/1706.07525v1.pdf | |
| PWC | https://paperswithcode.com/paper/coupled-support-vector-machines-for |
| Repo | |
| Framework | |
Derivative Based Focal Plane Array Nonuniformity Correction
| Title | Derivative Based Focal Plane Array Nonuniformity Correction |
| Authors | G. Ness, A. Oved, I. Kakon |
| Abstract | This paper presents a fast and robust method for fixed pattern noise nonuniformity correction of infrared focal plane arrays. The proposed method requires neither shutter nor elaborate calibrations and therefore enables a real time correction with no interruptions. Based on derivative estimation of the fixed pattern noise from pixel sized translations of the focal plane array, the proposed method has the advantages of being invariant to the noise magnitude and robust to unknown camera and inter-scene movements while being virtually transparent to the end-user. |
| Tasks | |
| Published | 2017-02-19 |
| URL | http://arxiv.org/abs/1702.06118v1 |
| http://arxiv.org/pdf/1702.06118v1.pdf | |
| PWC | https://paperswithcode.com/paper/derivative-based-focal-plane-array |
| Repo | |
| Framework | |
Tensors, Learning, and ‘Kolmogorov Extension’ for Finite-alphabet Random Vectors
| Title | Tensors, Learning, and ‘Kolmogorov Extension’ for Finite-alphabet Random Vectors |
| Authors | Nikos Kargas, Nicholas D. Sidiropoulos, Xiao Fu |
| Abstract | Estimating the joint probability mass function (PMF) of a set of random variables lies at the heart of statistical learning and signal processing. Without structural assumptions, such as modeling the variables as a Markov chain, tree, or other graphical model, joint PMF estimation is often considered mission impossible - the number of unknowns grows exponentially with the number of variables. But who gives us the structural model? Is there a generic, `non-parametric’ way to control joint PMF complexity without relying on a priori structural assumptions regarding the underlying probability model? Is it possible to discover the operational structure without biasing the analysis up front? What if we only observe random subsets of the variables, can we still reliably estimate the joint PMF of all? This paper shows, perhaps surprisingly, that if the joint PMF of any three variables can be estimated, then the joint PMF of all the variables can be provably recovered under relatively mild conditions. The result is reminiscent of Kolmogorov’s extension theorem - consistent specification of lower-dimensional distributions induces a unique probability measure for the entire process. The difference is that for processes of limited complexity (rank of the high-dimensional PMF) it is possible to obtain complete characterization from only three-dimensional distributions. In fact not all three-dimensional PMFs are needed; and under more stringent conditions even two-dimensional will do. Exploiting multilinear algebra, this paper proves that such higher-dimensional PMF completion can be guaranteed - several pertinent identifiability results are derived. It also provides a practical and efficient algorithm to carry out the recovery task. Judiciously designed simulations and real-data experiments on movie recommendation and data classification are presented to showcase the effectiveness of the approach. | |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://arxiv.org/abs/1712.00205v2 |
| http://arxiv.org/pdf/1712.00205v2.pdf | |
| PWC | https://paperswithcode.com/paper/tensors-learning-and-kolmogorov-extension-for |
| Repo | |
| Framework | |
Lensless Photography with only an image sensor
| Title | Lensless Photography with only an image sensor |
| Authors | Ganghun Kim, Kyle Isaacson, Racheal Palmer, Rajesh Menon |
| Abstract | Photography usually requires optics in conjunction with a recording device (an image sensor). Eliminating the optics could lead to new form factors for cameras. Here, we report a simple demonstration of imaging using a bare CMOS sensor that utilizes computation. The technique relies on the space variant point-spread functions resulting from the interaction of a point source in the field of view with the image sensor. These space-variant point-spread functions are combined with a reconstruction algorithm in order to image simple objects displayed on a discrete LED array as well as on an LCD screen. We extended the approach to video imaging at the native frame rate of the sensor. Finally, we performed experiments to analyze the parametric impact of the object distance. Improving the sensor designs and reconstruction algorithms can lead to useful cameras without optics. |
| Tasks | |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06619v1 |
| http://arxiv.org/pdf/1702.06619v1.pdf | |
| PWC | https://paperswithcode.com/paper/lensless-photography-with-only-an-image |
| Repo | |
| Framework | |
Note Value Recognition for Piano Transcription Using Markov Random Fields
| Title | Note Value Recognition for Piano Transcription Using Markov Random Fields |
| Authors | Eita Nakamura, Kazuyoshi Yoshii, Simon Dixon |
| Abstract | This paper presents a statistical method for use in music transcription that can estimate score times of note onsets and offsets from polyphonic MIDI performance signals. Because performed note durations can deviate largely from score-indicated values, previous methods had the problem of not being able to accurately estimate offset score times (or note values) and thus could only output incomplete musical scores. Based on observations that the pitch context and onset score times are influential on the configuration of note values, we construct a context-tree model that provides prior distributions of note values using these features and combine it with a performance model in the framework of Markov random fields. Evaluation results show that our method reduces the average error rate by around 40 percent compared to existing/simple methods. We also confirmed that, in our model, the score model plays a more important role than the performance model, and it automatically captures the voice structure by unsupervised learning. |
| Tasks | |
| Published | 2017-03-23 |
| URL | http://arxiv.org/abs/1703.08144v3 |
| http://arxiv.org/pdf/1703.08144v3.pdf | |
| PWC | https://paperswithcode.com/paper/note-value-recognition-for-piano |
| Repo | |
| Framework | |
Robust Order Scheduling in the Fashion Industry: A Multi-Objective Optimization Approach
| Title | Robust Order Scheduling in the Fashion Industry: A Multi-Objective Optimization Approach |
| Authors | Wei Du, Yang Tang, Sunney Yung Sun Leung, Le Tong, Athanasios V. Vasilakos, Feng Qian |
| Abstract | In the fashion industry, order scheduling focuses on the assignment of production orders to appropriate production lines. In reality, before a new order can be put into production, a series of activities known as pre-production events need to be completed. In addition, in real production process, owing to various uncertainties, the daily production quantity of each order is not always as expected. In this research, by considering the pre-production events and the uncertainties in the daily production quantity, robust order scheduling problems in the fashion industry are investigated with the aid of a multi-objective evolutionary algorithm (MOEA) called nondominated sorting adaptive differential evolution (NSJADE). The experimental results illustrate that it is of paramount importance to consider pre-production events in order scheduling problems in the fashion industry. We also unveil that the existence of the uncertainties in the daily production quantity heavily affects the order scheduling. |
| Tasks | |
| Published | 2017-02-01 |
| URL | http://arxiv.org/abs/1702.00159v1 |
| http://arxiv.org/pdf/1702.00159v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-order-scheduling-in-the-fashion |
| Repo | |
| Framework | |
Learning to Write Stylized Chinese Characters by Reading a Handful of Examples
| Title | Learning to Write Stylized Chinese Characters by Reading a Handful of Examples |
| Authors | Danyang Sun, Tongzheng Ren, Chongxun Li, Hang Su, Jun Zhu |
| Abstract | Automatically writing stylized Chinese characters is an attractive yet challenging task due to its wide applicabilities. In this paper, we propose a novel framework named Style-Aware Variational Auto-Encoder (SA-VAE) to flexibly generate Chinese characters. Specifically, we propose to capture the different characteristics of a Chinese character by disentangling the latent features into content-related and style-related components. Considering of the complex shapes and structures, we incorporate the structure information as prior knowledge into our framework to guide the generation. Our framework shows a powerful one-shot/low-shot generalization ability by inferring the style component given a character with unseen style. To the best of our knowledge, this is the first attempt to learn to write new-style Chinese characters by observing only one or a few examples. Extensive experiments demonstrate its effectiveness in generating different stylized Chinese characters by fusing the feature vectors corresponding to different contents and styles, which is of significant importance in real-world applications. |
| Tasks | |
| Published | 2017-12-06 |
| URL | http://arxiv.org/abs/1712.06424v3 |
| http://arxiv.org/pdf/1712.06424v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-write-stylized-chinese-characters |
| Repo | |
| Framework | |
Predicting multicellular function through multi-layer tissue networks
| Title | Predicting multicellular function through multi-layer tissue networks |
| Authors | Marinka Zitnik, Jure Leskovec |
| Abstract | Motivation: Understanding functions of proteins in specific human tissues is essential for insights into disease diagnostics and therapeutics, yet prediction of tissue-specific cellular function remains a critical challenge for biomedicine. Results: Here we present OhmNet, a hierarchy-aware unsupervised node feature learning approach for multi-layer networks. We build a multi-layer network, where each layer represents molecular interactions in a different human tissue. OhmNet then automatically learns a mapping of proteins, represented as nodes, to a neural embedding based low-dimensional space of features. OhmNet encourages sharing of similar features among proteins with similar network neighborhoods and among proteins activated in similar tissues. The algorithm generalizes prior work, which generally ignores relationships between tissues, by modeling tissue organization with a rich multiscale tissue hierarchy. We use OhmNet to study multicellular function in a multi-layer protein interaction network of 107 human tissues. In 48 tissues with known tissue-specific cellular functions, OhmNet provides more accurate predictions of cellular function than alternative approaches, and also generates more accurate hypotheses about tissue-specific protein actions. We show that taking into account the tissue hierarchy leads to improved predictive power. Remarkably, we also demonstrate that it is possible to leverage the tissue hierarchy in order to effectively transfer cellular functions to a functionally uncharacterized tissue. Overall, OhmNet moves from flat networks to multiscale models able to predict a range of phenotypes spanning cellular subsystems |
| Tasks | |
| Published | 2017-07-14 |
| URL | http://arxiv.org/abs/1707.04638v1 |
| http://arxiv.org/pdf/1707.04638v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-multicellular-function-through |
| Repo | |
| Framework | |
CNNs are Globally Optimal Given Multi-Layer Support
| Title | CNNs are Globally Optimal Given Multi-Layer Support |
| Authors | Chen Huang, Chen Kong, Simon Lucey |
| Abstract | Stochastic Gradient Descent (SGD) is the central workhorse for training modern CNNs. Although giving impressive empirical performance it can be slow to converge. In this paper we explore a novel strategy for training a CNN using an alternation strategy that offers substantial speedups during training. We make the following contributions: (i) replace the ReLU non-linearity within a CNN with positive hard-thresholding, (ii) reinterpret this non-linearity as a binary state vector making the entire CNN linear if the multi-layer support is known, and (iii) demonstrate that under certain conditions a global optima to the CNN can be found through local descent. We then employ a novel alternation strategy (between weights and support) for CNN training that leads to substantially faster convergence rates, nice theoretical properties, and achieving state of the art results across large scale datasets (e.g. ImageNet) as well as other standard benchmarks. |
| Tasks | |
| Published | 2017-12-07 |
| URL | http://arxiv.org/abs/1712.02501v2 |
| http://arxiv.org/pdf/1712.02501v2.pdf | |
| PWC | https://paperswithcode.com/paper/cnns-are-globally-optimal-given-multi-layer |
| Repo | |
| Framework | |
HiNet: Hierarchical Classification with Neural Network
| Title | HiNet: Hierarchical Classification with Neural Network |
| Authors | Zhenzhou Wu, Sean Saito |
| Abstract | Traditionally, classifying large hierarchical labels with more than 10000 distinct traces can only be achieved with flatten labels. Although flatten labels is feasible, it misses the hierarchical information in the labels. Hierarchical models like HSVM by \cite{vural2004hierarchical} becomes impossible to train because of the sheer number of SVMs in the whole architecture. We developed a hierarchical architecture based on neural networks that is simple to train. Also, we derived an inference algorithm that can efficiently infer the MAP (maximum a posteriori) trace guaranteed by our theorems. Furthermore, the complexity of the model is only $O(n^2)$ compared to $O(n^h)$ in a flatten model, where $h$ is the height of the hierarchy. |
| Tasks | |
| Published | 2017-05-31 |
| URL | http://arxiv.org/abs/1705.11105v2 |
| http://arxiv.org/pdf/1705.11105v2.pdf | |
| PWC | https://paperswithcode.com/paper/hinet-hierarchical-classification-with-neural |
| Repo | |
| Framework | |
Representations of Sound in Deep Learning of Audio Features from Music
| Title | Representations of Sound in Deep Learning of Audio Features from Music |
| Authors | Sergey Shuvaev, Hamza Giaffar, Alexei A. Koulakov |
| Abstract | The work of a single musician, group or composer can vary widely in terms of musical style. Indeed, different stylistic elements, from performance medium and rhythm to harmony and texture, are typically exploited and developed across an artist’s lifetime. Yet, there is often a discernable character to the work of, for instance, individual composers at the perceptual level - an experienced listener can often pick up on subtle clues in the music to identify the composer or performer. Here we suggest that a convolutional network may learn these subtle clues or features given an appropriate representation of the music. In this paper, we apply a deep convolutional neural network to a large audio dataset and empirically evaluate its performance on audio classification tasks. Our trained network demonstrates accurate performance on such classification tasks when presented with 5 s examples of music obtained by simple transformations of the raw audio waveform. A particularly interesting example is the spectral representation of music obtained by application of a logarithmically spaced filter bank, mirroring the early stages of auditory signal transduction in mammals. The most successful representation of music to facilitate discrimination was obtained via a random matrix transform (RMT). Networks based on logarithmic filter banks and RMT were able to correctly guess the one composer out of 31 possibilities in 68 and 84 percent of cases respectively. |
| Tasks | Audio Classification |
| Published | 2017-12-08 |
| URL | http://arxiv.org/abs/1712.02898v1 |
| http://arxiv.org/pdf/1712.02898v1.pdf | |
| PWC | https://paperswithcode.com/paper/representations-of-sound-in-deep-learning-of |
| Repo | |
| Framework | |
Utilizing Lexical Similarity between Related, Low-resource Languages for Pivot-based SMT
| Title | Utilizing Lexical Similarity between Related, Low-resource Languages for Pivot-based SMT |
| Authors | Anoop Kunchukuttan, Maulik Shah, Pradyot Prakash, Pushpak Bhattacharyya |
| Abstract | We investigate pivot-based translation between related languages in a low resource, phrase-based SMT setting. We show that a subword-level pivot-based SMT model using a related pivot language is substantially better than word and morpheme-level pivot models. It is also highly competitive with the best direct translation model, which is encouraging as no direct source-target training corpus is used. We also show that combining multiple related language pivot models can rival a direct translation model. Thus, the use of subwords as translation units coupled with multiple related pivot languages can compensate for the lack of a direct parallel corpus. |
| Tasks | |
| Published | 2017-02-23 |
| URL | http://arxiv.org/abs/1702.07203v2 |
| http://arxiv.org/pdf/1702.07203v2.pdf | |
| PWC | https://paperswithcode.com/paper/utilizing-lexical-similarity-between-related |
| Repo | |
| Framework | |
Solving the Brachistochrone Problem by an Influence Diagram
| Title | Solving the Brachistochrone Problem by an Influence Diagram |
| Authors | Jiří Vomlel |
| Abstract | Influence diagrams are a decision-theoretic extension of probabilistic graphical models. In this paper we show how they can be used to solve the Brachistochrone problem. We present results of numerical experiments on this problem, compare the solution provided by the influence diagram with the optimal solution. The R code used for the experiments is presented in the Appendix. |
| Tasks | |
| Published | 2017-02-04 |
| URL | http://arxiv.org/abs/1702.02032v1 |
| http://arxiv.org/pdf/1702.02032v1.pdf | |
| PWC | https://paperswithcode.com/paper/solving-the-brachistochrone-problem-by-an |
| Repo | |
| Framework | |
