Paper Group ANR 418
Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GAN. Machine Learning for Public Administration Research, with Application to Organizational Reputation. Subspace Embedding and Linear Regression with Orlicz Norm. SurReal: enhancing Surgical simulation Realism using style transfer. A punishment voting algorithm based on super …
Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GAN
Title | Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GAN |
Authors | Shervin Minaee, Amirali Abdolrashidi |
Abstract | Generating iris images which look realistic is both an interesting and challenging problem. Most of the classical statistical models are not powerful enough to capture the complicated texture representation in iris images, and therefore fail to generate iris images which look realistic. In this work, we present a machine learning framework based on generative adversarial network (GAN), which is able to generate iris images sampled from a prior distribution (learned from a set of training images). We apply this framework to two popular iris databases, and generate images which look very realistic, and similar to the image distribution in those databases. Through experimental results, we show that the generated iris images have a good diversity, and are able to capture different part of the prior distribution. |
Tasks | |
Published | 2018-12-12 |
URL | http://arxiv.org/abs/1812.04822v3 |
http://arxiv.org/pdf/1812.04822v3.pdf | |
PWC | https://paperswithcode.com/paper/iris-gan-learning-to-generate-realistic-iris |
Repo | |
Framework | |
Machine Learning for Public Administration Research, with Application to Organizational Reputation
Title | Machine Learning for Public Administration Research, with Application to Organizational Reputation |
Authors | L. Jason Anastasopoulos, Andrew B. Whitford |
Abstract | Machine learning methods have gained a great deal of popularity in recent years among public administration scholars and practitioners. These techniques open the door to the analysis of text, image and other types of data that allow us to test foundational theories of public administration and to develop new theories. Despite the excitement surrounding machine learning methods, clarity regarding their proper use and potential pitfalls is lacking. This paper attempts to fill this gap in the literature through providing a machine learning “guide to practice” for public administration scholars and practitioners. Here, we take a foundational view of machine learning and describe how these methods can enrich public administration research and practice through their ability develop new measures, tap into new sources of data and conduct statistical inference and causal inference in a principled manner. We then turn our attention to the pitfalls of using these methods such as unvalidated measures and lack of interpretability. Finally, we demonstrate how machine learning techniques can help us learn about organizational reputation in federal agencies through an illustrated example using tweets from 13 executive federal agencies. |
Tasks | Causal Inference |
Published | 2018-05-11 |
URL | http://arxiv.org/abs/1805.05409v2 |
http://arxiv.org/pdf/1805.05409v2.pdf | |
PWC | https://paperswithcode.com/paper/machine-learning-for-public-administration |
Repo | |
Framework | |
Subspace Embedding and Linear Regression with Orlicz Norm
Title | Subspace Embedding and Linear Regression with Orlicz Norm |
Authors | Alexandr Andoni, Chengyu Lin, Ying Sheng, Peilin Zhong, Ruiqi Zhong |
Abstract | We consider a generalization of the classic linear regression problem to the case when the loss is an Orlicz norm. An Orlicz norm is parameterized by a non-negative convex function $G:\mathbb{R}+\rightarrow\mathbb{R}+$ with $G(0)=0$: the Orlicz norm of a vector $x\in\mathbb{R}^n$ is defined as $ \x_G=\inf\left{\alpha>0\large\mid\sum{i=1}^n G(x_i/\alpha)\leq 1\right}. $ We consider the cases where the function $G(\cdot)$ grows subquadratically. Our main result is based on a new oblivious embedding which embeds the column space of a given matrix $A\in\mathbb{R}^{n\times d}$ with Orlicz norm into a lower dimensional space with $\ell_2$ norm. Specifically, we show how to efficiently find an embedding matrix $S\in\mathbb{R}^{m\times n},m<n$ such that $\forall x\in\mathbb{R}^{d},\Omega(1/(d\log n)) \cdot \Ax_G\leq \SAx_2\leq O(d^2\log n) \cdot \Ax_G.$ By applying this subspace embedding technique, we show an approximation algorithm for the regression problem $\min{x\in\mathbb{R}^d} \Ax-b_G$, up to a $O(d\log^2 n)$ factor. As a further application of our techniques, we show how to also use them to improve on the algorithm for the $\ell_p$ low rank matrix approximation problem for $1\leq p<2$. |
Tasks | |
Published | 2018-06-17 |
URL | http://arxiv.org/abs/1806.06430v1 |
http://arxiv.org/pdf/1806.06430v1.pdf | |
PWC | https://paperswithcode.com/paper/subspace-embedding-and-linear-regression-with |
Repo | |
Framework | |
SurReal: enhancing Surgical simulation Realism using style transfer
Title | SurReal: enhancing Surgical simulation Realism using style transfer |
Authors | Imanol Luengo, Evangello Flouty, Petros Giataganas, Piyamate Wisanuvej, Jean Nehme, Danail Stoyanov |
Abstract | Surgical simulation is an increasingly important element of surgical education. Using simulation can be a means to address some of the significant challenges in developing surgical skills with limited time and resources. The photo-realistic fidelity of simulations is a key feature that can improve the experience and transfer ratio of trainees. In this paper, we demonstrate how we can enhance the visual fidelity of existing surgical simulation by performing style transfer of multi-class labels from real surgical video onto synthetic content. We demonstrate our approach on simulations of cataract surgery using real data labels from an existing public dataset. Our results highlight the feasibility of the approach and also the powerful possibility to extend this technique to incorporate additional temporal constraints and to different applications. |
Tasks | Style Transfer |
Published | 2018-11-07 |
URL | http://arxiv.org/abs/1811.02946v1 |
http://arxiv.org/pdf/1811.02946v1.pdf | |
PWC | https://paperswithcode.com/paper/surreal-enhancing-surgical-simulation-realism |
Repo | |
Framework | |
A punishment voting algorithm based on super categories construction for acoustic scene classification
Title | A punishment voting algorithm based on super categories construction for acoustic scene classification |
Authors | Weiping Zheng, Zhenyao Mo, Jiantao Yi |
Abstract | In acoustic scene classification researches, audio segment is usually split into multiple samples. Majority voting is then utilized to ensemble the results of the samples. In this paper, we propose a punishment voting algorithm based on the super categories construction method for acoustic scene classification. Specifically, we propose a DenseNet-like model as the base classifier. The base classifier is trained by the CQT spectrograms generated from the raw audio segments. Taking advantage of the results of the base classifier, we propose a super categories construction method using the spectral clustering. Super classifiers corresponding to the constructed super categories are further trained. Finally, the super classifiers are utilized to enhance the majority voting of the base classifier by punishment voting. Experiments show that the punishment voting obviously improves the performances on both the DCASE2017 Development dataset and the LITIS Rouen dataset. |
Tasks | Acoustic Scene Classification, Scene Classification |
Published | 2018-07-11 |
URL | http://arxiv.org/abs/1807.04073v1 |
http://arxiv.org/pdf/1807.04073v1.pdf | |
PWC | https://paperswithcode.com/paper/a-punishment-voting-algorithm-based-on-super |
Repo | |
Framework | |
Adversarial Learning of Label Dependency: A Novel Framework for Multi-class Classification
Title | Adversarial Learning of Label Dependency: A Novel Framework for Multi-class Classification |
Authors | Che-Ping Tsai, Hung-Yi Lee |
Abstract | Recent work has shown that exploiting relations between labels improves the performance of multi-label classification. We propose a novel framework based on generative adversarial networks (GANs) to model label dependency. The discriminator learns to model label dependency by discriminating real and generated label sets. To fool the discriminator, the classifier, or generator, learns to generate label sets with dependencies close to real data. Extensive experiments and comparisons on two large-scale image classification benchmark datasets (MS-COCO and NUS-WIDE) show that the discriminator improves generalization ability for different kinds of models |
Tasks | Image Classification, Multi-Label Classification |
Published | 2018-11-12 |
URL | http://arxiv.org/abs/1811.04689v1 |
http://arxiv.org/pdf/1811.04689v1.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-learning-of-label-dependency-a |
Repo | |
Framework | |
Detecting Speech Act Types in Developer Question/Answer Conversations During Bug Repair
Title | Detecting Speech Act Types in Developer Question/Answer Conversations During Bug Repair |
Authors | Andrew Wood, Paige Rodeghero, Ameer Armaly, Collin McMillan |
Abstract | This paper targets the problem of speech act detection in conversations about bug repair. We conduct a “Wizard of Oz” experiment with 30 professional programmers, in which the programmers fix bugs for two hours, and use a simulated virtual assistant for help. Then, we use an open coding manual annotation procedure to identify the speech act types in the conversations. Finally, we train and evaluate a supervised learning algorithm to automatically detect the speech act types in the conversations. In 30 two-hour conversations, we made 2459 annotations and uncovered 26 speech act types. Our automated detection achieved 69% precision and 50% recall. The key application of this work is to advance the state of the art for virtual assistants in software engineering. Virtual assistant technology is growing rapidly, though applications in software engineering are behind those in other areas, largely due to a lack of relevant data and experiments. This paper targets this problem in the area of developer Q/A conversations about bug repair. |
Tasks | |
Published | 2018-06-13 |
URL | http://arxiv.org/abs/1806.05130v3 |
http://arxiv.org/pdf/1806.05130v3.pdf | |
PWC | https://paperswithcode.com/paper/detecting-speech-act-types-in-developer |
Repo | |
Framework | |
Learning Disentangled Representations of Texts with Application to Biomedical Abstracts
Title | Learning Disentangled Representations of Texts with Application to Biomedical Abstracts |
Authors | Sarthak Jain, Edward Banner, Jan-Willem van de Meent, Iain J. Marshall, Byron C. Wallace |
Abstract | We propose a method for learning disentangled representations of texts that code for distinct and complementary aspects, with the aim of affording efficient model transfer and interpretability. To induce disentangled embeddings, we propose an adversarial objective based on the (dis)similarity between triplets of documents with respect to specific aspects. Our motivating application is embedding biomedical abstracts describing clinical trials in a manner that disentangles the populations, interventions, and outcomes in a given trial. We show that our method learns representations that encode these clinically salient aspects, and that these can be effectively used to perform aspect-specific retrieval. We demonstrate that the approach generalizes beyond our motivating application in experiments on two multi-aspect review corpora. |
Tasks | |
Published | 2018-04-19 |
URL | http://arxiv.org/abs/1804.07212v2 |
http://arxiv.org/pdf/1804.07212v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-disentangled-representations-of |
Repo | |
Framework | |
Convolutional Collaborative Filter Network for Video Based Recommendation Systems
Title | Convolutional Collaborative Filter Network for Video Based Recommendation Systems |
Authors | Cheng-Kang Hsieh, Miguel Campo, Abhinav Taliyan, Matt Nickens, Mitkumar Pandya, JJ Espinoza |
Abstract | This analysis explores the temporal sequencing of objects in a movie trailer. Temporal sequencing of objects in a movie trailer (e.g., a long shot of an object vs intermittent short shots) can convey information about the type of movie, plot of the movie, role of the main characters, and the filmmakers cinematographic choices. When combined with historical customer data, sequencing analysis can be used to improve predictions of customer behavior. E.g., a customer buys tickets to a new movie and maybe the customer has seen movies in the past that contained similar sequences. To explore object sequencing in movie trailers, we propose a video convolutional network to capture actions and scenes that are predictive of customers’ preferences. The model learns the specific nature of sequences for different types of objects (e.g., cars vs faces), and the role of sequences in predicting customer future behavior. We show how such a temporal-aware model outperforms simple feature pooling methods proposed in our previous works and, importantly, demonstrate the additional model explain-ability allowed by such a model. |
Tasks | Recommendation Systems |
Published | 2018-10-18 |
URL | http://arxiv.org/abs/1810.08189v2 |
http://arxiv.org/pdf/1810.08189v2.pdf | |
PWC | https://paperswithcode.com/paper/convolutional-collaborative-filter-network |
Repo | |
Framework | |
Can Who-Edits-What Predict Edit Survival?
Title | Can Who-Edits-What Predict Edit Survival? |
Authors | Ali Batuhan Yardım, Victor Kristof, Lucas Maystre, Matthias Grossglauser |
Abstract | As the number of contributors to online peer-production systems grows, it becomes increasingly important to predict whether the edits that users make will eventually be beneficial to the project. Existing solutions either rely on a user reputation system or consist of a highly specialized predictor that is tailored to a specific peer-production system. In this work, we explore a different point in the solution space that goes beyond user reputation but does not involve any content-based feature of the edits. We view each edit as a game between the editor and the component of the project. We posit that the probability that an edit is accepted is a function of the editor’s skill, of the difficulty of editing the component and of a user-component interaction term. Our model is broadly applicable, as it only requires observing data about who makes an edit, what the edit affects and whether the edit survives or not. We apply our model on Wikipedia and the Linux kernel, two examples of large-scale peer-production systems, and we seek to understand whether it can effectively predict edit survival: in both cases, we provide a positive answer. Our approach significantly outperforms those based solely on user reputation and bridges the gap with specialized predictors that use content-based features. It is simple to implement, computationally inexpensive, and in addition it enables us to discover interesting structure in the data. |
Tasks | |
Published | 2018-01-12 |
URL | http://arxiv.org/abs/1801.04159v2 |
http://arxiv.org/pdf/1801.04159v2.pdf | |
PWC | https://paperswithcode.com/paper/can-who-edits-what-predict-edit-survival |
Repo | |
Framework | |
Kernel-based Outlier Detection using the Inverse Christoffel Function
Title | Kernel-based Outlier Detection using the Inverse Christoffel Function |
Authors | Armin Askari, Forest Yang, Laurent El Ghaoui |
Abstract | Outlier detection methods have become increasingly relevant in recent years due to increased security concerns and because of its vast application to different fields. Recently, Pauwels and Lasserre (2016) noticed that the sublevel sets of the inverse Christoffel function accurately depict the shape of a cloud of data using a sum-of-squares polynomial and can be used to perform outlier detection. In this work, we propose a kernelized variant of the inverse Christoffel function that makes it computationally tractable for data sets with a large number of features. We compare our approach to current methods on 15 different data sets and achieve the best average area under the precision recall curve (AUPRC) score, the best average rank and the lowest root mean square deviation. |
Tasks | Outlier Detection |
Published | 2018-06-18 |
URL | http://arxiv.org/abs/1806.06775v1 |
http://arxiv.org/pdf/1806.06775v1.pdf | |
PWC | https://paperswithcode.com/paper/kernel-based-outlier-detection-using-the |
Repo | |
Framework | |
Phase transition in the knapsack problem
Title | Phase transition in the knapsack problem |
Authors | Nitin Yadav, Carsten Murawski, Sebastian Sardina, Peter Bossaerts |
Abstract | We examine the phase transition phenomenon for the Knapsack problem from both a computational and a human perspective. We first provide, via an empirical and a theoretical analysis, a characterization of the phenomenon in terms of two instance properties; normalised capacity and normalised profit. Then, we show evidence that average time spent by human decision makers in solving an instance peaks near the phase transition. Given the ubiquity of the Knapsack problem in every-day life, a better understanding of its structure can improve our understanding not only of computational techniques but also of human behavior, including the use and development of heuristics and occurrence of biases. |
Tasks | |
Published | 2018-06-26 |
URL | http://arxiv.org/abs/1806.10244v1 |
http://arxiv.org/pdf/1806.10244v1.pdf | |
PWC | https://paperswithcode.com/paper/phase-transition-in-the-knapsack-problem |
Repo | |
Framework | |
Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring
Title | Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring |
Authors | Raghav Menon, Herman Kamper, John Quinn, Thomas Niesler |
Abstract | We use dynamic time warping (DTW) as supervision for training a convolutional neural network (CNN) based keyword spotting system using a small set of spoken isolated keywords. The aim is to allow rapid deployment of a keyword spotting system in a new language to support urgent United Nations (UN) relief programmes in parts of Africa where languages are extremely under-resourced and the development of annotated speech resources is infeasible. First, we use 1920 recorded keywords (40 keyword types, 34 minutes of speech) as exemplars in a DTW-based template matching system and apply it to untranscribed broadcast speech. Then, we use the resulting DTW scores as targets to train a CNN on the same unlabelled speech. In this way we use just 34 minutes of labelled speech, but leverage a large amount of unlabelled data for training. While the resulting CNN keyword spotter cannot match the performance of the DTW-based system, it substantially outperforms a CNN classifier trained only on the keywords, improving the area under the ROC curve from 0.54 to 0.64. Because our CNN system is several orders of magnitude faster at runtime than the DTW system, it represents the most viable keyword spotter on this extremely limited dataset. |
Tasks | Keyword Spotting |
Published | 2018-06-25 |
URL | http://arxiv.org/abs/1806.09374v1 |
http://arxiv.org/pdf/1806.09374v1.pdf | |
PWC | https://paperswithcode.com/paper/fast-asr-free-and-almost-zero-resource |
Repo | |
Framework | |
Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition
Title | Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition |
Authors | Pavel Denisov, Ngoc Thang Vu, Marc Ferras Font |
Abstract | In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with close-talk clean speech to the new recording conditions using untranscribed adaptation data. Our experimental results on Italian SPEECON data set show that our proposed method achieves 19.8% relative word error rate (WER) reduction compared to the unadapted models. Furthermore, this adaptation method is beneficial even when performed on data from another language (i.e. French) giving 12.6% relative WER reduction. |
Tasks | Domain Adaptation, Robust Speech Recognition, Speech Recognition, Unsupervised Domain Adaptation |
Published | 2018-07-30 |
URL | http://arxiv.org/abs/1807.11284v1 |
http://arxiv.org/pdf/1807.11284v1.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-by-adversarial |
Repo | |
Framework | |
Robust Object Tracking with Crow Search Optimized Multi-cue Particle Filter
Title | Robust Object Tracking with Crow Search Optimized Multi-cue Particle Filter |
Authors | Kapil Sharma, Gurjit Singh Walia, Ashish Kumar, Astitwa Saxena, Kuldeep Singh |
Abstract | Particle Filter(PF) is used extensively for estimation of target Non-linear and Non-gaussian state. However, its performance suffers due to inherent problem of sample degeneracy and impoverishment. In order to address this, we propose a novel resampling method based upon Crow Search Optimization to overcome low performing particles detected as outlier. Proposed outlier detection mechanism with transductive reliability achieve faster convergence of proposed PF tracking framework. In addition, we present an adaptive fuzzy fusion model to integrate multi-cue extracted for each evaluated particle. Automatic boosting and suppression of particles using proposed fusion model not only enhances performance of resampling method but also achieve optimal state estimation. Performance of the proposed tracker is evaluated over 12 benchmark video sequences and compared with state-of-the-art solutions. Qualitative and quantitative results reveals that the proposed tracker not only outperforms existing solutions but also efficiently handle various tracking challenges. On average of outcome, we achieve CLE of 7.98 and F-measure of 0.734. |
Tasks | Object Tracking, Outlier Detection |
Published | 2018-06-11 |
URL | http://arxiv.org/abs/1806.03753v1 |
http://arxiv.org/pdf/1806.03753v1.pdf | |
PWC | https://paperswithcode.com/paper/robust-object-tracking-with-crow-search |
Repo | |
Framework | |