July 28, 2019

3326 words 16 mins read

Paper Group ANR 443

The Expanding Approvals Rule: Improving Proportional Representation and Monotonicity. Bringing Impressionism to Life with Neural Style Transfer in Come Swim. Inter-Session Modeling for Session-Based Recommendation. Sensor Synthesis for POMDPs with Reachability Objectives. The impossibility of “fairness”: a generalized impossibility result for decis …

The Expanding Approvals Rule: Improving Proportional Representation and Monotonicity


Title	The Expanding Approvals Rule: Improving Proportional Representation and Monotonicity
Authors	Haris Aziz, Barton Lee
Abstract	Proportional representation (PR) is often discussed in voting settings as a major desideratum. For the past century or so, it is common both in practice and in the academic literature to jump to single transferable vote (STV) as the solution for achieving PR. Some of the most prominent electoral reform movements around the globe are pushing for the adoption of STV. It has been termed a major open problem to design a voting rule that satisfies the same PR properties as STV and better monotonicity properties. In this paper, we first present a taxonomy of proportional representation axioms for general weak order preferences, some of which generalise and strengthen previously introduced concepts. We then present a rule called Expanding Approvals Rule (EAR) that satisfies properties stronger than the central PR axiom satisfied by STV, can handle indifferences in a convenient and computationally efficient manner, and also satisfies better candidate monotonicity properties. In view of this, our proposed rule seems to be a compelling solution for achieving proportional representation in voting settings.
Tasks
Published	2017-08-25
URL	http://arxiv.org/abs/1708.07580v2
PDF	http://arxiv.org/pdf/1708.07580v2.pdf
PWC	https://paperswithcode.com/paper/the-expanding-approvals-rule-improving
Repo
Framework

Bringing Impressionism to Life with Neural Style Transfer in Come Swim


Title	Bringing Impressionism to Life with Neural Style Transfer in Come Swim
Authors	Bhautik Joshi, Kristen Stewart, David Shapiro
Abstract	Neural Style Transfer is a striking, recently-developed technique that uses neural networks to artistically redraw an image in the style of a source style image. This paper explores the use of this technique in a production setting, applying Neural Style Transfer to redraw key scenes in ‘Come Swim’ in the style of the impressionistic painting that inspired the film. We document how the technique can be driven within the framework of an iterative creative process to achieve a desired look, and propose a mapping of the broad parameter space to a key set of creative controls. We hope that this mapping can provide insights into priorities for future research.
Tasks	Style Transfer
Published	2017-01-18
URL	http://arxiv.org/abs/1701.04928v1
PDF	http://arxiv.org/pdf/1701.04928v1.pdf
PWC	https://paperswithcode.com/paper/bringing-impressionism-to-life-with-neural
Repo
Framework

Inter-Session Modeling for Session-Based Recommendation


Title	Inter-Session Modeling for Session-Based Recommendation
Authors	Massimiliano Ruocco, Ole Steinar Lillestøl Skrede, Helge Langseth
Abstract	In recent years, research has been done on applying Recurrent Neural Networks (RNNs) as recommender systems. Results have been promising, especially in the session-based setting where RNNs have been shown to outperform state-of-the-art models. In many of these experiments, the RNN could potentially improve the recommendations by utilizing information about the user’s past sessions, in addition to its own interactions in the current session. A problem for session-based recommendation, is how to produce accurate recommendations at the start of a session, before the system has learned much about the user’s current interests. We propose a novel approach that extends a RNN recommender to be able to process the user’s recent sessions, in order to improve recommendations. This is done by using a second RNN to learn from recent sessions, and predict the user’s interest in the current session. By feeding this information to the original RNN, it is able to improve its recommendations. Our experiments on two different datasets show that the proposed approach can significantly improve recommendations throughout the sessions, compared to a single RNN working only on the current session. The proposed model especially improves recommendations at the start of sessions, and is therefore able to deal with the cold start problem within sessions.
Tasks	Recommendation Systems, Session-Based Recommendations
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07506v1
PDF	http://arxiv.org/pdf/1706.07506v1.pdf
PWC	https://paperswithcode.com/paper/inter-session-modeling-for-session-based
Repo
Framework

Sensor Synthesis for POMDPs with Reachability Objectives


Title	Sensor Synthesis for POMDPs with Reachability Objectives
Authors	Krishnendu Chatterjee, Martin Chmelik, Ufuk Topcu
Abstract	Partially observable Markov decision processes (POMDPs) are widely used in probabilistic planning problems in which an agent interacts with an environment using noisy and imprecise sensors. We study a setting in which the sensors are only partially defined and the goal is to synthesize “weakest” additional sensors, such that in the resulting POMDP, there is a small-memory policy for the agent that almost-surely (with probability~1) satisfies a reachability objective. We show that the problem is NP-complete, and present a symbolic algorithm by encoding the problem into SAT instances. We illustrate trade-offs between the amount of memory of the policy and the number of additional sensors on a simple example. We have implemented our approach and consider three classical POMDP examples from the literature, and show that in all the examples the number of sensors can be significantly decreased (as compared to the existing solutions in the literature) without increasing the complexity of the policies.
Tasks
Published	2017-09-29
URL	http://arxiv.org/abs/1710.00675v1
PDF	http://arxiv.org/pdf/1710.00675v1.pdf
PWC	https://paperswithcode.com/paper/sensor-synthesis-for-pomdps-with-reachability
Repo
Framework

The impossibility of “fairness”: a generalized impossibility result for decisions


Title	The impossibility of “fairness”: a generalized impossibility result for decisions
Authors	Thomas Miconi
Abstract	Various measures can be used to estimate bias or unfairness in a predictor. Previous work has already established that some of these measures are incompatible with each other. Here we show that, when groups differ in prevalence of the predicted event, several intuitive, reasonable measures of fairness (probability of positive prediction given occurrence or non-occurrence; probability of occurrence given prediction or non-prediction; and ratio of predictions over occurrences for each group) are all mutually exclusive: if one of them is equal among groups, the other two must differ. The only exceptions are for perfect, or trivial (always-positive or always-negative) predictors. As a consequence, any non-perfect, non-trivial predictor must necessarily be “unfair” under two out of three reasonable sets of criteria. This result readily generalizes to a wide range of well-known statistical quantities (sensitivity, specificity, false positive rate, precision, etc.), all of which can be divided into three mutually exclusive groups. Importantly, The results applies to all predictors, whether algorithmic or human. We conclude with possible ways to handle this effect when assessing and designing prediction methods.
Tasks
Published	2017-07-05
URL	http://arxiv.org/abs/1707.01195v3
PDF	http://arxiv.org/pdf/1707.01195v3.pdf
PWC	https://paperswithcode.com/paper/the-impossibility-of-fairness-a-generalized
Repo
Framework

Sub-Pixel Registration of Wavelet-Encoded Images


Title	Sub-Pixel Registration of Wavelet-Encoded Images
Authors	Vildan Atalay Aydin, Hassan Foroosh
Abstract	Sub-pixel registration is a crucial step for applications such as super-resolution in remote sensing, motion compensation in magnetic resonance imaging, and non-destructive testing in manufacturing, to name a few. Recently, these technologies have been trending towards wavelet encoded imaging and sparse/compressive sensing. The former plays a crucial role in reducing imaging artifacts, while the latter significantly increases the acquisition speed. In view of these new emerging needs for applications of wavelet encoded imaging, we propose a sub-pixel registration method that can achieve direct wavelet domain registration from a sparse set of coefficients. We make the following contributions: (i) We devise a method of decoupling scale, rotation, and translation parameters in the Haar wavelet domain, (ii) We derive explicit mathematical expressions that define in-band sub-pixel registration in terms of wavelet coefficients, (iii) Using the derived expressions, we propose an approach to achieve in-band subpixel registration, avoiding back and forth transformations. (iv) Our solution remains highly accurate even when a sparse set of coefficients are used, which is due to localization of signals in a sparse set of wavelet coefficients. We demonstrate the accuracy of our method, and show that it outperforms the state-of-the-art on simulated and real data, even when the data is sparse.
Tasks	Compressive Sensing, Motion Compensation, Super-Resolution
Published	2017-05-01
URL	http://arxiv.org/abs/1705.00430v1
PDF	http://arxiv.org/pdf/1705.00430v1.pdf
PWC	https://paperswithcode.com/paper/sub-pixel-registration-of-wavelet-encoded
Repo
Framework

Boltzmann machines for time-series


Title	Boltzmann machines for time-series
Authors	Takayuki Osogami
Abstract	We review Boltzmann machines extended for time-series. These models often have recurrent structure, and back propagration through time (BPTT) is used to learn their parameters. The per-step computational complexity of BPTT in online learning, however, grows linearly with respect to the length of preceding time-series (i.e., learning rule is not local in time), which limits the applicability of BPTT in online learning. We then review dynamic Boltzmann machines (DyBMs), whose learning rule is local in time. DyBM’s learning rule relates to spike-timing dependent plasticity (STDP), which has been postulated and experimentally confirmed for biological neural networks.
Tasks	Time Series
Published	2017-08-20
URL	http://arxiv.org/abs/1708.06004v3
PDF	http://arxiv.org/pdf/1708.06004v3.pdf
PWC	https://paperswithcode.com/paper/boltzmann-machines-for-time-series
Repo
Framework

Enhanced Facial Recognition Framework based on Skin Tone and False Alarm Rejection


Title	Enhanced Facial Recognition Framework based on Skin Tone and False Alarm Rejection
Authors	Ali Sharifara, Mohd Shafry Mohd Rahim, Farhad Navabifar, Dylan Ebert, Amir Ghaderi, Michalis Papakostas
Abstract	Face detection is one of the challenging tasks in computer vision. Human face detection plays an essential role in the first stage of face processing applications such as face recognition, face tracking, image database management, etc. In these applications, face objects often come from an inconsequential part of images that contain variations, namely different illumination, poses, and occlusion. These variations can decrease face detection rate noticeably. Most existing face detection approaches are not accurate, as they have not been able to resolve unstructured images due to large appearance variations and can only detect human faces under one particular variation. Existing frameworks of face detection need enhancements to detect human faces under the stated variations to improve detection rate and reduce detection time. In this study, an enhanced face detection framework is proposed to improve detection rate based on skin color and provide a validation process. A preliminary segmentation of the input images based on skin color can significantly reduce search space and accelerate the process of human face detection. The primary detection is based on Haar-like features and the Adaboost algorithm. A validation process is introduced to reject non-face objects, which might occur during the face detection process. The validation process is based on two-stage Extended Local Binary Patterns. The experimental results on the CMU-MIT and Caltech 10000 datasets over a wide range of facial variations in different colors, positions, scales, and lighting conditions indicated a successful face detection rate.
Tasks	Face Detection, Face Recognition
Published	2017-02-14
URL	http://arxiv.org/abs/1702.04377v1
PDF	http://arxiv.org/pdf/1702.04377v1.pdf
PWC	https://paperswithcode.com/paper/enhanced-facial-recognition-framework-based
Repo
Framework

A Deep Policy Inference Q-Network for Multi-Agent Systems


Title	A Deep Policy Inference Q-Network for Multi-Agent Systems
Authors	Zhang-Wei Hong, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Chun-Yi Lee
Abstract	We present DPIQN, a deep policy inference Q-network that targets multi-agent systems composed of controllable agents, collaborators, and opponents that interact with each other. We focus on one challenging issue in such systems—modeling agents with varying strategies—and propose to employ “policy features” learned from raw observations (e.g., raw images) of collaborators and opponents by inferring their policies. DPIQN incorporates the learned policy features as a hidden vector into its own deep Q-network (DQN), such that it is able to predict better Q values for the controllable agents than the state-of-the-art deep reinforcement learning models. We further propose an enhanced version of DPIQN, called deep recurrent policy inference Q-network (DRPIQN), for handling partial observability. Both DPIQN and DRPIQN are trained by an adaptive training procedure, which adjusts the network’s attention to learn the policy features and its own Q-values at different phases of the training process. We present a comprehensive analysis of DPIQN and DRPIQN, and highlight their effectiveness and generalizability in various multi-agent settings. Our models are evaluated in a classic soccer game involving both competitive and collaborative scenarios. Experimental results performed on 1 vs. 1 and 2 vs. 2 games show that DPIQN and DRPIQN demonstrate superior performance to the baseline DQN and deep recurrent Q-network (DRQN) models. We also explore scenarios in which collaborators or opponents dynamically change their policies, and show that DPIQN and DRPIQN do lead to better overall performance in terms of stability and mean scores.
Tasks
Published	2017-12-21
URL	http://arxiv.org/abs/1712.07893v2
PDF	http://arxiv.org/pdf/1712.07893v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-policy-inference-q-network-for-multi
Repo
Framework

Pooling Facial Segments to Face: The Shallow and Deep Ends


Title	Pooling Facial Segments to Face: The Shallow and Deep Ends
Authors	Upal Mahbub, Sayantan Sarkar, Rama Chellappa
Abstract	Generic face detection algorithms do not perform very well in the mobile domain due to significant presence of occluded and partially visible faces. One promising technique to handle the challenge of partial faces is to design face detectors based on facial segments. In this paper two such face detectors namely, SegFace and DeepSegFace, are proposed that detect the presence of a face given arbitrary combinations of certain face segments. Both methods use proposals from facial segments as input that are found using weak boosted classifiers. SegFace is a shallow and fast algorithm using traditional features, tailored for situations where real time constraints must be satisfied. On the other hand, DeepSegFace is a more powerful algorithm based on a deep convolutional neutral network (DCNN) architecture. DeepSegFace offers certain advantages over other DCNN-based face detectors as it requires relatively little amount of data to train by utilizing a novel data augmentation scheme and is very robust to occlusion by design. Extensive experiments show the superiority of the proposed methods, specially DeepSegFace, over other state-of-the-art face detectors in terms of precision-recall and ROC curve on two mobile face datasets.
Tasks	Data Augmentation, Face Detection
Published	2017-01-29
URL	http://arxiv.org/abs/1701.08341v1
PDF	http://arxiv.org/pdf/1701.08341v1.pdf
PWC	https://paperswithcode.com/paper/pooling-facial-segments-to-face-the-shallow
Repo
Framework

A Machine Learning Alternative to P-values


Title	A Machine Learning Alternative to P-values
Authors	Min Lu, Hemant Ishwaran
Abstract	This paper presents an alternative approach to p-values in regression settings. This approach, whose origins can be traced to machine learning, is based on the leave-one-out bootstrap for prediction error. In machine learning this is called the out-of-bag (OOB) error. To obtain the OOB error for a model, one draws a bootstrap sample and fits the model to the in-sample data. The out-of-sample prediction error for the model is obtained by calculating the prediction error for the model using the out-of-sample data. Repeating and averaging yields the OOB error, which represents a robust cross-validated estimate of the accuracy of the underlying model. By a simple modification to the bootstrap data involving “noising up” a variable, the OOB method yields a variable importance (VIMP) index, which directly measures how much a specific variable contributes to the prediction precision of a model. VIMP provides a scientifically interpretable measure of the effect size of a variable, we call the “predictive effect size”, that holds whether the researcher’s model is correct or not, unlike the p-value whose calculation is based on the assumed correctness of the model. We also discuss a marginal VIMP index, also easily calculated, which measures the marginal effect of a variable, or what we call “the discovery effect”. The OOB procedure can be applied to both parametric and nonparametric regression models and requires only that the researcher can repeatedly fit their model to bootstrap and modified bootstrap data. We illustrate this approach on a survival data set involving patients with systolic heart failure and to a simulated survival data set where the model is incorrectly specified to illustrate its robustness to model misspecification.
Tasks
Published	2017-01-18
URL	http://arxiv.org/abs/1701.04944v5
PDF	http://arxiv.org/pdf/1701.04944v5.pdf
PWC	https://paperswithcode.com/paper/a-machine-learning-alternative-to-p-values
Repo
Framework

Hierarchy Influenced Differential Evolution: A Motor Operation Inspired Approach


Title	Hierarchy Influenced Differential Evolution: A Motor Operation Inspired Approach
Authors	Shubham Dokania, Ayush Chopra, Feroz Ahmad, Anil Singh Parihar
Abstract	Operational maturity of biological control systems have fuelled the inspiration for a large number of mathematical and logical models for control, automation and optimisation. The human brain represents the most sophisticated control architecture known to us and is a central motivation for several research attempts across various domains. In the present work, we introduce an algorithm for mathematical optimisation that derives its intuition from the hierarchical and distributed operations of the human motor system. The system comprises global leaders, local leaders and an effector population that adapt dynamically to attain global optimisation via a feedback mechanism coupled with the structural hierarchy. The hierarchical system operation is distributed into local control for movement and global controllers that facilitate gross motion and decision making. We present our algorithm as a variant of the classical Differential Evolution algorithm, introducing a hierarchical crossover operation. The discussed approach is tested exhaustively on standard test functions as well as the CEC 2017 benchmark. Our algorithm significantly outperforms various standard algorithms as well as their popular variants as discussed in the results.
Tasks	Decision Making
Published	2017-02-17
URL	http://arxiv.org/abs/1702.05308v2
PDF	http://arxiv.org/pdf/1702.05308v2.pdf
PWC	https://paperswithcode.com/paper/hierarchy-influenced-differential-evolution-a
Repo
Framework

Face Detection using Deep Learning: An Improved Faster RCNN Approach


Title	Face Detection using Deep Learning: An Improved Faster RCNN Approach
Authors	Xudong Sun, Pengcheng Wu, Steven C. H. Hoi
Abstract	In this report, we present a new face detection scheme using deep learning and achieve the state-of-the-art detection performance on the well-known FDDB face detetion benchmark evaluation. In particular, we improve the state-of-the-art faster RCNN framework by combining a number of strategies, including feature concatenation, hard negative mining, multi-scale training, model pretraining, and proper calibration of key parameters. As a consequence, the proposed scheme obtained the state-of-the-art face detection performance, making it the best model in terms of ROC curves among all the published methods on the FDDB benchmark.
Tasks	Calibration, Face Detection
Published	2017-01-28
URL	http://arxiv.org/abs/1701.08289v1
PDF	http://arxiv.org/pdf/1701.08289v1.pdf
PWC	https://paperswithcode.com/paper/face-detection-using-deep-learning-an
Repo
Framework

Sketch Layer Separation in Multi-Spectral Historical Document Images


Title	Sketch Layer Separation in Multi-Spectral Historical Document Images
Authors	AmirAbbas Davari, Armin Häberle, Vincent Christlein, Andreas Maier, Christian Riess
Abstract	High-resolution imaging has delivered new prospects for detecting the material composition and structure of cultural treasures. Despite the various techniques for analysis, a significant diagnostic gap remained in the range of available research capabilities for works on paper. Old master drawings were mostly composed in a multi-step manner with various materials. This resulted in the overlapping of different layers which made the subjacent strata difficult to differentiate. The separation of stratified layers using imaging methods could provide insights into the artistic work processes and help answer questions about the object, its attribution, or in identifying forgeries. The pattern recognition procedure was tested with mock replicas to achieve the separation and the capability of displaying concealed red chalk under ink. In contrast to RGB-sensor based imaging, the multi- or hyperspectral technology allows accurate layer separation by recording the characteristic signatures of the material’s reflectance. The risk of damage to the artworks as a result of the examination can be reduced by using combinations of defined spectra for lightning and image capturing. By guaranteeing the maximum level of readability, our results suggest that the technique can be applied to a broader range of objects and assist in diagnostic research into cultural treasures in the future.
Tasks
Published	2017-12-10
URL	http://arxiv.org/abs/1712.03596v1
PDF	http://arxiv.org/pdf/1712.03596v1.pdf
PWC	https://paperswithcode.com/paper/sketch-layer-separation-in-multi-spectral
Repo
Framework

The Dependence of Frequency Distributions on Multiple Meanings of Words, Codes and Signs


Title	The Dependence of Frequency Distributions on Multiple Meanings of Words, Codes and Signs
Authors	Xiaoyong Yan, Petter Minnhagen
Abstract	The dependence of the frequency distributions due to multiple meanings of words in a text is investigated by deleting letters. By coding the words with fewer letters the number of meanings per coded word increases. This increase is measured and used as an input in a predictive theory. For a text written in English, the word-frequency distribution is broad and fat-tailed, whereas if the words are only represented by their first letter the distribution becomes exponential. Both distribution are well predicted by the theory, as is the whole sequence obtained by consecutively representing the words by the first L=6,5,4,3,2,1 letters. Comparisons of texts written by Chinese characters and the same texts written by letter-codes are made and the similarity of the corresponding frequency-distributions are interpreted as a consequence of the multiple meanings of Chinese characters. This further implies that the difference of the shape for word-frequencies for an English text written by letters and a Chinese text written by Chinese characters is due to the coding and not to the language per se.
Tasks
Published	2017-09-28
URL	http://arxiv.org/abs/1710.00683v1
PDF	http://arxiv.org/pdf/1710.00683v1.pdf
PWC	https://paperswithcode.com/paper/the-dependence-of-frequency-distributions-on
Repo
Framework