October 18, 2019

2914 words 14 mins read

Paper Group ANR 677

DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference. Expanding search in the space of empirical ML. An Occluded Stacked Hourglass Approach to Facial Landmark Localization and Occlusion Estimation. Space Expansion of Feature Selection for Designing more Accurate Error Predictors. A Better Baseline for AVA. A new approach t …

DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference


Title	DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference
Authors	Reza Ghaeini, Sadid A. Hasan, Vivek Datla, Joey Liu, Kathy Lee, Ashequl Qadir, Yuan Ling, Aaditya Prakash, Xiaoli Z. Fern, Oladimeji Farri
Abstract	We present a novel deep learning architecture to address the natural language inference (NLI) task. Existing approaches mostly rely on simple reading mechanisms for independent encoding of the premise and hypothesis. Instead, we propose a novel dependent reading bidirectional LSTM network (DR-BiLSTM) to efficiently model the relationship between a premise and a hypothesis during encoding and inference. We also introduce a sophisticated ensemble strategy to combine our proposed models, which noticeably improves final predictions. Finally, we demonstrate how the results can be improved further with an additional preprocessing step. Our evaluation shows that DR-BiLSTM obtains the best single model and ensemble model results achieving the new state-of-the-art scores on the Stanford NLI dataset.
Tasks	Natural Language Inference
Published	2018-02-15
URL	http://arxiv.org/abs/1802.05577v2
PDF	http://arxiv.org/pdf/1802.05577v2.pdf
PWC	https://paperswithcode.com/paper/dr-bilstm-dependent-reading-bidirectional
Repo
Framework

Expanding search in the space of empirical ML


Title	Expanding search in the space of empirical ML
Authors	Bronwyn Woods
Abstract	As researchers and practitioners of applied machine learning, we are given a set of requirements on the problem to be solved, the plausibly obtainable data, and the computational resources available. We aim to find (within those bounds) reliably useful combinations of problem, data, and algorithm. An emphasis on algorithmic or technical novelty in ML conference publications leads to exploration of one dimension of this space. Data collection and ML deployment at scale in industry settings offers an environment for exploring the others. Our conferences and reviewing criteria can better support empirical ML by soliciting and incentivizing experimentation and synthesis independent of algorithmic innovation.
Tasks
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01495v1
PDF	http://arxiv.org/pdf/1812.01495v1.pdf
PWC	https://paperswithcode.com/paper/expanding-search-in-the-space-of-empirical-ml
Repo
Framework

An Occluded Stacked Hourglass Approach to Facial Landmark Localization and Occlusion Estimation


Title	An Occluded Stacked Hourglass Approach to Facial Landmark Localization and Occlusion Estimation
Authors	Kevan Yuen, Mohan M. Trivedi
Abstract	A key step to driver safety is to observe the driver’s activities with the face being a key step in this process to extracting information such as head pose, blink rate, yawns, talking to passenger which can then help derive higher level information such as distraction, drowsiness, intent, and where they are looking. In the context of driving safety, it is important for the system perform robust estimation under harsh lighting and occlusion but also be able to detect when the occlusion occurs so that information predicted from occluded parts of the face can be taken into account properly. This paper introduces the Occluded Stacked Hourglass, based on the work of original Stacked Hourglass network for body pose joint estimation, which is retrained to process a detected face window and output 68 occlusion heat maps, each corresponding to a facial landmark. Landmark location, occlusion levels and a refined face detection score, to reject false positives, are extracted from these heat maps. Using the facial landmark locations, features such as head pose and eye/mouth openness can be extracted to derive driver attention and activity. The system is evaluated for face detection, head pose, and occlusion estimation on various datasets in the wild, both quantitatively and qualitatively, and shows state-of-the-art results.
Tasks	Face Alignment, Face Detection
Published	2018-02-05
URL	http://arxiv.org/abs/1802.02137v1
PDF	http://arxiv.org/pdf/1802.02137v1.pdf
PWC	https://paperswithcode.com/paper/an-occluded-stacked-hourglass-approach-to
Repo
Framework

Space Expansion of Feature Selection for Designing more Accurate Error Predictors


Title	Space Expansion of Feature Selection for Designing more Accurate Error Predictors
Authors	Shayan Tabatabaei Nikkhah, Mehdi Kamal, Ali Afzali-Kusha, Massoud Pedram
Abstract	Approximate computing is being considered as a promising design paradigm to overcome the energy and performance challenges in computationally demanding applications. If the case where the accuracy can be configured, the quality level versus energy efficiency or delay also may be traded-off. For this technique to be used, one needs to make sure a satisfactory user experience. This requires employing error predictors to detect unacceptable approximation errors. In this work, we propose a scheduling-aware feature selection method which leverages the intermediate results of the hardware accelerator to improve the prediction accuracy. Additionally, it configures the error predictors according to the energy consumption and latency of the system. The approach enjoys the flexibility of the prediction time for a higher accuracy. The results on various benchmarks demonstrate significant improvements in the prediction accuracy compared to the prior works which used only the accelerator inputs for the prediction.
Tasks	Feature Selection
Published	2018-12-30
URL	http://arxiv.org/abs/1901.00952v1
PDF	http://arxiv.org/pdf/1901.00952v1.pdf
PWC	https://paperswithcode.com/paper/space-expansion-of-feature-selection-for
Repo
Framework

A Better Baseline for AVA


Title	A Better Baseline for AVA
Authors	Rohit Girdhar, João Carreira, Carl Doersch, Andrew Zisserman
Abstract	We introduce a simple baseline for action localization on the AVA dataset. The model builds upon the Faster R-CNN bounding box detection framework, adapted to operate on pure spatiotemporal features - in our case produced exclusively by an I3D model pretrained on Kinetics. This model obtains 21.9% average AP on the validation set of AVA v2.1, up from 14.5% for the best RGB spatiotemporal model used in the original AVA paper (which was pretrained on Kinetics and ImageNet), and up from 11.3 of the publicly available baseline using a ResNet101 image feature extractor, that was pretrained on ImageNet. Our final model obtains 22.8%/21.9% mAP on the val/test sets and outperforms all submissions to the AVA challenge at CVPR 2018.
Tasks	Action Localization
Published	2018-07-26
URL	http://arxiv.org/abs/1807.10066v1
PDF	http://arxiv.org/pdf/1807.10066v1.pdf
PWC	https://paperswithcode.com/paper/a-better-baseline-for-ava
Repo
Framework

A new approach to learning in Dynamic Bayesian Networks (DBNs)


Title	A new approach to learning in Dynamic Bayesian Networks (DBNs)
Authors	E. Benhamou, J. Atif, R. Laraki
Abstract	In this paper, we revisit the parameter learning problem, namely the estimation of model parameters for Dynamic Bayesian Networks (DBNs). DBNs are directed graphical models of stochastic processes that encompasses and generalize Hidden Markov models (HMMs) and Linear Dynamical Systems (LDSs). Whenever we apply these models to economics and finance, we are forced to make some modeling assumptions about the state dynamics and the graph topology (the DBN structure). These assumptions may be incorrectly specified and contain some additional noise compared to reality. Trying to use a best fit approach through maximum likelihood estimation may miss this point and try to fit at any price these models on data. We present here a new methodology that takes a radical point of view and instead focus on the final efficiency of our model. Parameters are hence estimated in terms of their efficiency rather than their distributional fit to the data. The resulting optimization problem that consists in finding the optimal parameters is a hard problem. We rely on Covariance Matrix Adaptation Evolution Strategy (CMA-ES) method to tackle this issue. We apply this method to the seminal problem of trend detection in financial markets. We see on numerical results that the resulting parameters seem less error prone to over fitting than traditional moving average cross over trend detection and perform better. The method developed here for algorithmic trading is general. It can be applied to other real case applications whenever there is no physical law underlying our DBNs.
Tasks
Published	2018-12-21
URL	http://arxiv.org/abs/1812.09027v2
PDF	http://arxiv.org/pdf/1812.09027v2.pdf
PWC	https://paperswithcode.com/paper/a-new-approach-to-learning-in-dynamic
Repo
Framework

Intersectionality: Multiple Group Fairness in Expectation Constraints


Title	Intersectionality: Multiple Group Fairness in Expectation Constraints
Authors	Jack Fitzsimons, Michael Osborne, Stephen Roberts
Abstract	Group fairness is an important concern for machine learning researchers, developers, and regulators. However, the strictness to which models must be constrained to be considered fair is still under debate. The focus of this work is on constraining the expected outcome of subpopulations in kernel regression and, in particular, decision tree regression, with application to random forests, boosted trees and other ensemble models. While individual constraints were previously addressed, this work addresses concerns about incorporating multiple constraints simultaneously. The proposed solution does not affect the order of computational or memory complexity of the decision trees and is easily integrated into models post training.
Tasks
Published	2018-11-25
URL	http://arxiv.org/abs/1811.09960v1
PDF	http://arxiv.org/pdf/1811.09960v1.pdf
PWC	https://paperswithcode.com/paper/intersectionality-multiple-group-fairness-in
Repo
Framework

Learning in time-varying games


Title	Learning in time-varying games
Authors	Benoit Duvocelle, Panayotis Mertikopoulos, Mathias Staudigl, Dries Vermeulen
Abstract	In this paper, we examine the long-term behavior of regret-minimizing agents in time-varying games with continuous action spaces. In its most basic form, (external) regret minimization guarantees that an agent’s cumulative payoff is no worse in the long run than that of the agent’s best fixed action in hindsight. Going beyond this worst-case guarantee, we consider a dynamic regret variant that compares the agent’s accrued rewards to those of any sequence of play. Specializing to a wide class of no-regret strategies based on mirror descent, we derive explicit rates of regret minimization relying only on imperfect gradient obvservations. We then leverage these results to show that players are able to stay close to Nash equilibrium in time-varying monotone games - and even converge to Nash equilibrium if the sequence of stage games admits a limit.
Tasks
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03066v1
PDF	http://arxiv.org/pdf/1809.03066v1.pdf
PWC	https://paperswithcode.com/paper/learning-in-time-varying-games
Repo
Framework

Learning Awareness Models


Title	Learning Awareness Models
Authors	Brandon Amos, Laurent Dinh, Serkan Cabi, Thomas Rothörl, Sergio Gómez Colmenarejo, Alistair Muldal, Tom Erez, Yuval Tassa, Nando de Freitas, Misha Denil
Abstract	We consider the setting of an agent with a fixed body interacting with an unknown and uncertain external world. We show that models trained to predict proprioceptive information about the agent’s body come to represent objects in the external world. In spite of being trained with only internally available signals, these dynamic body models come to represent external objects through the necessity of predicting their effects on the agent’s own body. That is, the model learns holistic persistent representations of objects in the world, even though the only training signals are body signals. Our dynamics model is able to successfully predict distributions over 132 sensor readings over 100 steps into the future and we demonstrate that even when the body is no longer in contact with an object, the latent variables of the dynamics model continue to represent its shape. We show that active data collection by maximizing the entropy of predictions about the body—touch sensors, proprioception and vestibular information—leads to learning of dynamic models that show superior performance when used for control. We also collect data from a real robotic hand and show that the same models can be used to answer questions about properties of objects in the real world. Videos with qualitative results of our models are available at https://goo.gl/mZuqAV.
Tasks
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06318v1
PDF	http://arxiv.org/pdf/1804.06318v1.pdf
PWC	https://paperswithcode.com/paper/learning-awareness-models
Repo
Framework

RetinaMatch: Efficient Template Matching of Retina Images for Teleophthalmology


Title	RetinaMatch: Efficient Template Matching of Retina Images for Teleophthalmology
Authors	Chen Gong, N. Benjamin Erichson, John P. Kelly, Laura Trutoiu, Brian T. Schowengerdt, Steven L. Brunton, Eric J. Seibel
Abstract	Retinal template matching and registration is an important challenge in teleophthalmology with low-cost imaging devices. However, the images from such devices generally have a small field of view (FOV) and image quality degradations, making matching difficult. In this work, we develop an efficient and accurate retinal matching technique that combines dimension reduction and mutual information (MI), called RetinaMatch. The dimension reduction initializes the MI optimization as a coarse localization process, which narrows the optimization domain and avoids local optima. The effectiveness of RetinaMatch is demonstrated on the open fundus image database STARE with simulated reduced FOV and anticipated degradations, and on retinal images acquired by adapter-based optics attached to a smartphone. RetinaMatch achieves a success rate over 94% on human retinal images with the matched target registration errors below 2 pixels on average, excluding the observer variability. It outperforms the standard template matching solutions. In the application of measuring vessel diameter repeatedly, single pixel errors are expected. In addition, our method can be used in the process of image mosaicking with area-based registration, providing a robust approach when the feature based methods fail. To the best of our knowledge, this is the first template matching algorithm for retina images with small template images from unconstrained retinal areas. In the context of the emerging mixed reality market, we envision automated retinal image matching and registration methods as transformative for advanced teleophthalmology and long-term retinal monitoring.
Tasks	Dimensionality Reduction
Published	2018-11-28
URL	http://arxiv.org/abs/1811.11874v1
PDF	http://arxiv.org/pdf/1811.11874v1.pdf
PWC	https://paperswithcode.com/paper/retinamatch-efficient-template-matching-of
Repo
Framework

An Empirical Approach For Probing the Definiteness of Kernels


Title	An Empirical Approach For Probing the Definiteness of Kernels
Authors	Martin Zaefferer, Thomas Bartz-Beielstein, Günter Rudolph
Abstract	Models like support vector machines or Gaussian process regression often require positive semi-definite kernels. These kernels may be based on distance functions. While definiteness is proven for common distances and kernels, a proof for a new kernel may require too much time and effort for users who simply aim at practical usage. Furthermore, designing definite distances or kernels may be equally intricate. Finally, models can be enabled to use indefinite kernels. This may deteriorate the accuracy or computational cost of the model. Hence, an efficient method to determine definiteness is required. We propose an empirical approach. We show that sampling as well as optimization with an evolutionary algorithm may be employed to determine definiteness. We provide a proof-of-concept with 16 different distance measures for permutations. Our approach allows to disprove definiteness if a respective counter-example is found. It can also provide an estimate of how likely it is to obtain indefinite kernel matrices. This provides a simple, efficient tool to decide whether additional effort should be spent on designing/selecting a more suitable kernel or algorithm.
Tasks
Published	2018-07-10
URL	http://arxiv.org/abs/1807.03555v1
PDF	http://arxiv.org/pdf/1807.03555v1.pdf
PWC	https://paperswithcode.com/paper/an-empirical-approach-for-probing-the
Repo
Framework

Surface Light Field Fusion


Title	Surface Light Field Fusion
Authors	Jeong Joon Park, Richard Newcombe, Steve Seitz
Abstract	We present an approach for interactively scanning highly reflective objects with a commodity RGBD sensor. In addition to shape, our approach models the surface light field, encoding scene appearance from all directions. By factoring the surface light field into view-independent and wavelength-independent components, we arrive at a representation that can be robustly estimated with IR-equipped commodity depth sensors, and achieves high quality results.
Tasks
Published	2018-09-06
URL	http://arxiv.org/abs/1809.02057v1
PDF	http://arxiv.org/pdf/1809.02057v1.pdf
PWC	https://paperswithcode.com/paper/surface-light-field-fusion
Repo
Framework

A Review on Image Texture Analysis Methods


Title	A Review on Image Texture Analysis Methods
Authors	Shervan Fekri-Ershad
Abstract	Texture classification is an active topic in image processing which plays an important role in many applications such as image retrieval, inspection systems, face recognition, medical image processing, etc. There are many approaches extracting texture features in gray-level images such as local binary patterns, gray level co-occurrence matrices, statistical features, skeleton, scale invariant feature transform, etc. The texture analysis methods can be categorized in 4 groups titles: statistical methods, structural methods, filter-based and model based approaches. In many related researches, authors have tried to extract color and texture features jointly. In this respect, combined methods are considered as efficient image analysis descriptors. Mostly important challenges in image texture analysis are rotation sensitivity, gray scale variations, noise sensitivity, illumination and brightness conditions, etc. In this paper, we review most efficient and state-of-the-art image texture analysis methods. Also, some texture classification approaches are survived.
Tasks	Face Recognition, Image Retrieval, Texture Classification
Published	2018-03-13
URL	http://arxiv.org/abs/1804.00494v1
PDF	http://arxiv.org/pdf/1804.00494v1.pdf
PWC	https://paperswithcode.com/paper/a-review-on-image-texture-analysis-methods
Repo
Framework

Attention-Aware Generalized Mean Pooling for Image Retrieval


Title	Attention-Aware Generalized Mean Pooling for Image Retrieval
Authors	Yinzheng Gu, Chuanpeng Li, Jinbin Xie
Abstract	It has been shown that image descriptors extracted by convolutional neural networks (CNNs) achieve remarkable results for retrieval problems. In this paper, we apply attention mechanism to CNN, which aims at enhancing more relevant features that correspond to important keypoints in the input image. The generated attention-aware features are then aggregated by the previous state-of-the-art generalized mean (GeM) pooling followed by normalization to produce a compact global descriptor, which can be efficiently compared to other image descriptors by the dot product. An extensive comparison of our proposed approach with state-of-the-art methods is performed on the new challenging ROxford5k and RParis6k retrieval benchmarks. Results indicate significant improvement over previous work. In particular, our attention-aware GeM (AGeM) descriptor outperforms state-of-the-art method on ROxford5k under the `Hard’ evaluation protocal. \|
Tasks	Image Retrieval
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00202v2
PDF	http://arxiv.org/pdf/1811.00202v2.pdf
PWC	https://paperswithcode.com/paper/attention-aware-generalized-mean-pooling-for
Repo
Framework

Multi-hypothesis contextual modeling for semantic segmentation


Title	Multi-hypothesis contextual modeling for semantic segmentation
Authors	Hasan F. Ates, Sercan Sunetci
Abstract	Semantic segmentation (i.e. image parsing) aims to annotate each image pixel with its corresponding semantic class label. Spatially consistent labeling of the image requires an accurate description and modeling of the local contextual information. Segmentation result is typically improved by Markov Random Field (MRF) optimization on the initial labels. However this improvement is limited by the accuracy of initial result and how the contextual neighborhood is defined. In this paper, we develop generalized and flexible contextual models for segmentation neighborhoods in order to improve parsing accuracy. Instead of using a fixed segmentation and neighborhood definition, we explore various contextual models for fusion of complementary information available in alternative segmentations of the same image. In other words, we propose a novel MRF framework that describes and optimizes the contextual dependencies between multiple segmentations. Simulation results on two common datasets demonstrate significant improvement in parsing accuracy over the baseline approaches.
Tasks	Semantic Segmentation
Published	2018-12-14
URL	http://arxiv.org/abs/1812.05850v1
PDF	http://arxiv.org/pdf/1812.05850v1.pdf
PWC	https://paperswithcode.com/paper/multi-hypothesis-contextual-modeling-for
Repo
Framework