Paper Group ANR 672
Proposition d’une nouvelle approche d’extraction des motifs fermés fréquents. Detecting and Diagnosing Incipient Building Faults Using Uncertainty Information from Deep Neural Networks. EAT2seq: A generic framework for controlled sentence transformation without task-specific training. Sudden Death: A New Way to Compare Recommendation Diversificatio …
Proposition d’une nouvelle approche d’extraction des motifs fermés fréquents
| Title | Proposition d’une nouvelle approche d’extraction des motifs fermés fréquents |
| Authors | Ons Khemiri |
| Abstract | This work is done as part of a master’s thesis project. The increase in the volume of data has given rise to various issues related to the collection, storage, analysis and exploitation of these data in order to create an added value. In this master, we are interested in the search of frequent closed patterns in the transaction bases. One way to process data is to partition the search space into subcontexts, and then explore the subcontexts simultaneously. In this context, we have proposed a new approach for extracting frequent closed itemsets. The main idea is to update frequent closed patterns with their minimal generators by applying a strategy of partitioning of the initial extraction context. Our new approach called UFCIGs-DAC was designed and implemented to perform a search in the test bases. The main originality of this approach is the simultaneous exploration of the research space by the update of the frequent closed patterns and the minimal generators. Moreover, our approach can be adapted to any algorithm of extraction of the frequent closed patterns with their minimal generators. |
| Tasks | |
| Published | 2019-06-09 |
| URL | https://arxiv.org/abs/1906.04586v1 |
| https://arxiv.org/pdf/1906.04586v1.pdf | |
| PWC | https://paperswithcode.com/paper/proposition-dune-nouvelle-approche |
| Repo | |
| Framework | |
Detecting and Diagnosing Incipient Building Faults Using Uncertainty Information from Deep Neural Networks
| Title | Detecting and Diagnosing Incipient Building Faults Using Uncertainty Information from Deep Neural Networks |
| Authors | Baihong Jin, Dan Li, Seshadhri Srinivasan, See-Kiong Ng, Kameshwar Poolla, Alberto~Sangiovanni-Vincentelli |
| Abstract | Early detection of incipient faults is of vital importance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings. Popular supervised learning models such as deep neural networks are considered promising due to their ability to directly learn from labeled fault data; however, it is known that the performance of supervised learning approaches highly relies on the availability and quality of labeled training data. In Fault Detection and Diagnosis (FDD) applications, the lack of labeled incipient fault data has posed a major challenge to applying these supervised learning techniques to commercial buildings. To overcome this challenge, this paper proposes using Monte Carlo dropout (MC-dropout) to enhance the supervised learning pipeline, so that the resulting neural network is able to detect and diagnose unseen incipient fault examples. We also examine the proposed MC-dropout method on the RP-1043 dataset to demonstrate its effectiveness in indicating the most likely incipient fault types. |
| Tasks | Fault Detection |
| Published | 2019-02-18 |
| URL | http://arxiv.org/abs/1902.06366v1 |
| http://arxiv.org/pdf/1902.06366v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-and-diagnosing-incipient-building |
| Repo | |
| Framework | |
EAT2seq: A generic framework for controlled sentence transformation without task-specific training
| Title | EAT2seq: A generic framework for controlled sentence transformation without task-specific training |
| Authors | Tommi Gröndahl, N. Asokan |
| Abstract | We present EAT2seq: a novel method to architect automatic linguistic transformations for a number of tasks, including controlled grammatical or lexical changes, style transfer, text generation, and machine translation. Our approach consists in creating an abstract representation of a sentence’s meaning and grammar, which we use as input to an encoder-decoder network trained to reproduce the original sentence. Manipulating the abstract representation allows the transformation of sentences according to user-provided parameters, both grammatically and lexically, in any combination. The same architecture can further be used for controlled text generation, and has additional promise for machine translation. This strategy holds the promise of enabling many tasks that were hitherto outside the scope of NLP techniques for want of sufficient training data. We provide empirical evidence for the effectiveness of our approach by reproducing and transforming English sentences, and evaluating the results both manually and automatically. A single model trained on monolingual data is used for all tasks without any task-specific training. For a model trained on 8.5 million sentences, we report a BLEU score of 74.45 for reproduction, and scores between 55.29 and 81.82 for back-and-forth grammatical transformations across 14 category pairs. |
| Tasks | Machine Translation, Style Transfer, Text Generation, Unsupervised Machine Translation |
| Published | 2019-02-25 |
| URL | http://arxiv.org/abs/1902.09381v3 |
| http://arxiv.org/pdf/1902.09381v3.pdf | |
| PWC | https://paperswithcode.com/paper/using-logical-form-encodings-for-unsupervised |
| Repo | |
| Framework | |
Sudden Death: A New Way to Compare Recommendation Diversification
| Title | Sudden Death: A New Way to Compare Recommendation Diversification |
| Authors | Derek Bridge, Mesut Kaya, Pablo Castells |
| Abstract | This paper describes problems with the current way we compare the diversity of different recommendation lists in offline experiments. We illustrate the problems with a case study. We propose the Sudden Death score as a new and better way of making these comparisons. |
| Tasks | |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1908.00419v1 |
| https://arxiv.org/pdf/1908.00419v1.pdf | |
| PWC | https://paperswithcode.com/paper/sudden-death-a-new-way-to-compare |
| Repo | |
| Framework | |
Manifold-regression to predict from MEG/EEG brain signals without source modeling
| Title | Manifold-regression to predict from MEG/EEG brain signals without source modeling |
| Authors | David Sabbagh, Pierre Ablin, Gael Varoquaux, Alexandre Gramfort, Denis A. Engemann |
| Abstract | Magnetoencephalography and electroencephalography (M/EEG) can reveal neuronal dynamics non-invasively in real-time and are therefore appreciated methods in medicine and neuroscience. Recent advances in modeling brain-behavior relationships have highlighted the effectiveness of Riemannian geometry for summarizing the spatially correlated time-series from M/EEG in terms of their covariance. However, after artefact-suppression, M/EEG data is often rank deficient which limits the application of Riemannian concepts. In this article, we focus on the task of regression with rank-reduced covariance matrices. We study two Riemannian approaches that vectorize the M/EEG covariance between-sensors through projection into a tangent space. The Wasserstein distance readily applies to rank-reduced data but lacks affine-invariance. This can be overcome by finding a common subspace in which the covariance matrices are full rank, enabling the affine-invariant geometric distance. We investigated the implications of these two approaches in synthetic generative models, which allowed us to control estimation bias of a linear model for prediction. We show that Wasserstein and geometric distances allow perfect out-of-sample prediction on the generative models. We then evaluated the methods on real data with regard to their effectiveness in predicting age from M/EEG covariance matrices. The findings suggest that the data-driven Riemannian methods outperform different sensor-space estimators and that they get close to the performance of biophysics-driven source-localization model that requires MRI acquisitions and tedious data processing. Our study suggests that the proposed Riemannian methods can serve as fundamental building-blocks for automated large-scale analysis of M/EEG. |
| Tasks | EEG, Time Series |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.02687v3 |
| https://arxiv.org/pdf/1906.02687v3.pdf | |
| PWC | https://paperswithcode.com/paper/manifold-regression-to-predict-from-megeeg |
| Repo | |
| Framework | |
Analysis of Generalized Entropies in Mutual Information Medical Image Registration
| Title | Analysis of Generalized Entropies in Mutual Information Medical Image Registration |
| Authors | Vinicius Pavanelli Vianna, Luiz Otavio Murta Junior |
| Abstract | Mutual information (MI) is the standard method used in image registration and the most studied one but can diverge and produce wrong results when used in an automated manner. In this study we compared the results of the ITK Mattes MI function, used in 3D Slicer and ITK derived software solutions, and our own MICUDA Shannon and Tsallis MI functions under the translation, rotation and scale transforms in a 3D mathematical space. This comparison allows to understand why registration fails in some circumstances and how to produce a more robust automated algorithm to register medical images. Since our algorithms were designed to use GPU computations we also have a huge gain in speed while improving the quality of registration. |
| Tasks | Image Registration, Medical Image Registration |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.10690v1 |
| https://arxiv.org/pdf/1909.10690v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-generalized-entropies-in-mutual |
| Repo | |
| Framework | |
General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping
| Title | General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping |
| Authors | Gabriel Ilharco, Vihan Jain, Alexander Ku, Eugene Ie, Jason Baldridge |
| Abstract | In instruction conditioned navigation, agents interpret natural language and their surroundings to navigate through an environment. Datasets for studying this task typically contain pairs of these instructions and reference trajectories. Yet, most evaluation metrics used thus far fail to properly account for the latter, relying instead on insufficient similarity comparisons. We address fundamental flaws in previously used metrics and show how Dynamic Time Warping (DTW), a long known method of measuring similarity between two time series, can be used for evaluation of navigation agents. For such, we define the normalized Dynamic Time Warping (nDTW) metric, that softly penalizes deviations from the reference path, is naturally sensitive to the order of the nodes composing each path, is suited for both continuous and graph-based evaluations, and can be efficiently calculated. Further, we define SDTW, which constrains nDTW to only successful paths. We collect human similarity judgments for simulated paths and find nDTW correlates better with human rankings than all other metrics. We also demonstrate that using nDTW as a reward signal for Reinforcement Learning navigation agents improves their performance on both the Room-to-Room (R2R) and Room-for-Room (R4R) datasets. The R4R results in particular highlight the superiority of SDTW over previous success-constrained metrics. |
| Tasks | Time Series |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05446v2 |
| https://arxiv.org/pdf/1907.05446v2.pdf | |
| PWC | https://paperswithcode.com/paper/effective-and-general-evaluation-for |
| Repo | |
| Framework | |
A Mobile Manipulation System for One-Shot Teaching of Complex Tasks in Homes
| Title | A Mobile Manipulation System for One-Shot Teaching of Complex Tasks in Homes |
| Authors | Max Bajracharya, James Borders, Dan Helmick, Thomas Kollar, Michael Laskey, John Leichty, Jeremy Ma, Umashankar Nagarajan, Akiyoshi Ochiai, Josh Petersen, Krishna Shankar, Kevin Stone, Yutaka Takaoka |
| Abstract | We describe a mobile manipulation hardware and software system capable of autonomously performing complex human-level tasks in real homes, after being taught the task with a single demonstration from a person in virtual reality. This is enabled by a highly capable mobile manipulation robot, whole-body task space hybrid position/force control, teaching of parameterized primitives linked to a robust learned dense visual embeddings representation of the scene, and a task graph of the taught behaviors. We demonstrate the robustness of the approach by presenting results for performing a variety of tasks, under different environmental conditions, in multiple real homes. Our approach achieves 85% overall success rate on three tasks that consist of an average of 45 behaviors each. |
| Tasks | |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.00127v3 |
| https://arxiv.org/pdf/1910.00127v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-mobile-manipulation-system-for-one-shot |
| Repo | |
| Framework | |
Adaptive Model Selection Framework: An Application to Airline Pricing
| Title | Adaptive Model Selection Framework: An Application to Airline Pricing |
| Authors | Naman Shukla, Arinbjörn Kolbeinsson, Lavanya Marla, Kartik Yellepeddi |
| Abstract | Multiple machine learning and prediction models are often used for the same prediction or recommendation task. In our recent work, where we develop and deploy airline ancillary pricing models in an online setting, we found that among multiple pricing models developed, no one model clearly dominates other models for all incoming customer requests. Thus, as algorithm designers, we face an exploration - exploitation dilemma. In this work, we introduce an adaptive meta-decision framework that uses Thompson sampling, a popular multi-armed bandit solution method, to route customer requests to various pricing models based on their online performance. We show that this adaptive approach outperform a uniformly random selection policy by improving the expected revenue per offer by 43% and conversion score by 58% in an offline simulation. |
| Tasks | Model Selection |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08874v1 |
| https://arxiv.org/pdf/1905.08874v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-model-selection-framework-an |
| Repo | |
| Framework | |
Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment
| Title | Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment |
| Authors | Peng Chu, Heng Fan, Chiu C Tan, Haibin Ling |
| Abstract | Recent progresses in model-free single object tracking (SOT) algorithms have largely inspired applying SOT to \emph{multi-object tracking} (MOT) to improve the robustness as well as relieving dependency on external detector. However, SOT algorithms are generally designed for distinguishing a target from its environment, and hence meet problems when a target is spatially mixed with similar objects as observed frequently in MOT. To address this issue, in this paper we propose an instance-aware tracker to integrate SOT techniques for MOT by encoding awareness both within and between target models. In particular, we construct each target model by fusing information for distinguishing target both from background and other instances (tracking targets). To conserve uniqueness of all target models, our instance-aware tracker considers response maps from all target models and assigns spatial locations exclusively to optimize the overall accuracy. Another contribution we make is a dynamic model refreshing strategy learned by a convolutional neural network. This strategy helps to eliminate initialization noise as well as to adapt to the variation of target size and appearance. To show the effectiveness of the proposed approach, it is evaluated on the popular MOT15 and MOT16 challenge benchmarks. On both benchmarks, our approach achieves the best overall performances in comparison with published results. |
| Tasks | Multi-Object Tracking, Object Tracking, Online Multi-Object Tracking |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.08231v1 |
| http://arxiv.org/pdf/1902.08231v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-multi-object-tracking-with-instance |
| Repo | |
| Framework | |
End-to-End Deep Convolutional Active Contours for Image Segmentation
| Title | End-to-End Deep Convolutional Active Contours for Image Segmentation |
| Authors | Ali Hatamizadeh, Debleena Sengupta, Demetri Terzopoulos |
| Abstract | The Active Contour Model (ACM) is a standard image analysis technique whose numerous variants have attracted an enormous amount of research attention across multiple fields. Incorrectly, however, the ACM’s differential-equation-based formulation and prototypical dependence on user initialization have been regarded as being largely incompatible with the recently popular deep learning approaches to image segmentation. This paper introduces the first tight unification of these two paradigms. In particular, we devise Deep Convolutional Active Contours (DCAC), a truly end-to-end trainable image segmentation framework comprising a Convolutional Neural Network (CNN) and an ACM with learnable parameters. The ACM’s Eulerian energy functional includes per-pixel parameter maps predicted by the backbone CNN, which also initializes the ACM. Importantly, both the CNN and ACM components are fully implemented in TensorFlow, and the entire DCAC architecture is end-to-end automatically differentiable and backpropagation trainable without user intervention. As a challenging test case, we tackle the problem of building instance segmentation in aerial images and evaluate DCAC on two publicly available datasets, Vaihingen and Bing Huts. Our reseults demonstrate that, for building segmentation, the DCAC establishes a new state-of-the-art performance by a wide margin. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1909.13359v2 |
| https://arxiv.org/pdf/1909.13359v2.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-deep-convolutional-active-contours |
| Repo | |
| Framework | |
An Extended Adaptive Subspace Self-Organizing Map (EASSOM) Imbalanced Learning and Its Applications in EEG
| Title | An Extended Adaptive Subspace Self-Organizing Map (EASSOM) Imbalanced Learning and Its Applications in EEG |
| Authors | Zehong Cao, Yu-Ting Liu, Chun-Hsiang Chuang, Yang-Yin Lin, Tsung-Yu Hsieh, Chieh-Ning Fan, Nikhil R. Pal, Chin-Teng Lin |
| Abstract | This paper presents a novel oversampling technique addressing highly imbalanced distributions in benchmark and electroencephalogram (EEG) datasets. Presently, conventional machine learning technologies do not adequately address imbalanced data with an anomalous class distribution and underrepresented data. To balance the class distributions, an extended adaptive subspace self-organizing map (EASSOM) that combines a local mapping scheme and the globally competitive rule is proposed to artificially generate synthetic samples that focus on minority class samples and its application in EEG. The EASSOM is configured with feature-invariant characteristics, including translation, scaling, and rotation, and it retains the independence of the basis vectors in each module. Specifically, basis vectors that are generated via each EASSOM module can avoid generating repeated representative features that only increase the computational load. Several benchmark experimental results demonstrate that the proposed EASSOM method incorporating a supervised learning approach could be superior to other existing oversampling techniques, and three EEG applications present the improvement of classification accuracy using the proposed EASSOM method. |
| Tasks | EEG |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1906.02772v2 |
| https://arxiv.org/pdf/1906.02772v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-adaptive-subspace-self-organizing-map |
| Repo | |
| Framework | |
Reinforcement Learning for Multi-Objective Optimization of Online Decisions in High-Dimensional Systems
| Title | Reinforcement Learning for Multi-Objective Optimization of Online Decisions in High-Dimensional Systems |
| Authors | Hardik Meisheri, Vinita Baniwal, Nazneen N Sultana, Balaraman Ravindran, Harshad Khadilkar |
| Abstract | This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while the micro-level behaviour of the system can be broadly captured by analytical expressions or simulation, the macro-level or emergent behaviour is complicated by non-linearity, constraints, and stochasticity. If we represent the set of concurrent decisions to be computed as a vector, each element of the vector is assumed to be a continuous variable, and the number of such elements is arbitrarily large and variable from one problem instance to another. We first formulate the decision-making problem as a canonical reinforcement learning (RL) problem, which can be solved using purely data-driven techniques. We modify a standard approach known as advantage actor critic (A2C) to ensure its suitability to the problem at hand, and compare its performance to that of baseline approaches on the specific instance of a multi-product inventory management task. The key modifications include a parallelised formulation of the decision-making task, and a training procedure that explicitly recognises the quantitative relationship between different decisions. We also present experimental results probing the learned policies, and their robustness to variations in the data. |
| Tasks | Decision Making |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00211v1 |
| https://arxiv.org/pdf/1910.00211v1.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-for-multi-objective |
| Repo | |
| Framework | |
Fine-Grained Object Detection over Scientific Document Images with Region Embeddings
| Title | Fine-Grained Object Detection over Scientific Document Images with Region Embeddings |
| Authors | Ankur Goswami, Joshua McGrath, Shanan Peters, Theodoros Rekatsinas |
| Abstract | We study the problem of object detection over scanned images of scientific documents. We consider images that contain objects of varying aspect ratios and sizes and range from coarse elements such as tables and figures to fine elements such as equations and section headers. We find that current object detectors fail to produce properly localized region proposals over such page objects. We revisit the original R-CNN model and present a method for generating fine-grained proposals over document elements. We also present a region embedding model that uses the convolutional maps of a proposal’s neighbors as context to produce an embedding for each proposal. This region embedding is able to capture the semantic relationships between a target region and its surrounding context. Our end-to-end model produces an embedding for each proposal, then classifies each proposal by using a multi-head attention model that attends to the most important neighbors of a proposal. To evaluate our model, we collect and annotate a dataset of publications from heterogeneous journals. We show that our model, referred to as Attentive-RCNN, yields a 17% mAP improvement compared to standard object detection models. |
| Tasks | Object Detection |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12462v2 |
| https://arxiv.org/pdf/1910.12462v2.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-object-detection-over-scientific |
| Repo | |
| Framework | |
Quantum Mean Embedding of Probability Distributions
| Title | Quantum Mean Embedding of Probability Distributions |
| Authors | Jonas M. Kübler, Krikamol Muandet, Bernhard Schölkopf |
| Abstract | The kernel mean embedding of probability distributions is commonly used in machine learning as an injective mapping from distributions to functions in an infinite dimensional Hilbert space. It allows us, for example, to define a distance measure between probability distributions, called maximum mean discrepancy (MMD). In this work, we propose to represent probability distributions in a pure quantum state of a system that is described by an infinite dimensional Hilbert space. This enables us to work with an explicit representation of the mean embedding, whereas classically one can only work implicitly with an infinite dimensional Hilbert space through the use of the kernel trick. We show how this explicit representation can speed up methods that rely on inner products of mean embeddings and discuss the theoretical and experimental challenges that need to be solved in order to achieve these speedups. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13526v1 |
| https://arxiv.org/pdf/1905.13526v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-mean-embedding-of-probability |
| Repo | |
| Framework | |
