Paper Group ANR 1678
Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation. Analysis and Extension of the Evidential Reasoning Algorithm for Multiple Attribute Decision Analysis with Uncertainty. Unsupervised Representation Learning by Predicting Random Distances. A general anomaly detection framework for fleet-based condition m …
Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation
| Title | Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation |
| Authors | Tianyu Zhao, Shinsuke Mori, Tatsuya Kawahara |
| Abstract | Various encoder-decoder models have been applied to response generation in open-domain dialogs, but a majority of conventional models directly learn a mapping from lexical input to lexical output without explicitly modeling intermediate representations. Utilizing language hierarchy and modeling intermediate information have been shown to benefit many language understanding and generation tasks. Motivated by Broca’s aphasia, we propose to use a content word sequence as an intermediate representation for open-domain response generation. Experimental results show that the proposed method improves content relatedness of produced responses, and our models can often choose correct grammar for generated content words. Meanwhile, instead of evaluating complete sentences, we propose to compute conventional metrics on content word sequences, which is a better indicator of content relevance. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13438v2 |
| https://arxiv.org/pdf/1905.13438v2.pdf | |
| PWC | https://paperswithcode.com/paper/content-word-based-sentence-decoding-and |
| Repo | |
| Framework | |
Analysis and Extension of the Evidential Reasoning Algorithm for Multiple Attribute Decision Analysis with Uncertainty
| Title | Analysis and Extension of the Evidential Reasoning Algorithm for Multiple Attribute Decision Analysis with Uncertainty |
| Authors | Lianmeng Jiao, Xiaojiao Geng |
| Abstract | In multiple attribute decision analysis (MADA) problems, one often needs to deal with assessment information with uncertainty. The evidential reasoning approach is one of the most effective methods to deal with such MADA problems. As kernel of the evidential reasoning approach, an original evidential reasoning (ER) algorithm was firstly proposed by Yang et al, and later they modified the ER algorithm in order to satisfy the proposed four synthesis axioms with which a rational aggregation process needs to satisfy. However, up to present, the essential difference of the two ER algorithms as well as the rationality of the synthesis axioms are still unclear. In this paper, we analyze the ER algorithms in Dempster-Shafer theory (DST) framework and prove that the original ER algorithm follows the reliability discounting and combination scheme, while the modified one follows the importance discounting and combination scheme. Further we reveal that the four synthesis axioms are not valid criteria to check the rationality of one attribute aggregation algorithm. Based on these new findings, an extended ER algorithm is proposed to take into account both the reliability and importance of different attributes, which provides a more general attribute aggregation scheme for MADA with uncertainty. A motorcycle performance assessment problem is examined to illustrate the proposed algorithm. |
| Tasks | |
| Published | 2019-03-28 |
| URL | http://arxiv.org/abs/1903.11857v1 |
| http://arxiv.org/pdf/1903.11857v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-and-extension-of-the-evidential |
| Repo | |
| Framework | |
Unsupervised Representation Learning by Predicting Random Distances
| Title | Unsupervised Representation Learning by Predicting Random Distances |
| Authors | Hu Wang, Guansong Pang, Chunhua Shen, Congbo Ma |
| Abstract | Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensional data. However, they often require large-scale labelled data to successfully learn such features, which significantly hinders their adaption into unsupervised learning tasks, such as anomaly detection and clustering, and limits their applications into critical domains where obtaining massive labelled data is prohibitively expensive. To enable downstream unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected space. Random mapping is a theoretical proven approach to obtain approximately preserved distances. To well predict these random distances, the representation learner is optimised to learn genuine class structures that are implicitly embedded in the randomly projected space. Experimental results on 19 real-world datasets show our learned representations substantially outperform state-of-the-art competing methods in both anomaly detection and clustering tasks. |
| Tasks | Anomaly Detection, Representation Learning, Unsupervised Representation Learning |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.12186v1 |
| https://arxiv.org/pdf/1912.12186v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-representation-learning-by-6 |
| Repo | |
| Framework | |
A general anomaly detection framework for fleet-based condition monitoring of machines
| Title | A general anomaly detection framework for fleet-based condition monitoring of machines |
| Authors | Kilian Hendrickx, Wannes Meert, Yves Mollet, Johan Gyselinck, Bram Cornelis, Konstantinos Gryllias, Jesse Davis |
| Abstract | Machine failures decrease up-time and can lead to extra repair costs or even to human casualties and environmental pollution. Recent condition monitoring techniques use artificial intelligence in an effort to avoid time-consuming manual analysis and handcrafted feature extraction. Many of these only analyze a single machine and require a large historical data set. In practice, this can be difficult and expensive to collect. However, some industrial condition monitoring applications involve a fleet of similar operating machines. In most of these applications, it is safe to assume healthy conditions for the majority of machines. Deviating machine behavior is then an indicator for a machine fault. This work proposes an unsupervised, generic, anomaly detection framework for fleet-based condition monitoring. It uses generic building blocks and offers three key advantages. First, a historical data set is not required due to online fleet-based comparisons. Second, it allows incorporating domain expertise by user-defined comparison measures. Finally, contrary to most black-box artificial intelligence techniques, easy interpretability allows a domain expert to validate the predictions made by the framework. Two use-cases on an electrical machine fleet demonstrate the applicability of the framework to detect a voltage unbalance by means of electrical and vibration signatures. |
| Tasks | Anomaly Detection |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12941v3 |
| https://arxiv.org/pdf/1912.12941v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-anomaly-detection-framework-for |
| Repo | |
| Framework | |
Unsupervised Stemming based Language Model for Telugu Broadcast News Transcription
| Title | Unsupervised Stemming based Language Model for Telugu Broadcast News Transcription |
| Authors | Mythili Sharan Pala, Parayitam Laxminarayana, A. V. Ramana |
| Abstract | In Indian Languages , native speakers are able to understand new words formed by either combining or modifying root words with tense and / or gender. Due to data insufficiency, Automatic Speech Recognition system (ASR) may not accommodate all the words in the language model irrespective of the size of the text corpus. It also becomes computationally challenging if the volume of the data increases exponentially due to morphological changes to the root word. In this paper a new unsupervised method is proposed for a Indian language: Telugu, based on the unsupervised method for Hindi, to generate the Out of Vocabulary (OOV) words in the language model. By using techniques like smoothing and interpolation of pre-processed data with supervised and unsupervised stemming, different issues in language model for Indian language: Telugu has been addressed. We observe that the smoothing techniques Witten-Bell and Kneser-Ney perform well when compared to other techniques on pre-processed data from supervised learning. The ASRs accuracy is improved by 0.76% and 0.94% with supervised and unsupervised stemming respectively. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2019-08-10 |
| URL | https://arxiv.org/abs/1908.03734v1 |
| https://arxiv.org/pdf/1908.03734v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-stemming-based-language-model |
| Repo | |
| Framework | |
Evolutionary Algorithms for the Chance-Constrained Knapsack Problem
| Title | Evolutionary Algorithms for the Chance-Constrained Knapsack Problem |
| Authors | Yue Xie, Oscar Harper, Hirad Assimi, Aneta Neumann, Frank Neumann |
| Abstract | Evolutionary algorithms have been widely used for a range of stochastic optimization problems. In most studies, the goal is to optimize the expected quality of the solution. Motivated by real-world problems where constraint violations have extremely disruptive effects, we consider a variant of the knapsack problem where the profit is maximized under the constraint that the knapsack capacity bound is violated with a small probability of at most $\alpha$. This problem is known as chance-constrained knapsack problem and chance-constrained optimization problems have so far gained little attention in the evolutionary computation literature. We show how to use popular deviation inequalities such as Chebyshev’s inequality and Chernoff bounds as part of the solution evaluation when tackling these problems by evolutionary algorithms and compare the effectiveness of our algorithms on a wide range of chance-constrained knapsack instances. |
| Tasks | Stochastic Optimization |
| Published | 2019-02-13 |
| URL | http://arxiv.org/abs/1902.04767v1 |
| http://arxiv.org/pdf/1902.04767v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolutionary-algorithms-for-the-chance |
| Repo | |
| Framework | |
Salient Object Detection: A Distinctive Feature Integration Model
| Title | Salient Object Detection: A Distinctive Feature Integration Model |
| Authors | Abdullah J. Alzahrani, Hina Afridi |
| Abstract | We propose a novel method for salient object detection in different images. Our method integrates spatial features for efficient and robust representation to capture meaningful information about the salient objects. We then train a conditional random field (CRF) using the integrated features. The trained CRF model is then used to detect salient objects during the online testing stage. We perform experiments on two standard datasets and compare the performance of our method with different reference methods. Our experiments show that our method outperforms the compared methods in terms of precision, recall, and F-Measure. |
| Tasks | Object Detection, Salient Object Detection |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08868v1 |
| http://arxiv.org/pdf/1904.08868v1.pdf | |
| PWC | https://paperswithcode.com/paper/salient-object-detection-a-distinctive |
| Repo | |
| Framework | |
Gland Segmentation in Histopathology Images Using Deep Networks and Handcrafted Features
| Title | Gland Segmentation in Histopathology Images Using Deep Networks and Handcrafted Features |
| Authors | Safiyeh Rezaei, Ali Emami, Hamidreza Zarrabi, Shima Rafiei, Kayvan Najarian, Nader Karimi, Shadrokh Samavi, S. M. Reza Soroushmehr |
| Abstract | Histopathology images contain essential information for medical diagnosis and prognosis of cancerous disease. Segmentation of glands in histopathology images is a primary step for analysis and diagnosis of an unhealthy patient. Due to the widespread application and the great success of deep neural networks in intelligent medical diagnosis and histopathology, we propose a modified version of LinkNet for gland segmentation and recognition of malignant cases. We show that using specific handcrafted features such as invariant local binary pattern drastically improves the system performance. The experimental results demonstrate the competency of the proposed system against state-of-the-art methods. We achieved the best results in testing on section B images of the Warwick-QU dataset and obtained comparable results on section A images. |
| Tasks | Medical Diagnosis |
| Published | 2019-08-31 |
| URL | https://arxiv.org/abs/1909.00270v1 |
| https://arxiv.org/pdf/1909.00270v1.pdf | |
| PWC | https://paperswithcode.com/paper/gland-segmentation-in-histopathology-images-1 |
| Repo | |
| Framework | |
DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection
| Title | DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection |
| Authors | Yun Liu, Ming-Ming Cheng, Xinyu Zhang, Guang-Yu Nie, Meng Wang |
| Abstract | Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs). Many popular methods impose deep supervision to perform side-output predictions that are linearly aggregated for final saliency prediction. In this paper, we theoretically and experimentally demonstrate that linear aggregation of side-output predictions is suboptimal, and it only makes limited use of the side-output information obtained by deep supervision. To solve this problem, we propose Deeply-supervised Nonlinear Aggregation (DNA) for better leveraging the complementary information of various side-outputs. Compared with existing methods, it i) aggregates side-output features rather than predictions, and ii) adopts nonlinear instead of linear transformations. Experiments demonstrate that DNA can successfully break through the bottleneck of current linear approaches. Specifically, the proposed saliency detector, a modified U-Net architecture with DNA, performs favorably against state-of-the-art methods on various datasets and evaluation metrics without bells and whistles. Code and data will be released upon paper acceptance. |
| Tasks | Object Detection, Saliency Prediction, Salient Object Detection |
| Published | 2019-03-28 |
| URL | https://arxiv.org/abs/1903.12476v2 |
| https://arxiv.org/pdf/1903.12476v2.pdf | |
| PWC | https://paperswithcode.com/paper/dna-deeply-supervised-nonlinear-aggregation |
| Repo | |
| Framework | |
SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums
| Title | SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums |
| Authors | Tsvetomila Mihaylova, Georgi Karadjov, Pepa Atanasova, Ramy Baly, Mitra Mohtarami, Preslav Nakov |
| Abstract | We present SemEval-2019 Task 8 on Fact Checking in Community Question Answering Forums, which features two subtasks. Subtask A is about deciding whether a question asks for factual information vs. an opinion/advice vs. just socializing. Subtask B asks to predict whether an answer to a factual question is true, false or not a proper answer. We received 17 official submissions for subtask A and 11 official submissions for Subtask B. For subtask A, all systems improved over the majority class baseline. For Subtask B, all systems were below a majority class baseline, but several systems were very close to it. The leaderboard and the data from the competition can be found at http://competitions.codalab.org/competitions/20022 |
| Tasks | Community Question Answering, Question Answering |
| Published | 2019-05-25 |
| URL | https://arxiv.org/abs/1906.01727v1 |
| https://arxiv.org/pdf/1906.01727v1.pdf | |
| PWC | https://paperswithcode.com/paper/190601727 |
| Repo | |
| Framework | |
RGB-D image-based Object Detection: from Traditional Methods to Deep Learning Techniques
| Title | RGB-D image-based Object Detection: from Traditional Methods to Deep Learning Techniques |
| Authors | Isaac Ronald Ward, Hamid Laga, Mohammed Bennamoun |
| Abstract | Object detection from RGB images is a long-standing problem in image processing and computer vision. It has applications in various domains including robotics, surveillance, human-computer interaction, and medical diagnosis. With the availability of low cost 3D scanners, a large number of RGB-D object detection approaches have been proposed in the past years. This chapter provides a comprehensive survey of the recent developments in this field. We structure the chapter into two parts; the focus of the first part is on techniques that are based on hand-crafted features combined with machine learning algorithms. The focus of the second part is on the more recent work, which is based on deep learning. Deep learning techniques, coupled with the availability of large training datasets, have now revolutionized the field of computer vision, including RGB-D object detection, achieving an unprecedented level of performance. We survey the key contributions, summarize the most commonly used pipelines, discuss their benefits and limitations, and highlight some important directions for future research. |
| Tasks | Medical Diagnosis, Object Detection |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09236v1 |
| https://arxiv.org/pdf/1907.09236v1.pdf | |
| PWC | https://paperswithcode.com/paper/rgb-d-image-based-object-detection-from |
| Repo | |
| Framework | |
Be Consistent! Improving Procedural Text Comprehension using Label Consistency
| Title | Be Consistent! Improving Procedural Text Comprehension using Label Consistency |
| Authors | Xinya Du, Bhavana Dalvi Mishra, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark, Claire Cardie |
| Abstract | Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about photosynthesis, a recipe). This task is challenging as the world is changing throughout the text, and despite recent advances, current systems still struggle with this task. Our approach is to leverage the fact that, for many procedural texts, multiple independent descriptions are readily available, and that predictions from them should be consistent (label consistency). We present a new learning framework that leverages label consistency during training, allowing consistency bias to be built into the model. Evaluation on a standard benchmark dataset for procedural text, ProPara (Dalvi et al., 2018), shows that our approach significantly improves prediction performance (F1) over prior state-of-the-art systems. |
| Tasks | Reading Comprehension |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.08942v1 |
| https://arxiv.org/pdf/1906.08942v1.pdf | |
| PWC | https://paperswithcode.com/paper/be-consistent-improving-procedural-text-1 |
| Repo | |
| Framework | |
Salient object detection on hyperspectral images using features learned from unsupervised segmentation task
| Title | Salient object detection on hyperspectral images using features learned from unsupervised segmentation task |
| Authors | Nevrez Imamoglu, Guanqun Ding, Yuming Fang, Asako Kanezaki, Toru Kouyama, Ryosuke Nakamura |
| Abstract | Various saliency detection algorithms from color images have been proposed to mimic eye fixation or attentive object detection response of human observers for the same scenes. However, developments on hyperspectral imaging systems enable us to obtain redundant spectral information of the observed scenes from the reflected light source from objects. A few studies using low-level features on hyperspectral images demonstrated that salient object detection can be achieved. In this work, we proposed a salient object detection model on hyperspectral images by applying manifold ranking (MR) on self-supervised Convolutional Neural Network (CNN) features (high-level features) from unsupervised image segmentation task. Self-supervision of CNN continues until clustering loss or saliency maps converges to a defined error between each iteration. Finally, saliency estimations is done as the saliency map at last iteration when the self-supervision procedure terminates with convergence. Experimental evaluations demonstrated that proposed saliency detection algorithm on hyperspectral images is outperforming state-of-the-arts hyperspectral saliency models including the original MR based saliency model. |
| Tasks | Object Detection, Saliency Detection, Salient Object Detection, Semantic Segmentation |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.10993v1 |
| http://arxiv.org/pdf/1902.10993v1.pdf | |
| PWC | https://paperswithcode.com/paper/salient-object-detection-on-hyperspectral |
| Repo | |
| Framework | |
Vision-Based Autonomous UAV Navigation and Landing for Urban Search and Rescue
| Title | Vision-Based Autonomous UAV Navigation and Landing for Urban Search and Rescue |
| Authors | Mayank Mittal, Rohit Mohan, Wolfram Burgard, Abhinav Valada |
| Abstract | Unmanned Aerial Vehicles (UAVs) equipped with bioradars are a life-saving technology that can enable identification of survivors under collapsed buildings in the aftermath of natural disasters such as earthquakes or gas explosions. However, these UAVs have to be able to autonomously navigate in disaster struck environments and land on debris piles in order to accurately locate the survivors. This problem is extremely challenging as pre-existing maps cannot be leveraged for navigation due to structural changes that may have occurred. Furthermore, existing landing site detection algorithms are not suitable to identify safe landing regions on debris piles. In this work, we present a computationally efficient system for autonomous UAV navigation and landing that does not require any prior knowledge about the environment. We propose a novel landing site detection algorithm that computes costmaps based on several hazard factors including terrain flatness, steepness, depth accuracy, and energy consumption information. We also introduce a first-of-a-kind synthetic dataset of over 1.2 million images of collapsed buildings with groundtruth depth, surface normals, semantics and camera pose information. We demonstrate the efficacy of our system using experiments from a city scale hyperrealistic simulation environment and in real-world scenarios with collapsed buildings. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01304v2 |
| https://arxiv.org/pdf/1906.01304v2.pdf | |
| PWC | https://paperswithcode.com/paper/vision-based-autonomous-uav-navigation-and |
| Repo | |
| Framework | |
Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight
| Title | Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight |
| Authors | Annie Xie, Frederik Ebert, Sergey Levine, Chelsea Finn |
| Abstract | Machine learning techniques have enabled robots to learn narrow, yet complex tasks and also perform broad, yet simple skills with a wide variety of objects. However, learning a model that can both perform complex tasks and generalize to previously unseen objects and goals remains a significant challenge. We study this challenge in the context of “improvisational” tool use: a robot is presented with novel objects and a user-specified goal (e.g., sweep some clutter into the dustpan), and must figure out, using only raw image observations, how to accomplish the goal using the available objects as tools. We approach this problem by training a model with both a visual and physical understanding of multi-object interactions, and develop a sampling-based optimizer that can leverage these interactions to accomplish tasks. We do so by combining diverse demonstration data with self-supervised interaction data, aiming to leverage the interaction data to build generalizable models and the demonstration data to guide the model-based RL planner to solve complex tasks. Our experiments show that our approach can solve a variety of complex tool use tasks from raw pixel inputs, outperforming both imitation learning and self-supervised learning individually. Furthermore, we show that the robot can perceive and use novel objects as tools, including objects that are not conventional tools, while also choosing dynamically to use or not use tools depending on whether or not they are required. |
| Tasks | Imitation Learning |
| Published | 2019-04-11 |
| URL | http://arxiv.org/abs/1904.05538v1 |
| http://arxiv.org/pdf/1904.05538v1.pdf | |
| PWC | https://paperswithcode.com/paper/improvisation-through-physical-understanding |
| Repo | |
| Framework | |
