Paper Group ANR 719
A Summary of the 4th International Workshop on Recovering 6D Object Pose. Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing. The Three Pillars of Machine Programming. Robust 6D Object Pose Estimation in Cluttered Scenes using Semantic Segmentation and Pose Regression Networks. When do Words Matter? Understanding the …
A Summary of the 4th International Workshop on Recovering 6D Object Pose
Title | A Summary of the 4th International Workshop on Recovering 6D Object Pose |
Authors | Tomas Hodan, Rigas Kouskouridas, Tae-Kyun Kim, Federico Tombari, Kostas Bekris, Bertram Drost, Thibault Groueix, Krzysztof Walas, Vincent Lepetit, Ales Leonardis, Carsten Steger, Frank Michel, Caner Sahin, Carsten Rother, Jiri Matas |
Abstract | This document summarizes the 4th International Workshop on Recovering 6D Object Pose which was organized in conjunction with ECCV 2018 in Munich. The workshop featured four invited talks, oral and poster presentations of accepted workshop papers, and an introduction of the BOP benchmark for 6D object pose estimation. The workshop was attended by 100+ people working on relevant topics in both academia and industry who shared up-to-date advances and discussed open problems. |
Tasks | 6D Pose Estimation using RGB, Pose Estimation |
Published | 2018-10-09 |
URL | http://arxiv.org/abs/1810.03758v1 |
http://arxiv.org/pdf/1810.03758v1.pdf | |
PWC | https://paperswithcode.com/paper/a-summary-of-the-4th-international-workshop |
Repo | |
Framework | |
Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing
Title | Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing |
Authors | Zhuo Chen, Weisi Lin, Shiqi Wang, Lingyu Duan, Alex C. Kot |
Abstract | The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical. To better enable the intelligent sensing at the front-end, instead of compressing and transmitting visual signals or the ultimately utilized top-layer deep learning features, we propose to compactly represent and convey the intermediate-layer deep learning features of high generalization capability, to facilitate the collaborating approach between front and cloud ends. This strategy enables a good balance among the computational load, transmission load and the generalization ability for cloud servers when deploying the deep neural networks for large scale cloud based visual analysis. Moreover, the presented strategy also makes the standardization of deep feature coding more feasible and promising, as a series of tasks can simultaneously benefit from the transmitted intermediate layers. We also present the results for evaluation of lossless deep feature compression with four benchmark data compression methods, which provides meaningful investigations and baselines for future research and standardization activities. |
Tasks | |
Published | 2018-09-17 |
URL | http://arxiv.org/abs/1809.06196v1 |
http://arxiv.org/pdf/1809.06196v1.pdf | |
PWC | https://paperswithcode.com/paper/intermediate-deep-feature-compression-the |
Repo | |
Framework | |
The Three Pillars of Machine Programming
Title | The Three Pillars of Machine Programming |
Authors | Justin Gottschlich, Armando Solar-Lezama, Nesime Tatbul, Michael Carbin, Martin Rinard, Regina Barzilay, Saman Amarasinghe, Joshua B Tenenbaum, Tim Mattson |
Abstract | In this position paper, we describe our vision of the future of machine programming through a categorical examination of three pillars of research. Those pillars are: (i) intention, (ii) invention, and(iii) adaptation. Intention emphasizes advancements in the human-to-computer and computer-to-machine-learning interfaces. Invention emphasizes the creation or refinement of algorithms or core hardware and software building blocks through machine learning (ML). Adaptation emphasizes advances in the use of ML-based constructs to autonomously evolve software. |
Tasks | |
Published | 2018-03-20 |
URL | http://arxiv.org/abs/1803.07244v2 |
http://arxiv.org/pdf/1803.07244v2.pdf | |
PWC | https://paperswithcode.com/paper/the-three-pillars-of-machine-programming |
Repo | |
Framework | |
Robust 6D Object Pose Estimation in Cluttered Scenes using Semantic Segmentation and Pose Regression Networks
Title | Robust 6D Object Pose Estimation in Cluttered Scenes using Semantic Segmentation and Pose Regression Networks |
Authors | Arul Selvam Periyasamy, Max Schwarz, Sven Behnke |
Abstract | Object pose estimation is a crucial prerequisite for robots to perform autonomous manipulation in clutter. Real-world bin-picking settings such as warehouses present additional challenges, e.g., new objects are added constantly. Most of the existing object pose estimation methods assume that 3D models of the objects is available beforehand. We present a pipeline that requires minimal human intervention and circumvents the reliance on the availability of 3D models by a fast data acquisition method and a synthetic data generation procedure. This work builds on previous work on semantic segmentation of cluttered bin-picking scenes to isolate individual objects in clutter. An additional network is trained on synthetic scenes to estimate object poses from a cropped object-centered encoding extracted from the segmentation results. The proposed method is evaluated on a synthetic validation dataset and cluttered real-world scenes. |
Tasks | 6D Pose Estimation using RGB, Pose Estimation, Semantic Segmentation, Synthetic Data Generation |
Published | 2018-10-08 |
URL | http://arxiv.org/abs/1810.03410v1 |
http://arxiv.org/pdf/1810.03410v1.pdf | |
PWC | https://paperswithcode.com/paper/robust-6d-object-pose-estimation-in-cluttered |
Repo | |
Framework | |
When do Words Matter? Understanding the Impact of Lexical Choice on Audience Perception using Individual Treatment Effect Estimation
Title | When do Words Matter? Understanding the Impact of Lexical Choice on Audience Perception using Individual Treatment Effect Estimation |
Authors | Zhao Wang, Aron Culotta |
Abstract | Studies across many disciplines have shown that lexical choice can affect audience perception. For example, how users describe themselves in a social media profile can affect their perceived socio-economic status. However, we lack general methods for estimating the causal effect of lexical choice on the perception of a specific sentence. While randomized controlled trials may provide good estimates, they do not scale to the potentially millions of comparisons necessary to consider all lexical choices. Instead, in this paper, we first offer two classes of methods to estimate the effect on perception of changing one word to another in a given sentence. The first class of algorithms builds upon quasi-experimental designs to estimate individual treatment effects from observational data. The second class treats treatment effect estimation as a classification problem. We conduct experiments with three data sources (Yelp, Twitter, and Airbnb), finding that the algorithmic estimates align well with those produced by randomized-control trials. Additionally, we find that it is possible to transfer treatment effect classifiers across domains and still maintain high accuracy. |
Tasks | |
Published | 2018-11-12 |
URL | http://arxiv.org/abs/1811.04890v4 |
http://arxiv.org/pdf/1811.04890v4.pdf | |
PWC | https://paperswithcode.com/paper/when-do-words-matter-understanding-the-impact |
Repo | |
Framework | |
Incorporating Consistency Verification into Neural Data-to-Document Generation
Title | Incorporating Consistency Verification into Neural Data-to-Document Generation |
Authors | Feng Nie, Hailin Chen, Jinpeng Wang, Jin-Ge Yao, Chin-Yew Lin, Rong Pan |
Abstract | Recent neural models for data-to-document generation have achieved remarkable progress in producing fluent and informative texts. However, large proportions of generated texts do not actually conform to the input data. To address this issue, we propose a new training framework which attempts to verify the consistency between the generated texts and the input data to guide the training process. To measure the consistency, a relation extraction model is applied to check information overlaps between the input data and the generated texts. The non-differentiable consistency signal is optimized via reinforcement learning. Experimental results on a recently released challenging dataset ROTOWIRE show improvements from our framework in various metrics. |
Tasks | Relation Extraction |
Published | 2018-08-15 |
URL | http://arxiv.org/abs/1808.05306v2 |
http://arxiv.org/pdf/1808.05306v2.pdf | |
PWC | https://paperswithcode.com/paper/incorporating-consistency-verification-into |
Repo | |
Framework | |
Generative Invertible Networks (GIN): Pathophysiology-Interpretable Feature Mapping and Virtual Patient Generation
Title | Generative Invertible Networks (GIN): Pathophysiology-Interpretable Feature Mapping and Virtual Patient Generation |
Authors | Jialei Chen, Yujia Xie, Kan Wang, Zih Huei Wang, Geet Lahoti, Chuck Zhang, Mani A Vannan, Ben Wang, Zhen Qian |
Abstract | Machine learning methods play increasingly important roles in pre-procedural planning for complex surgeries and interventions. Very often, however, researchers find the historical records of emerging surgical techniques, such as the transcatheter aortic valve replacement (TAVR), are highly scarce in quantity. In this paper, we address this challenge by proposing novel generative invertible networks (GIN) to select features and generate high-quality virtual patients that may potentially serve as an additional data source for machine learning. Combining a convolutional neural network (CNN) and generative adversarial networks (GAN), GIN discovers the pathophysiologic meaning of the feature space. Moreover, a test of predicting the surgical outcome directly using the selected features results in a high accuracy of 81.55%, which suggests little pathophysiologic information has been lost while conducting the feature selection. This demonstrates GIN can generate virtual patients not only visually authentic but also pathophysiologically interpretable. |
Tasks | Feature Selection |
Published | 2018-08-14 |
URL | http://arxiv.org/abs/1808.04495v1 |
http://arxiv.org/pdf/1808.04495v1.pdf | |
PWC | https://paperswithcode.com/paper/generative-invertible-networks-gin |
Repo | |
Framework | |
Proceedings of NeurIPS 2018 Workshop on Machine Learning for the Developing World: Achieving Sustainable Impact
Title | Proceedings of NeurIPS 2018 Workshop on Machine Learning for the Developing World: Achieving Sustainable Impact |
Authors | Maria De-Arteaga, Amanda Coston, William Herlands |
Abstract | This is the Proceedings of NeurIPS 2018 Workshop on Machine Learning for the Developing World: Achieving Sustainable Impact, held in Montreal, Canada on December 8, 2018 |
Tasks | |
Published | 2018-12-21 |
URL | http://arxiv.org/abs/1812.10398v2 |
http://arxiv.org/pdf/1812.10398v2.pdf | |
PWC | https://paperswithcode.com/paper/proceedings-of-neurips-2018-workshop-on |
Repo | |
Framework | |
Bad practices in evaluation methodology relevant to class-imbalanced problems
Title | Bad practices in evaluation methodology relevant to class-imbalanced problems |
Authors | Jan Brabec, Lukas Machlica |
Abstract | For research to go in the right direction, it is essential to be able to compare and quantify performance of different algorithms focused on the same problem. Choosing a suitable evaluation metric requires deep understanding of the pursued task along with all of its characteristics. We argue that in the case of applied machine learning, proper evaluation metric is the basic building block that should be in the spotlight and put under thorough examination. Here, we address tasks with class imbalance, in which the class of interest is the one with much lower number of samples. We encountered non-insignificant amount of recent papers, in which improper evaluation methods are used, borrowed mainly from the field of balanced problems. Such bad practices may heavily bias the results in favour of inappropriate algorithms and give false expectations of the state of the field. |
Tasks | |
Published | 2018-12-04 |
URL | http://arxiv.org/abs/1812.01388v1 |
http://arxiv.org/pdf/1812.01388v1.pdf | |
PWC | https://paperswithcode.com/paper/bad-practices-in-evaluation-methodology |
Repo | |
Framework | |
Learning Classical Planning Strategies with Policy Gradient
Title | Learning Classical Planning Strategies with Policy Gradient |
Authors | Pawel Gomoluch, Dalal Alrajeh, Alessandra Russo |
Abstract | A common paradigm in classical planning is heuristic forward search. Forward search planners often rely on simple best-first search which remains fixed throughout the search process. In this paper, we introduce a novel search framework capable of alternating between several forward search approaches while solving a particular planning problem. Selection of the approach is performed using a trainable stochastic policy, mapping the state of the search to a probability distribution over the approaches. This enables using policy gradient to learn search strategies tailored to a specific distributions of planning problems and a selected performance metric, e.g. the IPC score. We instantiate the framework by constructing a policy space consisting of five search approaches and a two-dimensional representation of the planner’s state. Then, we train the system on randomly generated problems from five IPC domains using three different performance metrics. Our experimental results show that the learner is able to discover domain-specific search strategies, improving the planner’s performance relative to the baselines of plain best-first search and a uniform policy. |
Tasks | |
Published | 2018-10-23 |
URL | http://arxiv.org/abs/1810.09923v2 |
http://arxiv.org/pdf/1810.09923v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-classical-planning-strategies-with |
Repo | |
Framework | |
Synthetic contrast enhancement in cardiac CT with Deep Learning
Title | Synthetic contrast enhancement in cardiac CT with Deep Learning |
Authors | Gianmarco Santini, Lorena M. Zumbo, Nicola Martini, Gabriele Valvano, Andrea Leo, Andrea Ripoli, Francesco Avogliero, Dante Chiappino, Daniele Della Latta |
Abstract | In Europe the 20% of the CT scans cover the thoracic region. The acquired images contain information about the cardiovascular system that often remains latent due to the lack of contrast in the cardiac area. On the other hand, the contrast enhanced computed tomography (CECT) represents an imaging technique that allows to easily assess the cardiac chambers volumes and the contrast dynamics. With this work we aim to face the problem of extraction and presentation of these latent information, using a deep learning approach with convolutional neural networks. Starting from the extraction of relevant features from the image without contrast medium, we try to re-map them on features typical of CECT, to synthesize an image characterized by an attenuation in the cardiac chambers as if a virtually iodine contrast medium was injected. The purposes are to guarantee an estimation of the left cardiac chambers volume and to perform an evaluation of the contrast dynamics. Our approach is based on a deconvolutional network trained on a set of 120 patients who underwent both CT acquisitions in the same contrastographic arterial phase and the same cardiac phase. To ensure a reliable predicted CECT image, in terms of values and morphology, a custom loss function is defined by combining an error function to find a pixel-wise correspondence, which takes into account the similarity in term of Hounsfield units between the input and output images and by a cross-entropy computed on the binarized versions of the synthesized and of the real CECT image. The proposed method is finally tested on 20 subjects. |
Tasks | |
Published | 2018-07-02 |
URL | http://arxiv.org/abs/1807.01779v1 |
http://arxiv.org/pdf/1807.01779v1.pdf | |
PWC | https://paperswithcode.com/paper/synthetic-contrast-enhancement-in-cardiac-ct |
Repo | |
Framework | |
Multi-lingual neural title generation for e-Commerce browse pages
Title | Multi-lingual neural title generation for e-Commerce browse pages |
Authors | Prashant Mathur, Nicola Ueffing, Gregor Leusch |
Abstract | To provide better access of the inventory to buyers and better search engine optimization, e-Commerce websites are automatically generating millions of easily searchable browse pages. A browse page consists of a set of slot name/value pairs within a given category, grouping multiple items which share some characteristics. These browse pages require a title describing the content of the page. Since the number of browse pages are huge, manual creation of these titles is infeasible. Previous statistical and neural approaches depend heavily on the availability of large amounts of data in a language. In this research, we apply sequence-to-sequence models to generate titles for high- & low-resourced languages by leveraging transfer learning. We train these models on multi-lingual data, thereby creating one joint model which can generate titles in various different languages. Performance of the title generation system is evaluated on three different languages; English, German, and French, with a particular focus on low-resourced French language. |
Tasks | Transfer Learning |
Published | 2018-04-03 |
URL | http://arxiv.org/abs/1804.01041v1 |
http://arxiv.org/pdf/1804.01041v1.pdf | |
PWC | https://paperswithcode.com/paper/multi-lingual-neural-title-generation-for-e |
Repo | |
Framework | |
Automatic Text Document Summarization using Semantic-based Analysis
Title | Automatic Text Document Summarization using Semantic-based Analysis |
Authors | Chandra Shekhar Yadav |
Abstract | Since the advent of the web, the amount of data on wen has been increased several million folds. In recent years web data generated is more than data stored for years. One important data format is text. To answer user queries over the internet, and to overcome the problem of information overload one possible solution is text document summarization. This not only reduces query access time, but also optimize the document results according to specific users requirements. Summarization of text document can be categorized as abstractive and extractive. Most of the work has been done in the direction of Extractive summarization. Extractive summarized result is a subset of original documents with the objective of more content coverage and lea redundancy. Our work is based on Extractive approaches. In the first approach, we are using some statistical features and semantic-based features. To include sentiment as a feature is an idea cached from a view that emotion plays an important role. It effectively conveys a message. So, it may play a vital role in text document summarization. |
Tasks | Document Summarization |
Published | 2018-11-15 |
URL | http://arxiv.org/abs/1811.06567v1 |
http://arxiv.org/pdf/1811.06567v1.pdf | |
PWC | https://paperswithcode.com/paper/automatic-text-document-summarization-using |
Repo | |
Framework | |
Convolutional Neural Networks for Aerial Vehicle Detection and Recognition
Title | Convolutional Neural Networks for Aerial Vehicle Detection and Recognition |
Authors | Amir Soleimani, Nasser M. Nasrabadi, Elias Griffith, Jason Ralph, Simon Maskell |
Abstract | This paper investigates the problem of aerial vehicle recognition using a text-guided deep convolutional neural network classifier. The network receives an aerial image and a desired class, and makes a yes or no output by matching the image and the textual description of the desired class. We train and test our model on a synthetic aerial dataset and our desired classes consist of the combination of the class types and colors of the vehicles. This strategy helps when considering more classes in testing than in training. |
Tasks | |
Published | 2018-08-26 |
URL | http://arxiv.org/abs/1808.08560v1 |
http://arxiv.org/pdf/1808.08560v1.pdf | |
PWC | https://paperswithcode.com/paper/convolutional-neural-networks-for-aerial |
Repo | |
Framework | |
Sentiment Classification of Customer Reviews about Automobiles in Roman Urdu
Title | Sentiment Classification of Customer Reviews about Automobiles in Roman Urdu |
Authors | Moin Khan, Kamran Malik |
Abstract | Text mining is a broad field having sentiment mining as its important constituent in which we try to deduce the behavior of people towards a specific item, merchandise, politics, sports, social media comments, review sites etc. Out of many issues in sentiment mining, analysis and classification, one major issue is that the reviews and comments can be in different languages like English, Arabic, Urdu etc. Handling each language according to its rules is a difficult task. A lot of research work has been done in English Language for sentiment analysis and classification but limited sentiment analysis work is being carried out on other regional languages like Arabic, Urdu and Hindi. In this paper, Waikato Environment for Knowledge Analysis (WEKA) is used as a platform to execute different classification models for text classification of Roman Urdu text. Reviews dataset has been scrapped from different automobiles sites. These extracted Roman Urdu reviews, containing 1000 positive and 1000 negative reviews, are then saved in WEKA attribute-relation file format (arff) as labeled examples. Training is done on 80% of this data and rest of it is used for testing purpose which is done using different models and results are analyzed in each case. The results show that Multinomial Naive Bayes outperformed Bagging, Deep Neural Network, Decision Tree, Random Forest, AdaBoost, k-NN and SVM Classifiers in terms of more accuracy, precision, recall and F-measure. |
Tasks | Sentiment Analysis, Text Classification |
Published | 2018-12-30 |
URL | http://arxiv.org/abs/1812.11587v1 |
http://arxiv.org/pdf/1812.11587v1.pdf | |
PWC | https://paperswithcode.com/paper/sentiment-classification-of-customer-reviews |
Repo | |
Framework | |