Paper Group ANR 803
Confidence intervals for class prevalences under prior probability shift. A New Few-shot Segmentation Network Based on Class Representation. Deep Probabilistic Surrogate Networks for Universal Simulator Approximation. Universal Marginaliser for Deep Amortised Inference for Probabilistic Programs. Virtual Piano using Computer Vision. Strengthening t …
Confidence intervals for class prevalences under prior probability shift
| Title | Confidence intervals for class prevalences under prior probability shift |
| Authors | Dirk Tasche |
| Abstract | Point estimation of class prevalences in the presence of data set shift has been a popular research topic for more than two decades. Less attention has been paid to the construction of confidence and prediction intervals for estimates of class prevalences. One little considered question is whether or not it is necessary for practical purposes to distinguish confidence and prediction intervals. Another question so far not yet conclusively answered is whether or not the discriminatory power of the classifier or score at the basis of an estimation method matters for the accuracy of the estimates of the class prevalences. This paper presents a simulation study aimed at shedding some light on these and other related questions. |
| Tasks | |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.04119v2 |
| https://arxiv.org/pdf/1906.04119v2.pdf | |
| PWC | https://paperswithcode.com/paper/confidence-intervals-for-class-prevalences |
| Repo | |
| Framework | |
A New Few-shot Segmentation Network Based on Class Representation
| Title | A New Few-shot Segmentation Network Based on Class Representation |
| Authors | Yuwei Yang, Fanman Meng, Hongliang Li, King N. Ngan, Qingbo Wu |
| Abstract | This paper studies few-shot segmentation, which is a task of predicting foreground mask of unseen classes by a few of annotations only, aided by a set of rich annotations already existed. The existing methods mainly focus the task on “\textit{how to transfer segmentation cues from support images (labeled images) to query images (unlabeled images)}", and try to learn efficient and general transfer module that can be easily extended to unseen classes. However, it is proved to be a challenging task to learn the transfer module that is general to various classes. This paper solves few-shot segmentation in a new perspective of “\textit{how to represent unseen classes by existing classes}", and formulates few-shot segmentation as the representation process that represents unseen classes (in terms of forming the foreground prior) by existing classes precisely. Based on such idea, we propose a new class representation based few-shot segmentation framework, which firstly generates class activation map of unseen class based on the knowledge of existing classes, and then uses the map as foreground probability map to extract the foregrounds from query image. A new two-branch based few-shot segmentation network is proposed. Moreover, a new CAM generation module that extracts the CAM of unseen classes rather than the classical training classes is raised. We validate the effectiveness of our method on Pascal VOC 2012 dataset, the value FB-IoU of one-shot and five-shot arrives at 69.2% and 70.1% respectively, which outperforms the state-of-the-art method. |
| Tasks | |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08754v1 |
| https://arxiv.org/pdf/1909.08754v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-few-shot-segmentation-network-based-on |
| Repo | |
| Framework | |
Deep Probabilistic Surrogate Networks for Universal Simulator Approximation
| Title | Deep Probabilistic Surrogate Networks for Universal Simulator Approximation |
| Authors | Andreas Munk, Adam Ścibior, Atılım Güneş Baydin, Andrew Stewart, Goran Fernlund, Anoush Poursartip, Frank Wood |
| Abstract | We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of existing stochastic simulators. Unlike traditional approaches to surrogate modeling, our surrogates retain the interpretable structure of the reference simulators. The particular way we achieve this allows us to replace the reference simulator with the surrogate when undertaking amortized inference in the probabilistic programming sense. The fidelity and speed of our surrogates allow for not only faster “forward” stochastic simulation but also for accurate and substantially faster inference. We support these claims via experiments that involve a commercial composite-materials curing simulator. Employing our surrogate modeling technique makes inference an order of magnitude faster, opening up the possibility of doing simulator-based, non-invasive, just-in-time parts quality testing; in this case inferring safety-critical latent internal temperature profiles of composite materials undergoing curing from surface temperature profile measurements. |
| Tasks | Probabilistic Programming |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11950v1 |
| https://arxiv.org/pdf/1910.11950v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-probabilistic-surrogate-networks-for |
| Repo | |
| Framework | |
Universal Marginaliser for Deep Amortised Inference for Probabilistic Programs
| Title | Universal Marginaliser for Deep Amortised Inference for Probabilistic Programs |
| Authors | Robert Walecki, Kostis Gourgoulias, Adam Baker, Chris Hart, Chris Lucas, Max Zwiessele, Albert Buchard, Maria Lomeli, Yura Perov, Saurabh Johri |
| Abstract | Probabilistic programming languages (PPLs) are powerful modelling tools which allow to formalise our knowledge about the world and reason about its inherent uncertainty. Inference methods used in PPL can be computationally costly due to significant time burden and/or storage requirements; or they can lack theoretical guarantees of convergence and accuracy when applied to large scale graphical models. To this end, we present the Universal Marginaliser (UM), a novel method for amortised inference, in PPL. We show how combining samples drawn from the original probabilistic program prior with an appropriate augmentation method allows us to train one neural network to approximate any of the corresponding conditional marginal distributions, with any separation into latent and observed variables, and thus amortise the cost of inference. Finally, we benchmark the method on multiple probabilistic programs, in Pyro, with different model structure. |
| Tasks | Probabilistic Programming |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07474v1 |
| https://arxiv.org/pdf/1910.07474v1.pdf | |
| PWC | https://paperswithcode.com/paper/universal-marginaliser-for-deep-amortised |
| Repo | |
| Framework | |
Virtual Piano using Computer Vision
| Title | Virtual Piano using Computer Vision |
| Authors | Seongjae Kang, Jaeyoon Kim, Sung-eui Yoon |
| Abstract | In this research, Piano performances have been analyzed only based on visual information. Computer vision algorithms, e.g., Hough transform and binary thresholding, have been applied to find where the keyboard and specific keys are located. At the same time, Convolutional Neural Networks(CNNs) has been also utilized to find whether specific keys are pressed or not, and how much intensity the keys are pressed only based on visual information. Especially for detecting intensity, a new method of utilizing spatial, temporal CNNs model is devised. Early fusion technique is especially applied in temporal CNNs architecture to analyze hand movement. We also make a new dataset for training each model. Especially when finding an intensity of a pressed key, both of video frames and their optical flow images are used to train models to find effectiveness. |
| Tasks | Optical Flow Estimation |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12539v1 |
| https://arxiv.org/pdf/1910.12539v1.pdf | |
| PWC | https://paperswithcode.com/paper/virtual-piano-using-computer-vision |
| Repo | |
| Framework | |
Strengthening the Case for a Bayesian Approach to Car-following Model Calibration and Validation using Probabilistic Programming
| Title | Strengthening the Case for a Bayesian Approach to Car-following Model Calibration and Validation using Probabilistic Programming |
| Authors | Franklin Abodo, Andrew Berthaume, Stephen Zitzow-Childs, Leonardo Bobadilla |
| Abstract | Compute and memory constraints have historically prevented traffic simulation software users from fully utilizing the predictive models underlying them. When calibrating car-following models, particularly, accommodations have included 1) using sensitivity analysis to limit the number of parameters to be calibrated, and 2) identifying only one set of parameter values using data collected from multiple car-following instances across multiple drivers. Shortcuts are further motivated by insufficient data set sizes, for which a driver may have too few instances to fully account for the variation in their driving behavior. In this paper, we demonstrate that recent technological advances can enable transportation researchers and engineers to overcome these constraints and produce calibration results that 1) outperform industry standard approaches, and 2) allow for a unique set of parameters to be estimated for each driver in a data set, even given a small amount of data. We propose a novel calibration procedure for car-following models based on Bayesian machine learning and probabilistic programming, and apply it to real-world data from a naturalistic driving study. We also discuss how this combination of mathematical and software tools can offer additional benefits such as more informative model validation and the incorporation of true-to-data uncertainty into simulation traces. |
| Tasks | Calibration, Probabilistic Programming |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.02427v1 |
| https://arxiv.org/pdf/1908.02427v1.pdf | |
| PWC | https://paperswithcode.com/paper/strengthening-the-case-for-a-bayesian |
| Repo | |
| Framework | |
Optimization of Chance-Constrained Submodular Functions
| Title | Optimization of Chance-Constrained Submodular Functions |
| Authors | Benjamin Doerr, Carola Doerr, Aneta Neumann, Frank Neumann, Andrew M. Sutton |
| Abstract | Submodular optimization plays a key role in many real-world problems. In many real-world scenarios, it is also necessary to handle uncertainty, and potentially disruptive events that violate constraints in stochastic settings need to be avoided. In this paper, we investigate submodular optimization problems with chance constraints. We provide a first analysis on the approximation behavior of popular greedy algorithms for submodular problems with chance constraints. Our results show that these algorithms are highly effective when using surrogate functions that estimate constraint violations based on Chernoff bounds. Furthermore, we investigate the behavior of the algorithms on popular social network problems and show that high quality solutions can still be obtained even if there are strong restrictions imposed by the chance constraint. |
| Tasks | |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11451v1 |
| https://arxiv.org/pdf/1911.11451v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimization-of-chance-constrained-submodular |
| Repo | |
| Framework | |
Bayesian Synthesis of Probabilistic Programs for Automatic Data Modeling
| Title | Bayesian Synthesis of Probabilistic Programs for Automatic Data Modeling |
| Authors | Feras A. Saad, Marco F. Cusumano-Towner, Ulrich Schaechtle, Martin C. Rinard, Vikash K. Mansinghka |
| Abstract | We present new techniques for automatically constructing probabilistic programs for data analysis, interpretation, and prediction. These techniques work with probabilistic domain-specific data modeling languages that capture key properties of a broad class of data generating processes, using Bayesian inference to synthesize probabilistic programs in these modeling languages given observed data. We provide a precise formulation of Bayesian synthesis for automatic data modeling that identifies sufficient conditions for the resulting synthesis procedure to be sound. We also derive a general class of synthesis algorithms for domain-specific languages specified by probabilistic context-free grammars and establish the soundness of our approach for these languages. We apply the techniques to automatically synthesize probabilistic programs for time series data and multivariate tabular data. We show how to analyze the structure of the synthesized programs to compute, for key qualitative properties of interest, the probability that the underlying data generating process exhibits each of these properties. Second, we translate probabilistic programs in the domain-specific language into probabilistic programs in Venture, a general-purpose probabilistic programming system. The translated Venture programs are then executed to obtain predictions of new time series data and new multivariate data records. Experimental results show that our techniques can accurately infer qualitative structure in multiple real-world data sets and outperform standard data analysis methods in forecasting and predicting new data. |
| Tasks | Bayesian Inference, Probabilistic Programming, Time Series |
| Published | 2019-07-14 |
| URL | https://arxiv.org/abs/1907.06249v1 |
| https://arxiv.org/pdf/1907.06249v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-synthesis-of-probabilistic-programs |
| Repo | |
| Framework | |
Analysing Coreference in Transformer Outputs
| Title | Analysing Coreference in Transformer Outputs |
| Authors | Ekaterina Lapshinova-Koltunski, Cristina España-Bonet, Josef van Genabith |
| Abstract | We analyse coreference phenomena in three neural machine translation systems trained with different data settings with or without access to explicit intra- and cross-sentential anaphoric information. We compare system performance on two different genres: news and TED talks. To do this, we manually annotate (the possibly incorrect) coreference chains in the MT outputs and evaluate the coreference chain translations. We define an error typology that aims to go further than pronoun translation adequacy and includes types such as incorrect word selection or missing words. The features of coreference chains in automatic translations are also compared to those of the source texts and human translations. The analysis shows stronger potential translationese effects in machine translated outputs than in human translations. |
| Tasks | Machine Translation |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01188v1 |
| https://arxiv.org/pdf/1911.01188v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysing-coreference-in-transformer-outputs-1 |
| Repo | |
| Framework | |
Equivariant Entity-Relationship Networks
| Title | Equivariant Entity-Relationship Networks |
| Authors | Devon Graham, Siamak Ravanbakhsh |
| Abstract | The relational model is a ubiquitous representation of big-data, in part due to its extensive use in databases. However, recent progress in deep learning with relational data has been focused on (knowledge) graphs. In this paper we propose Equivariant Entity-Relationship Networks, a general class of parameter-sharing neural networks derived from the entity-relationship model. We prove that our proposed feed-forward layer is the most expressive linear layer under the given equivariance constraints, and subsumes recently introduced equivariant models for sets, exchangeable tensors, and graphs. The proposed feed-forward layer has linear complexity in the the data and can be used for both inductive and transductive reasoning about relational databases, including database embedding, and the prediction of missing records. This provides a principled theoretical foundation for the application of deep learning to one of the most abundant forms of data. |
| Tasks | Knowledge Graphs |
| Published | 2019-03-21 |
| URL | https://arxiv.org/abs/1903.09033v3 |
| https://arxiv.org/pdf/1903.09033v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-models-for-relational-databases |
| Repo | |
| Framework | |
Classification as Decoder: Trading Flexibility for Control in Medical Dialogue
| Title | Classification as Decoder: Trading Flexibility for Control in Medical Dialogue |
| Authors | Sam Shleifer, Manish Chablani, Anitha Kannan, Namit Katariya, Xavier Amatriain |
| Abstract | Generative seq2seq dialogue systems are trained to predict the next word in dialogues that have already occurred. They can learn from large unlabeled conversation datasets, build a deeper understanding of conversational context, and generate a wide variety of responses. This flexibility comes at the cost of control, a concerning tradeoff in doctor/patient interactions. Inaccuracies, typos, or undesirable content in the training data will be reproduced by the model at inference time. We trade a small amount of labeling effort and some loss of response variety in exchange for quality control. More specifically, a pretrained language model encodes the conversational context, and we finetune a classification head to map an encoded conversational context to a response class, where each class is a noisily labeled group of interchangeable responses. Experts can update these exemplar responses over time as best practices change without retraining the classifier or invalidating old training data. Expert evaluation of 775 unseen doctor/patient conversations shows that only 12% of the discriminative model’s responses are worse than the what the doctor ended up writing, compared to 18% for the generative model. |
| Tasks | Language Modelling |
| Published | 2019-11-16 |
| URL | https://arxiv.org/abs/1911.08554v1 |
| https://arxiv.org/pdf/1911.08554v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-as-decoder-trading-flexibility-1 |
| Repo | |
| Framework | |
Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks
| Title | Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks |
| Authors | Ryan Eloff, André Nortje, Benjamin van Niekerk, Avashna Govender, Leanne Nortje, Arnu Pretorius, Elan van Biljon, Ewald van der Westhuizen, Lisa van Staden, Herman Kamper |
| Abstract | For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis. Unsupervised discrete subword modelling could be useful for studies of phonetic category learning in infants or in low-resource speech technology requiring symbolic input. We use an autoencoder (AE) architecture with intermediate discretisation. We decouple acoustic unit discovery from speaker modelling by conditioning the AE’s decoder on the training speaker identity. At test time, unit discovery is performed on speech from an unseen speaker, followed by unit decoding conditioned on a known target speaker to obtain reconstructed filterbanks. This output is fed to a neural vocoder to synthesise speech in the target speaker’s voice. For discretisation, categorical variational autoencoders (CatVAEs), vector-quantised VAEs (VQ-VAEs) and straight-through estimation are compared at different compression levels on two languages. Our final model uses convolutional encoding, VQ-VAE discretisation, deconvolutional decoding and an FFTNet vocoder. We show that decoupled speaker conditioning intrinsically improves discrete acoustic representations, yielding competitive synthesis quality compared to the challenge baseline. |
| Tasks | Speech Synthesis |
| Published | 2019-04-16 |
| URL | https://arxiv.org/abs/1904.07556v2 |
| https://arxiv.org/pdf/1904.07556v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-acoustic-unit-discovery-for |
| Repo | |
| Framework | |
Matching Entities Across Different Knowledge Graphs with Graph Embeddings
| Title | Matching Entities Across Different Knowledge Graphs with Graph Embeddings |
| Authors | Michael Azmy, Peng Shi, Jimmy Lin, Ihab F. Ilyas |
| Abstract | This paper explores the problem of matching entities across different knowledge graphs. Given a query entity in one knowledge graph, we wish to find the corresponding real-world entity in another knowledge graph. We formalize this problem and present two large-scale datasets for this task based on exiting cross-ontology links between DBpedia and Wikidata, focused on several hundred thousand ambiguous entities. Using a classification-based approach, we find that a simple multi-layered perceptron based on representations derived from RDF2Vec graph embeddings of entities in each knowledge graph is sufficient to achieve high accuracy, with only small amounts of training data. The contributions of our work are datasets for examining this problem and strong baselines on which future work can be based. |
| Tasks | Knowledge Graphs |
| Published | 2019-03-15 |
| URL | http://arxiv.org/abs/1903.06607v1 |
| http://arxiv.org/pdf/1903.06607v1.pdf | |
| PWC | https://paperswithcode.com/paper/matching-entities-across-different-knowledge |
| Repo | |
| Framework | |
U-NetPlus: A Modified Encoder-Decoder U-Net Architecture for Semantic and Instance Segmentation of Surgical Instrument
| Title | U-NetPlus: A Modified Encoder-Decoder U-Net Architecture for Semantic and Instance Segmentation of Surgical Instrument |
| Authors | S. M. Kamrul Hasan, Cristian A. Linte |
| Abstract | Conventional therapy approaches limit surgeons’ dexterity control due to limited field-of-view. With the advent of robot-assisted surgery, there has been a paradigm shift in medical technology for minimally invasive surgery. However, it is very challenging to track the position of the surgical instruments in a surgical scene, and accurate detection & identification of surgical tools is paramount. Deep learning-based semantic segmentation in frames of surgery videos has the potential to facilitate this task. In this work, we modify the U-Net architecture named U-NetPlus, by introducing a pre-trained encoder and re-design the decoder part, by replacing the transposed convolution operation with an upsampling operation based on nearest-neighbor (NN) interpolation. To further improve performance, we also employ a very fast and flexible data augmentation technique. We trained the framework on 8 x 225 frame sequences of robotic surgical videos, available through the MICCAI 2017 EndoVis Challenge dataset and tested it on 8 x 75 frame and 2 x 300 frame videos. Using our U-NetPlus architecture, we report a 90.20% DICE for binary segmentation, 76.26% DICE for instrument part segmentation, and 46.07% for instrument type (i.e., all instruments) segmentation, outperforming the results of previous techniques implemented and tested on these data. |
| Tasks | Data Augmentation, Instance Segmentation, Semantic Segmentation |
| Published | 2019-02-24 |
| URL | http://arxiv.org/abs/1902.08994v1 |
| http://arxiv.org/pdf/1902.08994v1.pdf | |
| PWC | https://paperswithcode.com/paper/u-netplus-a-modified-encoder-decoder-u-net |
| Repo | |
| Framework | |
A high quality and phonetic balanced speech corpus for Vietnamese
| Title | A high quality and phonetic balanced speech corpus for Vietnamese |
| Authors | Pham Ngoc Phuong, Quoc Truong Do, Luong Chi Mai |
| Abstract | This paper presents a high quality Vietnamese speech corpus that can be used for analyzing Vietnamese speech characteristic as well as building speech synthesis models. The corpus consists of 5400 clean-speech utterances spoken by 12 speakers including 6 males and 6 females. The corpus is designed with phonetic balanced in mind so that it can be used for speech synthesis, especially, speech adaptation approaches. Specifically, all speakers utter a common dataset contains 250 phonetic balanced sentences. To increase the variety of speech context, each speaker also utters another 200 non-shared, phonetic-balanced sentences. The speakers are selected to cover a wide range of age and come from different regions of the North of Vietnam. The audios are recorded in a soundproof studio room, they are sampling at 48 kHz, 16 bits PCM, mono channel. |
| Tasks | Speech Synthesis |
| Published | 2019-04-11 |
| URL | http://arxiv.org/abs/1904.05569v1 |
| http://arxiv.org/pdf/1904.05569v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-high-quality-and-phonetic-balanced-speech |
| Repo | |
| Framework | |
