Paper Group ANR 74
Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks (Extended Abstract). Sketch2code: Generating a website from a paper mockup. Learning for Multi-Type Subspace Clustering. Autonomous Management of Energy-Harvesting IoT Nodes Using Deep Reinforcement Learning. The State and Future of Genetic Improvement. Detection of Re …
Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks (Extended Abstract)
| Title | Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks (Extended Abstract) |
| Authors | Stefano V. Albrecht, Subramanian Ramamoorthy |
| Abstract | Dynamic Bayesian networks (DBNs) are a general model for stochastic processes with partially observed states. Belief filtering in DBNs is the task of inferring the belief state (i.e. the probability distribution over process states) based on incomplete and uncertain observations. In this article, we explore the idea of accelerating the filtering task by automatically exploiting causality in the process. We consider a specific type of causal relation, called passivity, which pertains to how state variables cause changes in other variables. We present the Passivity-based Selective Belief Filtering (PSBF) method, which maintains a factored belief representation and exploits passivity to perform selective updates over the belief factors. PSBF is evaluated in both synthetic processes and a simulated multi-robot warehouse, where it outperformed alternative filtering methods by exploiting passivity. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.05850v1 |
| https://arxiv.org/pdf/1907.05850v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-causality-for-selective-belief-1 |
| Repo | |
| Framework | |
Sketch2code: Generating a website from a paper mockup
| Title | Sketch2code: Generating a website from a paper mockup |
| Authors | Alex Robinson |
| Abstract | An early stage of developing user-facing applications is creating a wireframe to layout the interface. Once a wireframe has been created it is given to a developer to implement in code. Developing boiler plate user interface code is time consuming work but still requires an experienced developer. In this dissertation we present two approaches which automates this process, one using classical computer vision techniques, and another using a novel application of deep semantic segmentation networks. We release a dataset of websites which can be used to train and evaluate these approaches. Further, we have designed a novel evaluation framework which allows empirical evaluation by creating synthetic sketches. Our evaluation illustrates that our deep learning approach outperforms our classical computer vision approach and we conclude that deep learning is the most promising direction for future research. |
| Tasks | Code Generation, Semantic Segmentation |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.13750v1 |
| https://arxiv.org/pdf/1905.13750v1.pdf | |
| PWC | https://paperswithcode.com/paper/190513750 |
| Repo | |
| Framework | |
Learning for Multi-Type Subspace Clustering
| Title | Learning for Multi-Type Subspace Clustering |
| Authors | Xun Xu, Loong-Fah Cheong, Zhuwen Li |
| Abstract | Subspace clustering has been extensively studied from the hypothesis-and-test, algebraic, and spectral clustering based perspectives. Most assume that only a single type/class of subspace is present. Generalizations to multiple types are non-trivial, plagued by challenges such as choice of types and numbers of models, sampling imbalance and parameter tuning. In this work, we formulate the multi-type subspace clustering problem as one of learning non-linear subspace filters via deep multi-layer perceptrons (mlps). The response to the learnt subspace filters serve as the feature embedding that is clustering-friendly, i.e., points of the same clusters will be embedded closer together through the network. For inference, we apply K-means to the network output to cluster the data. Experiments are carried out on both synthetic and real world multi-type fitting problems, producing state-of-the-art results. |
| Tasks | |
| Published | 2019-04-03 |
| URL | http://arxiv.org/abs/1904.02075v1 |
| http://arxiv.org/pdf/1904.02075v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-for-multi-type-subspace-clustering |
| Repo | |
| Framework | |
Autonomous Management of Energy-Harvesting IoT Nodes Using Deep Reinforcement Learning
| Title | Autonomous Management of Energy-Harvesting IoT Nodes Using Deep Reinforcement Learning |
| Authors | Abdulmajid Murad, Frank Alexander Kraemer, Kerstin Bach, Gavin Taylor |
| Abstract | Reinforcement learning (RL) is capable of managing wireless, energy-harvesting IoT nodes by solving the problem of autonomous management in non-stationary, resource-constrained settings. We show that the state-of-the-art policy-gradient approaches to RL are appropriate for the IoT domain and that they outperform previous approaches. Due to the ability to model continuous observation and action spaces, as well as improved function approximation capability, the new approaches are able to solve harder problems, permitting reward functions that are better aligned with the actual application goals. We show such a reward function and use policy-gradient approaches to learn capable policies, leading to behavior more appropriate for IoT nodes with less manual design effort, increasing the level of autonomy in IoT. |
| Tasks | |
| Published | 2019-05-10 |
| URL | https://arxiv.org/abs/1905.04181v1 |
| https://arxiv.org/pdf/1905.04181v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-management-of-energy-harvesting |
| Repo | |
| Framework | |
The State and Future of Genetic Improvement
| Title | The State and Future of Genetic Improvement |
| Authors | William B. Langdon, Westley Weimer, Christopher Timperley, Oliver Krauss, Zhen Yu Ding, Yiwei Lyu, Nicolas Chausseau, Eric Schulte, Shin Hwei Tan, Kevin Leach, Yu Huang, Gabin An |
| Abstract | We report the discussion session at the sixth international Genetic Improvement workshop, GI-2019 @ ICSE, which was held as part of the 41st ACM/IEEE International Conference on Software Engineering on Tuesday 28th May 2019. Topics included GI representations, the maintainability of evolved code, automated software testing, future areas of GI research, such as co-evolution, and existing GI tools and benchmarks. |
| Tasks | |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1907.03773v1 |
| https://arxiv.org/pdf/1907.03773v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-state-and-future-of-genetic-improvement |
| Repo | |
| Framework | |
Detection of Real-world Driving-induced Affective State Using Physiological Signals and Multi-view Multi-task Machine Learning
| Title | Detection of Real-world Driving-induced Affective State Using Physiological Signals and Multi-view Multi-task Machine Learning |
| Authors | Daniel Lopez-Martinez, Neska El-Haouij, Rosalind Picard |
| Abstract | Affective states have a critical role in driving performance and safety. They can degrade driver situation awareness and negatively impact cognitive processes, severely diminishing road safety. Therefore, detecting and assessing drivers’ affective states is crucial in order to help improve the driving experience, and increase safety, comfort and well-being. Recent advances in affective computing have enabled the detection of such states. This may lead to empathic automotive user interfaces that account for the driver’s emotional state and influence the driver in order to improve safety. In this work, we propose a multiview multi-task machine learning method for the detection of driver’s affective states using physiological signals. The proposed approach is able to account for inter-drive variability in physiological responses while enabling interpretability of the learned models, a factor that is especially important in systems deployed in the real world. We evaluate the models on three different datasets containing real-world driving experiences. Our results indicate that accounting for drive-specific differences significantly improves model performance. |
| Tasks | |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.09929v1 |
| https://arxiv.org/pdf/1907.09929v1.pdf | |
| PWC | https://paperswithcode.com/paper/detection-of-real-world-driving-induced |
| Repo | |
| Framework | |
C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
| Title | C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation |
| Authors | Qihang Yu, Dong Yang, Holger Roth, Yutong Bai, Yixiao Zhang, Alan L. Yuille, Daguang Xu |
| Abstract | 3D convolution neural networks (CNN) have been proved very successful in parsing organs or tumours in 3D medical images, but it remains sophisticated and time-consuming to choose or design proper 3D networks given different task contexts. Recently, Neural Architecture Search (NAS) is proposed to solve this problem by searching for the best network architecture automatically. However, the inconsistency between search stage and deployment stage often exists in NAS algorithms due to memory constraints and large search space, which could become more serious when applying NAS to some memory and time consuming tasks, such as 3D medical image segmentation. In this paper, we propose coarse-to-fine neural architecture search (C2FNAS) to automatically search a 3D segmentation network from scratch without inconsistency on network size or input size. Specifically, we divide the search procedure into two stages: 1) the coarse stage, where we search the macro-level topology of the network, i.e. how each convolution module is connected to other modules; 2) the fine stage, where we search at micro-level for operations in each cell based on previous searched macro-level topology. The coarse-to-fine manner divides the search procedure into two consecutive stages and meanwhile resolves the inconsistency. We evaluate our method on 10 public datasets from Medical Segmentation Decalthon (MSD) challenge, and achieve state-of-the-art performance with the network searched using one dataset, which demonstrates the effectiveness and generalization of our searched models. |
| Tasks | Medical Image Segmentation, Neural Architecture Search, Semantic Segmentation |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09628v1 |
| https://arxiv.org/pdf/1912.09628v1.pdf | |
| PWC | https://paperswithcode.com/paper/191209628 |
| Repo | |
| Framework | |
Boundary Aware Multi-Focus Image Fusion Using Deep Neural Network
| Title | Boundary Aware Multi-Focus Image Fusion Using Deep Neural Network |
| Authors | Haoyu Ma, Juncheng Zhang, Shaojun Liu, Qingmin Liao |
| Abstract | Since it is usually difficult to capture an all-in-focus image of a 3D scene directly, various multi-focus image fusion methods are employed to generate it from several images focusing at different depths. However, the performance of existing methods is barely satisfactory and often degrades for areas near the focused/defocused boundary (FDB). In this paper, a boundary aware method using deep neural network is proposed to overcome this problem. (1) Aiming to acquire improved fusion images, a 2-channel deep network is proposed to better extract the relative defocus information of the two source images. (2) After analyzing the different situations for patches far away from and near the FDB, we use two networks to handle them respectively. (3) To simulate the reality more precisely, a new approach of dataset generation is designed. Experiments demonstrate that the proposed method outperforms the state-of-the-art methods, both qualitatively and quantitatively. |
| Tasks | |
| Published | 2019-03-30 |
| URL | http://arxiv.org/abs/1904.00198v1 |
| http://arxiv.org/pdf/1904.00198v1.pdf | |
| PWC | https://paperswithcode.com/paper/boundary-aware-multi-focus-image-fusion-using |
| Repo | |
| Framework | |
Decrement Operators in Belief Change
| Title | Decrement Operators in Belief Change |
| Authors | Kai Sauerwald, Christoph Beierle |
| Abstract | While research on iterated revision is predominant in the field of iterated belief change, the class of iterated contraction operators received more attention in recent years. In this article, we examine a non-prioritized generalisation of iterated contraction. In particular, the class of weak decrement operators is introduced, which are operators that by multiple steps achieve the same as a contraction. Inspired by Darwiche and Pearl’s work on iterated revision the subclass of decrement operators is defined. For both, decrement and weak decrement operators, postulates are presented and for each of them a representation theorem in the framework of total preorders is given. Furthermore, we present two sub-types of decrement operators. |
| Tasks | |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08347v2 |
| https://arxiv.org/pdf/1905.08347v2.pdf | |
| PWC | https://paperswithcode.com/paper/decrement-operators-in-belief-change |
| Repo | |
| Framework | |
Aspect and Opinion Terms Extraction Using Double Embeddings and Attention Mechanism for Indonesian Hotel Reviews
| Title | Aspect and Opinion Terms Extraction Using Double Embeddings and Attention Mechanism for Indonesian Hotel Reviews |
| Authors | Jordhy Fernando, Masayu Leylia Khodra, Ali Akbar Septiandri |
| Abstract | Aspect and opinion terms extraction from review texts is one of the key tasks in aspect-based sentiment analysis. In order to extract aspect and opinion terms for Indonesian hotel reviews, we adapt double embeddings feature and attention mechanism that outperform the best system at SemEval 2015 and 2016. We conduct experiments using 4000 reviews to find the best configuration and show the influences of double embeddings and attention mechanism toward model performance. Using 1000 reviews for evaluation, we achieved F1-measure of 0.914 and 0.90 for aspect and opinion terms extraction in token and entity (term) level respectively. |
| Tasks | Aspect-Based Sentiment Analysis, Extract Aspect, Sentiment Analysis |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.04899v2 |
| https://arxiv.org/pdf/1908.04899v2.pdf | |
| PWC | https://paperswithcode.com/paper/aspect-and-opinion-terms-extraction-using |
| Repo | |
| Framework | |
Sentiment Analysis of Czech Texts: An Algorithmic Survey
| Title | Sentiment Analysis of Czech Texts: An Algorithmic Survey |
| Authors | Erion Çano, Ondřej Bojar |
| Abstract | In the area of online communication, commerce and transactions, analyzing sentiment polarity of texts written in various natural languages has become crucial. While there have been a lot of contributions in resources and studies for the English language, “smaller” languages like Czech have not received much attention. In this survey, we explore the effectiveness of many existing machine learning algorithms for sentiment analysis of Czech Facebook posts and product reviews. We report the sets of optimal parameter values for each algorithm and the scores in both datasets. We finally observe that support vector machines are the best classifier and efforts to increase performance even more with bagging, boosting or voting ensemble schemes fail to do so. |
| Tasks | Sentiment Analysis |
| Published | 2019-01-09 |
| URL | http://arxiv.org/abs/1901.02780v2 |
| http://arxiv.org/pdf/1901.02780v2.pdf | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-of-czech-texts-an |
| Repo | |
| Framework | |
Let’s agree to disagree: learning highly debatable multirater labelling
| Title | Let’s agree to disagree: learning highly debatable multirater labelling |
| Authors | Carole H. Sudre, Beatriz Gomez Anson, Silvia Ingala, Chris D. Lane, Daniel Jimenez, Lukas Haider, Thomas Varsavsky, Ryutaro Tanno, Lorna Smith, Sébastien Ourselin, Rolf H. Jäger, M. Jorge Cardoso |
| Abstract | Classification and differentiation of small pathological objects may greatly vary among human raters due to differences in training, expertise and their consistency over time. In a radiological setting, objects commonly have high within-class appearance variability whilst sharing certain characteristics across different classes, making their distinction even more difficult. As an example, markers of cerebral small vessel disease, such as enlarged perivascular spaces (EPVS) and lacunes, can be very varied in their appearance while exhibiting high inter-class similarity, making this task highly challenging for human raters. In this work, we investigate joint models of individual rater behaviour and multirater consensus in a deep learning setting, and apply it to a brain lesion object-detection task. Results show that jointly modelling both individual and consensus estimates leads to significant improvements in performance when compared to directly predicting consensus labels, while also allowing the characterization of human-rater consistency. |
| Tasks | Object Detection |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01891v1 |
| https://arxiv.org/pdf/1909.01891v1.pdf | |
| PWC | https://paperswithcode.com/paper/lets-agree-to-disagree-learning-highly |
| Repo | |
| Framework | |
Wykorzystanie sztucznej inteligencji do generowania treści muzycznych
| Title | Wykorzystanie sztucznej inteligencji do generowania treści muzycznych |
| Authors | Mateusz Dorobek |
| Abstract | This thesis is presenting a method for generating short musical phrases using a deep convolutional generative adversarial network (DCGAN). To train neural network were used datasets of classical and jazz music MIDI recordings. Our approach introduces translating the MIDI data into graphical images in a piano roll format suitable for the network input size, using the RGB channels as additional information carriers for improved performance. The network has learned to generate images that are indistinguishable from the input data and, when translated back to MIDI and played back, include several musically interesting rhythmic and harmonic structures. The results of the conducted experiments are described and discussed, with conclusions for further work and a short comparison with selected existing solutions. |
| Tasks | |
| Published | 2019-12-15 |
| URL | https://arxiv.org/abs/1912.10815v1 |
| https://arxiv.org/pdf/1912.10815v1.pdf | |
| PWC | https://paperswithcode.com/paper/wykorzystanie-sztucznej-inteligencji-do |
| Repo | |
| Framework | |
Cross-Lingual Vision-Language Navigation
| Title | Cross-Lingual Vision-Language Navigation |
| Authors | An Yan, Xin Wang, Jiangtao Feng, Lei Li, William Yang Wang |
| Abstract | Vision-Language Navigation (VLN) is the task where an agent is commanded to navigate in photo-realistic environments with natural language instructions. Previous research on VLN is primarily conducted on the Room-to-Room (R2R) dataset with only English instructions. The ultimate goal of VLN, however, is to serve people speaking arbitrary languages. To do this, we collect a cross-lingual R2R dataset, extending the original benchmark with corresponding Chinese instructions. But it is impractical to collect human-annotated instructions for every existing language. Based on the newly introduced dataset, we propose a general cross-lingual VLN framework to enable instruction-following navigation for different languages. We first explore the possibility of building a cross-lingual agent when no training data of the target language is available. The cross-lingual agent is equipped with a meta-learner to aggregate cross-lingual representations and with a visually grounded cross-lingual alignment module to align textual representations of different languages. Under the zero-shot learning scenario, our model shows competitive results even compared to a model trained with all target language instructions. Besides, we introduce an adversarial domain adaption loss to improve the transferring ability of our model when given a certain amount of target language data. Our dataset and methods demonstrate potentials of building scalable cross-lingual agents to serve speakers with different languages. |
| Tasks | Domain Adaptation, Vision-Language Navigation, Zero-Shot Learning |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11301v1 |
| https://arxiv.org/pdf/1910.11301v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-lingual-vision-language-navigation-1 |
| Repo | |
| Framework | |
On the Bounds of Function Approximations
| Title | On the Bounds of Function Approximations |
| Authors | Adrian de Wynter |
| Abstract | Within machine learning, the subfield of Neural Architecture Search (NAS) has recently garnered research attention due to its ability to improve upon human-designed models. However, the computational requirements for finding an exact solution to this problem are often intractable, and the design of the search space still requires manual intervention. In this paper we attempt to establish a formalized framework from which we can better understand the computational bounds of NAS in relation to its search space. For this, we first reformulate the function approximation problem in terms of sequences of functions, and we call it the Function Approximation (FA) problem; then we show that it is computationally infeasible to devise a procedure that solves FA for all functions to zero error, regardless of the search space. We show also that such error will be minimal if a specific class of functions is present in the search space. Subsequently, we show that machine learning as a mathematical problem is a solution strategy for FA, albeit not an effective one, and further describe a stronger version of this approach: the Approximate Architectural Search Problem (a-ASP), which is the mathematical equivalent of NAS. We leverage the framework from this paper and results from the literature to describe the conditions under which a-ASP can potentially solve FA as well as an exhaustive search, but in polynomial time. |
| Tasks | Neural Architecture Search |
| Published | 2019-08-26 |
| URL | https://arxiv.org/abs/1908.09942v1 |
| https://arxiv.org/pdf/1908.09942v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-bounds-of-function-approximations |
| Repo | |
| Framework | |
