Paper Group ANR 1465
OASIS: One-pass aligned Atlas Set for Image Segmentation. Scene recognition based on DNN and game theory with its applications in human-robot interaction. Comparing Greedy Constructive Heuristic Subtour Elimination Methods for the Traveling Salesman Problem. Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasound. A Comparat …
OASIS: One-pass aligned Atlas Set for Image Segmentation
| Title | OASIS: One-pass aligned Atlas Set for Image Segmentation |
| Authors | Qikui Zhu, Bo Du, Pingkun Yan |
| Abstract | Medical image segmentation is a fundamental task in medical image analysis. Despite that deep convolutional neural networks have gained stellar performance in this challenging task, they typically rely on large labeled datasets, which have limited their extension to customized applications. By revisiting the superiority of atlas based segmentation methods, we present a new framework of One-pass aligned Atlas Set for Images Segmentation (OASIS). To address the problem of time-consuming iterative image registration used for atlas warping, the proposed method takes advantage of the power of deep learning to achieve one-pass image registration. In addition, by applying label constraint, OASIS also makes the registration process to be focused on the regions to be segmented for improving the performance of segmentation. Furthermore, instead of using image based similarity for label fusion, which can be distracted by the large background areas, we propose a novel strategy to compute the label similarity based weights for label fusion. Our experimental results on the challenging task of prostate MR image segmentation demonstrate that OASIS is able to significantly increase the segmentation performance compared to other state-of-the-art methods. |
| Tasks | Image Registration, Medical Image Segmentation, Semantic Segmentation |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02417v1 |
| https://arxiv.org/pdf/1912.02417v1.pdf | |
| PWC | https://paperswithcode.com/paper/oasis-one-pass-aligned-atlas-set-for-image |
| Repo | |
| Framework | |
Scene recognition based on DNN and game theory with its applications in human-robot interaction
| Title | Scene recognition based on DNN and game theory with its applications in human-robot interaction |
| Authors | R. Q. Wang, W. Z. Wang, D. Z. Zhao, G. H. Chen, D. S. Luo |
| Abstract | Scene recognition model based on the DNN and game theory with its applications in human-robot interaction is proposed in this paper. The use of deep learning methods in the field of scene recognition is still in its infancy, but has become an important trend in the future. As the innovative idea of the paper, we propose the following novelties. (1) In this paper, the image registration problem is transformed into a problem of minimum energy in Markov Random Field to finalize the image pre-processing task. Game theory is used to find the optimal. (2) We select neighboring homogeneous sample features and the neighboring heterogeneous sample features for the extracted sample features to build a triple and modify the traditional neural network to propose the novel DNN for scene understanding. (3) The robot control is well combined to guide the robot vision for multiple tasks. The experiment is then conducted to validate the overall performance. |
| Tasks | Image Registration, Scene Recognition, Scene Understanding |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01293v4 |
| https://arxiv.org/pdf/1912.01293v4.pdf | |
| PWC | https://paperswithcode.com/paper/scene-recognition-based-on-dnn-and-game |
| Repo | |
| Framework | |
Comparing Greedy Constructive Heuristic Subtour Elimination Methods for the Traveling Salesman Problem
| Title | Comparing Greedy Constructive Heuristic Subtour Elimination Methods for the Traveling Salesman Problem |
| Authors | Petar D. Jackovich, Bruce A. Cox, Raymond R. Hill |
| Abstract | This paper further defines the class of fragment constructive heuristics used to compute feasible solutions for the Traveling Salesman Problem into arc-greedy and node-greedy subclasses. Since these subclasses of heuristics can create subtours, two known methodologies for subtour elimination on symmetric instances are reviewed and are expanded to cover asymmetric problem instances. This paper introduces a third novel methodology, the Greedy Tracker, and compares it to both known methodologies. Computational results are generated across multiple symmetric and asymmetric instances. The results demonstrate the Greedy Tracker is the fastest method for preventing subtours for instances below 400 nodes. A distinction between fragment constructive heuristics and the subtour elimination methodology used to ensure the feasibility of resulting solutions enables the introduction of a new node-greedy fragment heuristic called Ordered Greedy. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.08625v1 |
| https://arxiv.org/pdf/1910.08625v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-greedy-constructive-heuristic |
| Repo | |
| Framework | |
Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasound
| Title | Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasound |
| Authors | Shujaat Khan, Jaeyoung Huh, Jong Chul Ye |
| Abstract | In ultrasound (US) imaging, various types of adaptive beamforming techniques have been investigated to improve the resolution and contrast-to-noise ratio of the delay and sum (DAS) beamformers. Unfortunately, the performance of these adaptive beamforming approaches degrade when the underlying model is not sufficiently accurate and the number of channels decreases. To address this problem, here we propose a deep learning-based beamformer to generate significantly improved images over widely varying measurement conditions and channel subsampling patterns. In particular, our deep neural network is designed to directly process full or sub-sampled radio-frequency (RF) data acquired at various subsampling rates and detector configurations so that it can generate high quality ultrasound images using a single beamformer. The origin of such input-dependent adaptivity is also theoretically analyzed. Experimental results using B-mode focused ultrasound confirm the efficacy of the proposed methods. |
| Tasks | |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10257v3 |
| https://arxiv.org/pdf/1907.10257v3.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-and-compressive-beamforming-using |
| Repo | |
| Framework | |
A Comparative Study of Some Central Notions of ASPIC+ and DeLP
| Title | A Comparative Study of Some Central Notions of ASPIC+ and DeLP |
| Authors | Alejandro J. Garcia, Henry Prakken, Guillermo R. Simari |
| Abstract | This paper formally compares some central notions from two well-known formalisms for rule-based argumentation, DeLP and ASPIC+. The comparisons especially focus on intuitive adequacy and inter-translatability, consistency, and closure properties. As for differences in the definitions of arguments and attack, it turns out that DeLP’s definitions are intuitively appealing but that they may not fully comply with Caminada and Amgoud’s rationality postulates of strict closure and indirect consistency. For some special cases, the DeLP definitions are shown to fare better than ASPIC+. Next, it is argued that there are reasons to consider a variant of DeLP with grounded semantics, since in some examples its current notion of warrant arguably has counterintuitive consequences and may lead to sets of warranted arguments that are not admissible. Finally, under some minimality and consistency assumptions on ASPIC+ arguments, a one-to-many correspondence between ASPIC+ arguments and DeLP arguments is identified in such a way that if the DeLP warranting procedure is changed to grounded semantics, then DeLP notion of warrant and ASPIC+'s notion of justification are equivalent. This result is proven for three alternative definitions of attack. |
| Tasks | |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.02810v2 |
| https://arxiv.org/pdf/1909.02810v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparative-study-of-some-central-notions |
| Repo | |
| Framework | |
Can Graph Neural Networks Go “Online”? An Analysis of Pretraining and Inference
| Title | Can Graph Neural Networks Go “Online”? An Analysis of Pretraining and Inference |
| Authors | Lukas Galke, Iacopo Vagliano, Ansgar Scherp |
| Abstract | Large-scale graph data in real-world applications is often not static but dynamic, i. e., new nodes and edges appear over time. Current graph convolution approaches are promising, especially, when all the graph’s nodes and edges are available during training. When unseen nodes and edges are inserted after training, it is not yet evaluated whether up-training or re-training from scratch is preferable. We construct an experimental setup, in which we insert previously unseen nodes and edges after training and conduct a limited amount of inference epochs. In this setup, we compare adapting pretrained graph neural networks against retraining from scratch. Our results show that pretrained models yield high accuracy scores on the unseen nodes and that pretraining is preferable over retraining from scratch. Our experiments represent a first step to evaluate and develop truly online variants of graph neural networks. |
| Tasks | |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06018v1 |
| https://arxiv.org/pdf/1905.06018v1.pdf | |
| PWC | https://paperswithcode.com/paper/can-graph-neural-networks-go-online-an |
| Repo | |
| Framework | |
Bayesian Optimization Allowing for Common Random Numbers
| Title | Bayesian Optimization Allowing for Common Random Numbers |
| Authors | Michael Pearce, Matthias Poloczek, Juergen Branke |
| Abstract | Bayesian optimization is a powerful tool for expensive stochastic black-box optimization problems such as simulation-based optimization or machine learning hyperparameter tuning. Many stochastic objective functions implicitly require a random number seed as input. By explicitly reusing a seed a user can exploit common random numbers, comparing two or more inputs under the same randomly generated scenario, such as a common customer stream in a job shop problem, or the same random partition of training data into training and validation set for a machine learning algorithm. With the aim of finding an input with the best average performance over infinitely many seeds, we propose a novel Gaussian process model that jointly models both the output for each seed and the average. We then introduce the Knowledge gradient for Common Random Numbers that iteratively determines a combination of input and random seed to evaluate the objective and automatically trades off reusing old seeds and querying new seeds, thus overcoming the need to evaluate inputs in batches or measuring differences of pairs as suggested in previous methods. We investigate the Knowledge Gradient for Common Random Numbers both theoretically and empirically, finding it achieves significant performance improvements with only moderate added computational cost. |
| Tasks | |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09259v1 |
| https://arxiv.org/pdf/1910.09259v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-optimization-allowing-for-common |
| Repo | |
| Framework | |
Optimization for deep learning: theory and algorithms
| Title | Optimization for deep learning: theory and algorithms |
| Authors | Ruoyu Sun |
| Abstract | When and why can a neural network be successfully trained? This article provides an overview of optimization algorithms and theory for training neural networks. First, we discuss the issue of gradient explosion/vanishing and the more general issue of undesirable spectrum, and then discuss practical solutions including careful initialization and normalization methods. Second, we review generic optimization methods used in training neural networks, such as SGD, adaptive gradient methods and distributed methods, and theoretical results for these algorithms. Third, we review existing research on the global issues of neural network training, including results on bad local minima, mode connectivity, lottery ticket hypothesis and infinite-width analysis. |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.08957v1 |
| https://arxiv.org/pdf/1912.08957v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimization-for-deep-learning-theory-and |
| Repo | |
| Framework | |
Comparison of Quality Indicators in User-generated Content Using Social Media and Scholarly Text
| Title | Comparison of Quality Indicators in User-generated Content Using Social Media and Scholarly Text |
| Authors | Manirupa Das, Renhao Cui |
| Abstract | Predicting the quality of a text document is a critical task when presented with the problem of measuring the performance of a document before its release. In this work, we evaluate various features including those extracted from the text content (textual) and those describing higher-level characteristics of the text (meta) features that are not directly available from the text, and show how these features inform prediction of document quality in different ways. Moreover, we also compare our methods on both social user-generated data such as tweets, and scholarly user-generated data such as academic articles, showing how the same features differently influence prediction of quality across these disparate domains. |
| Tasks | |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11399v1 |
| https://arxiv.org/pdf/1910.11399v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-quality-indicators-in-user |
| Repo | |
| Framework | |
Timeline-based planning: Expressiveness and Complexity
| Title | Timeline-based planning: Expressiveness and Complexity |
| Authors | Nicola Gigante |
| Abstract | Timeline-based planning is an approach originally developed in the context of space mission planning and scheduling, where problem domains are modelled as systems made of a number of independent but interacting components, whose behaviour over time, the timelines, is governed by a set of temporal constraints. This approach is different from the action-based perspective of common PDDL-like planning languages. Timeline-based systems have been successfully deployed in a number of space missions and other domains. However, despite this practical success, a thorough theoretical understanding of the paradigm was missing. This thesis fills this gap, providing the first detailed account of formal and computational properties of the timeline-based approach to planning. In particular, we show that a particularly restricted variant of the formalism is already expressive enough to compactly capture action-based temporal planning problems. Then, finding a solution plan for a timeline-based planning problem is proved to be EXPSPACE-complete. Then, we study the problem of timeline-based planning with uncertainty, that include external components whose behaviour is not under the control of the planned system. We identify a few issues in the state-of-the-art approach based on flexible plans, proposing timeline-based games, a more general game-theoretic formulation of the problem, that addresses those issues. We show that winning strategies for such games can be found in doubly-exponential time. Then, we study the expressiveness of the formalism from a logic point of view, showing that (most of) timeline-based planning problems can be captured by Bounded TPTL with Past, a fragment of TPTL+P that, unlike the latter, keeps an EXPSPACE satisfiability problem. The logic is introduced and its satisfiabilty problem is solved by extending a recent one-pass tree-shaped tableau method for LTL. |
| Tasks | |
| Published | 2019-02-16 |
| URL | http://arxiv.org/abs/1902.06123v1 |
| http://arxiv.org/pdf/1902.06123v1.pdf | |
| PWC | https://paperswithcode.com/paper/timeline-based-planning-expressiveness-and |
| Repo | |
| Framework | |
A Grounded Interaction Protocol for Explainable Artificial Intelligence
| Title | A Grounded Interaction Protocol for Explainable Artificial Intelligence |
| Authors | Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere |
| Abstract | Explainable Artificial Intelligence (XAI) systems need to include an explanation model to communicate the internal decisions, behaviours and actions to the interacting humans. Successful explanation involves both cognitive and social processes. In this paper we focus on the challenge of meaningful interaction between an explainer and an explainee and investigate the structural aspects of an interactive explanation to propose an interaction protocol. We follow a bottom-up approach to derive the model by analysing transcripts of different explanation dialogue types with 398 explanation dialogues. We use grounded theory to code and identify key components of an explanation dialogue. We formalize the model using the agent dialogue framework (ADF) as a new dialogue type and then evaluate it in a human-agent interaction study with 101 dialogues from 14 participants. Our results show that the proposed model can closely follow the explanation dialogues of human-agent conversations. |
| Tasks | |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.02409v1 |
| http://arxiv.org/pdf/1903.02409v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-grounded-interaction-protocol-for |
| Repo | |
| Framework | |
The Game of Tetris in Machine Learning
| Title | The Game of Tetris in Machine Learning |
| Authors | Simón Algorta, Özgür Şimşek |
| Abstract | The game of Tetris is an important benchmark for research in artificial intelligence and machine learning. This paper provides a historical account of the algorithmic developments in Tetris and discusses open challenges. Handcrafted controllers, genetic algorithms, and reinforcement learning have all contributed to good solutions. However, existing solutions fall far short of what can be achieved by expert players playing without time pressure. Further study of the game has the potential to contribute to important areas of research, including feature discovery, autonomous learning of action hierarchies, and sample-efficient reinforcement learning. |
| Tasks | |
| Published | 2019-05-05 |
| URL | https://arxiv.org/abs/1905.01652v2 |
| https://arxiv.org/pdf/1905.01652v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-game-of-tetris-in-machine-learning |
| Repo | |
| Framework | |
Self-Attentional Credit Assignment for Transfer in Reinforcement Learning
| Title | Self-Attentional Credit Assignment for Transfer in Reinforcement Learning |
| Authors | Johan Ferret, Raphaël Marinier, Matthieu Geist, Olivier Pietquin |
| Abstract | The ability to transfer knowledge to novel environments and tasks is a sensible desiderata for general learning agents. Despite the apparent promises, transfer in RL is still an open and little exploited research area. In this paper, we take a brand-new perspective about transfer: we suggest that the ability to assign credit unveils structural invariants in the tasks that can be transferred to make RL more sample-efficient. Our main contribution is SECRET, a novel approach to transfer learning for RL that uses a backward-view credit assignment mechanism based on a self-attentive architecture. Two aspects are key to its generality: it learns to assign credit as a separate offline supervised process and exclusively modifies the reward function. Consequently, it can be supplemented by transfer methods that do not modify the reward function and it can be plugged on top of any RL algorithm. |
| Tasks | Transfer Learning |
| Published | 2019-07-18 |
| URL | https://arxiv.org/abs/1907.08027v2 |
| https://arxiv.org/pdf/1907.08027v2.pdf | |
| PWC | https://paperswithcode.com/paper/credit-assignment-as-a-proxy-for-transfer-in |
| Repo | |
| Framework | |
Adversarial Cross-Modal Retrieval via Learning and Transferring Single-Modal Similarities
| Title | Adversarial Cross-Modal Retrieval via Learning and Transferring Single-Modal Similarities |
| Authors | Xin Wen, Zhizhong Han, Xinyu Yin, Yu-Shen Liu |
| Abstract | Cross-modal retrieval aims to retrieve relevant data across different modalities (e.g., texts vs. images). The common strategy is to apply element-wise constraints between manually labeled pair-wise items to guide the generators to learn the semantic relationships between the modalities, so that the similar items can be projected close to each other in the common representation subspace. However, such constraints often fail to preserve the semantic structure between unpaired but semantically similar items (e.g. the unpaired items with the same class label are more similar than items with different labels). To address the above problem, we propose a novel cross-modal similarity transferring (CMST) method to learn and preserve the semantic relationships between unpaired items in an unsupervised way. The key idea is to learn the quantitative similarities in single-modal representation subspace, and then transfer them to the common representation subspace to establish the semantic relationships between unpaired items across modalities. Experiments show that our method outperforms the state-of-the-art approaches both in the class-based and pair-based retrieval tasks. |
| Tasks | Cross-Modal Retrieval |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08042v1 |
| http://arxiv.org/pdf/1904.08042v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-cross-modal-retrieval-via |
| Repo | |
| Framework | |
A Multi-task Learning Approach for Named Entity Recognition using Local Detection
| Title | A Multi-task Learning Approach for Named Entity Recognition using Local Detection |
| Authors | Nargiza Nosirova, Mingbin Xu, Hui Jiang |
| Abstract | Named entity recognition (NER) systems that perform well require task-related and manually annotated datasets. However, they are expensive to develop, and are thus limited in size. As there already exists a large number of NER datasets that share a certain degree of relationship but differ in content, it is important to explore the question of whether such datasets can be combined as a simple method for improving NER performance. To investigate this, we developed a novel locally detecting multitask model using FFNNs. The model relies on encoding variable-length sequences of words into theoretically lossless and unique fixed-size representations. We applied this method to several well-known NER tasks and compared the results of our model to baseline models as well as other published results. As a result, we observed competitive performance in nearly all of the tasks. |
| Tasks | Multi-Task Learning, Named Entity Recognition |
| Published | 2019-04-05 |
| URL | http://arxiv.org/abs/1904.03300v2 |
| http://arxiv.org/pdf/1904.03300v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-task-learning-approach-for-named |
| Repo | |
| Framework | |
