Paper Group ANR 1571
mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesis. Learning Nonlinear Mixtures: Identifiability and Algorithm. A Hybrid Evolutionary System for Automated Artificial Neural Networks Generation and Simplification in Biomedical Applications. Real-time 3-D Mapping with Estimating Acoustic Materials. 2L-3W: 2-Level 3-Way Hardw …
mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesis
| Title | mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesis |
| Authors | Mahmut Yurt, Salman Ul Hassan Dar, Aykut Erdem, Erkut Erdem, Tolga Çukur |
| Abstract | Multi-contrast MRI protocols increase the level of morphological information available for diagnosis. Yet, the number and quality of contrasts is limited in practice by various factors including scan time and patient motion. Synthesis of missing or corrupted contrasts can alleviate this limitation to improve clinical utility. Common approaches for multi-contrast MRI involve either one-to-one and many-to-one synthesis methods. One-to-one methods take as input a single source contrast, and they learn a latent representation sensitive to unique features of the source. Meanwhile, many-to-one methods receive multiple distinct sources, and they learn a shared latent representation more sensitive to common features across sources. For enhanced image synthesis, here we propose a multi-stream approach that aggregates information across multiple source images via a mixture of multiple one-to-one streams and a joint many-to-one stream. The shared feature maps generated in the many-to-one stream and the complementary feature maps generated in the one-to-one streams are combined with a fusion block. The location of the fusion block is adaptively modified to maximize task-specific performance. Qualitative and quantitative assessments on T1-, T2-, PD-weighted and FLAIR images clearly demonstrate the superior performance of the proposed method compared to previous state-of-the-art one-to-one and many-to-one methods. |
| Tasks | Image Generation |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11504v1 |
| https://arxiv.org/pdf/1909.11504v1.pdf | |
| PWC | https://paperswithcode.com/paper/mustgan-multi-stream-generative-adversarial |
| Repo | |
| Framework | |
Learning Nonlinear Mixtures: Identifiability and Algorithm
| Title | Learning Nonlinear Mixtures: Identifiability and Algorithm |
| Authors | Bo Yang, Xiao Fu, Nicholas D. Sidiropoulos, Kejun Huang |
| Abstract | Linear mixture models have proven very useful in a plethora of applications, e.g., topic modeling, clustering, and source separation. As a critical aspect of the linear mixture models, identifiability of the model parameters is well-studied, under frameworks such as independent component analysis and constrained matrix factorization. Nevertheless, when the linear mixtures are distorted by an unknown nonlinear functions – which is well-motivated and more realistic in many cases – the identifiability issues are much less studied. This work proposes an identification criterion for a nonlinear mixture model that is well grounded in many real-world applications, and offers identifiability guarantees. A practical implementation based on a judiciously designed neural network is proposed to realize the criterion, and an effective learning algorithm is proposed. Numerical results on synthetic and real-data corroborate effectiveness of the proposed method. |
| Tasks | |
| Published | 2019-01-06 |
| URL | http://arxiv.org/abs/1901.01568v1 |
| http://arxiv.org/pdf/1901.01568v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-nonlinear-mixtures-identifiability |
| Repo | |
| Framework | |
A Hybrid Evolutionary System for Automated Artificial Neural Networks Generation and Simplification in Biomedical Applications
| Title | A Hybrid Evolutionary System for Automated Artificial Neural Networks Generation and Simplification in Biomedical Applications |
| Authors | Enrique Fernandez-Blanco, Daniel Rivero, Marcos Gestal, Carlos Fernandez-Lozano, Norberto Ezquerra, Cristian R. Munteanu, Julian Dorado |
| Abstract | Data mining and data classification over biomedical data are two of the most important research fields in computer science. Among the great diversity of techniques that can be used for this purpose, Artifical Neural Networks (ANNs) is one of the most suited. One of the main problems in the development of this technique is the slow performance of the full process. Traditionally, in this development process, human experts are needed to experiment with different architectural procedures until they find the one that presents the correct results for solving a specific problem. However, many studies have emerged in which different ANN developmental techniques, more or less automated, are described. In this paper, the authors have focused on developing a new technique to perform this process over biomedical data. The new technique is described in which two Evolutionary Computation (EC) techniques are mixed to automatically develop ANNs. These techniques are Genetic Algorithms and Genetic Programming. The work goes further, and the system described here allows to obtain simplified networks with a low number of neurons to resolve the problems. The system is compared with the already existent system which also uses EC over a set of well-known problems. The conclusions reached from these comparisons indicate that this new system produces very good results, which in the worst case are at least comparable to existing techniques and in many cases are substantially better. |
| Tasks | |
| Published | 2019-04-09 |
| URL | http://arxiv.org/abs/1904.04754v1 |
| http://arxiv.org/pdf/1904.04754v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hybrid-evolutionary-system-for-automated |
| Repo | |
| Framework | |
Real-time 3-D Mapping with Estimating Acoustic Materials
| Title | Real-time 3-D Mapping with Estimating Acoustic Materials |
| Authors | Taeyoung Kim, Youngsun Kwon, Sung-eui Yoon |
| Abstract | This paper proposes a real-time system integrating an acoustic material estimation from visual appearance and an on-the-fly mapping in the 3-dimension. The proposed method estimates the acoustic materials of surroundings in indoor scenes and incorporates them to a 3-D occupancy map, as a robot moves around the environment. To estimate the acoustic material from the visual cue, we apply the state-of-the-art semantic segmentation CNN network based on the assumption that the visual appearance and the acoustic materials have a strong association. Furthermore, we introduce an update policy to handle the material estimations during the online mapping process. As a result, our environment map with acoustic material can be used for sound-related robotics applications, such as sound source localization taking into account various acoustic propagation (e.g., reflection). |
| Tasks | Semantic Segmentation |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.06998v1 |
| https://arxiv.org/pdf/1909.06998v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-3-d-mapping-with-estimating |
| Repo | |
| Framework | |
2L-3W: 2-Level 3-Way Hardware-Software Co-Verification for the Mapping of Deep Learning Architecture (DLA) onto FPGA Boards
| Title | 2L-3W: 2-Level 3-Way Hardware-Software Co-Verification for the Mapping of Deep Learning Architecture (DLA) onto FPGA Boards |
| Authors | Tolulope A. Odetola, Katie M. Groves, Syed Rafay Hasan |
| Abstract | FPGAs have become a popular choice for deploying deep learning architectures (DLA). There are many researchers that have explored the deployment and mapping of DLA on FPGA. However, there has been a growing need to do design-time hardware-software co-verification of these deployments. To the best of our knowledge this is the first work that proposes a 2-Level 3-Way (2L-3W) hardware-software co-verification methodology and provides a step-by-step guide for the successful mapping, deployment and verification of DLA on FPGA boards. The 2-Level verification is to make sure the implementation in each stage (software and hardware) are following the desired behavior. The 3-Way co-verification provides a cross-paradigm (software, design and hardware) layer-by-layer parameter check to assure the correct implementation and mapping of the DLA onto FPGA boards. The proposed 2L-3W co-verification methodology has been evaluated over several test cases. In each case, the prediction and layer-by-layer output of the DLA deployed on PYNQ FPGA board (hardware) alongside with the intermediate design results of the layer-by-layer output of the DLA implemented on Vivado HLS and the prediction and layer-by-layer output of the software level (Caffe deep learning framework) are compared to obtain a layer-by-layer similarity score. The comparison is achieved using a completely automated Python script. The comparison provides a layer-by-layer similarity score that informs us the degree of success of the DLA mapping to the FPGA or help identify in design time the layer to be debugged in the case of unsuccessful mapping. We demonstrated our technique on LeNet DLA and Caffe inspired Cifar-10 DLA and the co-verification results yielded layer-by-layer similarity scores of 99% accuracy. |
| Tasks | |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.05944v1 |
| https://arxiv.org/pdf/1911.05944v1.pdf | |
| PWC | https://paperswithcode.com/paper/2l-3w-2-level-3-way-hardware-software-co |
| Repo | |
| Framework | |
Learning to smell for wellness
| Title | Learning to smell for wellness |
| Authors | Kehinde Owoeye |
| Abstract | Learning to automatically perceive smell is becoming increasingly important with applications in monitoring the quality of food and drinks for healthy living. In todays age of proliferation of internet of things devices, the deployment of electronic nose otherwise known as smell sensors is on the increase for a variety of olfaction applications with the aid of machine learning models. These models are trained to classify food and drink quality into several categories depending on the granularity of interest. However, models trained to smell in one domain rarely perform adequately when used in another domain. In this work, we consider a problem where only few samples are available in the target domain and we are faced with the task of leveraging knowledge from another domain with relatively abundant data to make reliable inference in the target domain. We propose a weakly supervised domain adaptation framework where we demonstrate that by building multiple models in a mixture of supervised and unsupervised framework, we can generalise effectively from one domain to another. We evaluate our approach on several datasets of beef cuts and quality collected across different conditions and environments. We empirically show via several experiments that our approach perform competitively compared to a variety of baselines. |
| Tasks | Domain Adaptation |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00895v1 |
| https://arxiv.org/pdf/1912.00895v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-smell-for-wellness |
| Repo | |
| Framework | |
Lift Up and Act! Classifier Performance in Resource-Constrained Applications
| Title | Lift Up and Act! Classifier Performance in Resource-Constrained Applications |
| Authors | Galit Shmueli |
| Abstract | Classification tasks are common across many fields and applications where the decision maker’s action is limited by resource constraints. In direct marketing only a subset of customers is contacted; scarce human resources limit the number of interviews to the most promising job candidates; limited donated organs are prioritized to those with best fit. In such scenarios, performance measures such as the classification matrix, ROC analysis, and even ranking metrics such as AUC measures outcomes different from the action of interest. At the same time, gains and lift that do measure the relevant outcome are rarely used by machine learners. In this paper we define resource-constrained classifier performance as a task distinguished from classification and ranking. We explain how gains and lift can lead to different algorithm choices and discuss the effect of class distribution. |
| Tasks | |
| Published | 2019-06-08 |
| URL | https://arxiv.org/abs/1906.03374v2 |
| https://arxiv.org/pdf/1906.03374v2.pdf | |
| PWC | https://paperswithcode.com/paper/lift-up-and-act-classifier-performance-in |
| Repo | |
| Framework | |
Generated Loss and Augmented Training of MNIST VAE
| Title | Generated Loss and Augmented Training of MNIST VAE |
| Authors | Jason Chou |
| Abstract | The variational autoencoder (VAE) framework is a popular option for training unsupervised generative models, featuring ease of training and latent representation of data. The objective function of VAE does not guarantee to achieve the latter, however, and failure to do so leads to a frequent failure mode called posterior collapse. Even in successful cases, VAEs often result in low-precision reconstructions and generated samples. The introduction of the KL-divergence weight $\beta$ can help steer the model clear of posterior collapse, but its tuning is often a trial-and-error process with no guiding metrics. Here we test the idea of using the total VAE loss of generated samples (generated loss) as the proxy metric for generation quality, the related hypothesis that VAE reconstruction from the mean latent vector tends to be a more typical example of its class than the original, and the idea of exploiting this property by augmenting training data with generated variants (augmented training). The results are mixed, but repeated encoding and decoding indeed result in qualitatively and quantitatively more typical examples from both convolutional and fully-connected MNIST VAEs, suggesting that it may be an inherent property of the VAE framework. |
| Tasks | |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1904.10937v1 |
| http://arxiv.org/pdf/1904.10937v1.pdf | |
| PWC | https://paperswithcode.com/paper/generated-loss-and-augmented-training-of |
| Repo | |
| Framework | |
On the Definition of Japanese Word
| Title | On the Definition of Japanese Word |
| Authors | Yugo Murawaki |
| Abstract | The annotation guidelines for Universal Dependencies (UD) stipulate that the basic units of dependency annotation are syntactic words, but it is not clear what are syntactic words in Japanese. Departing from the long tradition of using phrasal units called bunsetsu for dependency parsing, the current UD Japanese treebanks adopt the Short Unit Words. However, we argue that they are not syntactic word as specified by the annotation guidelines. Although we find non-mainstream attempts to linguistically define Japanese words, such definitions have never been applied to corpus annotation. We discuss the costs and benefits of adopting the rather unfamiliar criteria. |
| Tasks | Dependency Parsing |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.09719v1 |
| https://arxiv.org/pdf/1906.09719v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-definition-of-japanese-word |
| Repo | |
| Framework | |
Method for the semantic indexing of concept hierarchies, uniform representation, use of relational database systems and generic and case-based reasoning
| Title | Method for the semantic indexing of concept hierarchies, uniform representation, use of relational database systems and generic and case-based reasoning |
| Authors | Uwe Petersohn, Sandra Zimmer, Jens Lehmann |
| Abstract | This paper presents a method for semantic indexing and describes its application in the field of knowledge representation. Starting point of the semantic indexing is the knowledge represented by concept hierarchies. The goal is to assign keys to nodes (concepts) that are hierarchically ordered and syntactically and semantically correct. With the indexing algorithm, keys are computed such that concepts are partially unifiable with all more specific concepts and only semantically correct concepts are allowed to be added. The keys represent terminological relationships. Correctness and completeness of the underlying indexing algorithm are proven. The use of classical relational databases for the storage of instances is described. Because of the uniform representation, inference can be done using case-based reasoning and generic problem solving methods. |
| Tasks | |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01539v1 |
| https://arxiv.org/pdf/1910.01539v1.pdf | |
| PWC | https://paperswithcode.com/paper/method-for-the-semantic-indexing-of-concept |
| Repo | |
| Framework | |
Towards Comparing Programming Paradigms
| Title | Towards Comparing Programming Paradigms |
| Authors | Igor Ivkic, Alexander Wöhrer, Markus Tauber |
| Abstract | Rapid technological progress in computer sciences finds solutions and at the same time creates ever more complex requirements. Due to an evolving complexity todays programming languages provide powerful frameworks which offer standard solutions for recurring tasks to assist the programmer and to avoid the re-invention of the wheel with so-called out-of-the-box-features. In this paper, we propose a way of comparing different programming paradigms on a theoretical, technical and practical level. Furthermore, the paper presents the results of an initial comparison of two representative programming approaches, both in the closed SAP environment. |
| Tasks | |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06777v1 |
| https://arxiv.org/pdf/1905.06777v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-comparing-programming-paradigms |
| Repo | |
| Framework | |
A Narration-based Reward Shaping Approach using Grounded Natural Language Commands
| Title | A Narration-based Reward Shaping Approach using Grounded Natural Language Commands |
| Authors | Nicholas Waytowich, Sean L. Barton, Vernon Lawhern, Garrett Warnell |
| Abstract | While deep reinforcement learning techniques have led to agents that are successfully able to learn to perform a number of tasks that had been previously unlearnable, these techniques are still susceptible to the longstanding problem of reward sparsity. This is especially true for tasks such as training an agent to play StarCraft II, a real-time strategy game where reward is only given at the end of a game which is usually very long. While this problem can be addressed through reward shaping, such approaches typically require a human expert with specialized knowledge. Inspired by the vision of enabling reward shaping through the more-accessible paradigm of natural-language narration, we develop a technique that can provide the benefits of reward shaping using natural language commands. Our narration-guided RL agent projects sequences of natural-language commands into the same high-dimensional representation space as corresponding goal states. We show that we can get improved performance with our method compared to traditional reward-shaping approaches. Additionally, we demonstrate the ability of our method to generalize to unseen natural-language commands. |
| Tasks | Starcraft, Starcraft II |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1911.00497v1 |
| https://arxiv.org/pdf/1911.00497v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-narration-based-reward-shaping-approach |
| Repo | |
| Framework | |
Arena: a toolkit for Multi-Agent Reinforcement Learning
| Title | Arena: a toolkit for Multi-Agent Reinforcement Learning |
| Authors | Qing Wang, Jiechao Xiong, Lei Han, Meng Fang, Xinghai Sun, Zhuobin Zheng, Peng Sun, Zhengyou Zhang |
| Abstract | We introduce Arena, a toolkit for multi-agent reinforcement learning (MARL) research. In MARL, it usually requires customizing observations, rewards and actions for each agent, changing cooperative-competitive agent-interaction, and playing with/against a third-party agent, etc. We provide a novel modular design, called Interface, for manipulating such routines in essentially two ways: 1) Different interfaces can be concatenated and combined, which extends the OpenAI Gym Wrappers concept to MARL scenarios. 2) During MARL training or testing, interfaces can be embedded in either wrapped OpenAI Gym compatible Environments or raw environment compatible Agents. We offer off-the-shelf interfaces for several popular MARL platforms, including StarCraft II, Pommerman, ViZDoom, Soccer, etc. The interfaces effectively support self-play RL and cooperative-competitive hybrid MARL. Also, Arena can be conveniently extended to your own favorite MARL platform. |
| Tasks | Multi-agent Reinforcement Learning, Starcraft, Starcraft II |
| Published | 2019-07-20 |
| URL | https://arxiv.org/abs/1907.09467v1 |
| https://arxiv.org/pdf/1907.09467v1.pdf | |
| PWC | https://paperswithcode.com/paper/arena-a-toolkit-for-multi-agent-reinforcement |
| Repo | |
| Framework | |
Learning a Behavioral Repertoire from Demonstrations
| Title | Learning a Behavioral Repertoire from Demonstrations |
| Authors | Niels Justesen, Miguel Gonzalez Duque, Daniel Cabarcas Jaramillo, Jean-Baptiste Mouret, Sebastian Risi |
| Abstract | Imitation Learning (IL) is a machine learning approach to learn a policy from a dataset of demonstrations. IL can be useful to kick-start learning before applying reinforcement learning (RL) but it can also be useful on its own, e.g. to learn to imitate human players in video games. However, a major limitation of current IL approaches is that they learn only a single “average” policy based on a dataset that possibly contains demonstrations of numerous different types of behaviors. In this paper, we propose a new approach called Behavioral Repertoire Imitation Learning (BRIL) that instead learns a repertoire of behaviors from a set of demonstrations by augmenting the state-action pairs with behavioral descriptions. The outcome of this approach is a single neural network policy conditioned on a behavior description that can be precisely modulated. We apply this approach to train a policy on 7,777 human replays to perform build-order planning in StarCraft II. Principal Component Analysis (PCA) is applied to construct a low-dimensional behavioral space from the high-dimensional army unit composition of each demonstration. The results demonstrate that the learned policy can be effectively manipulated to express distinct behaviors. Additionally, by applying the UCB1 algorithm, we are able to adapt the behavior of the policy - in-between games - to reach a performance beyond that of the traditional IL baseline approach. |
| Tasks | Imitation Learning, Starcraft, Starcraft II |
| Published | 2019-07-05 |
| URL | https://arxiv.org/abs/1907.03046v1 |
| https://arxiv.org/pdf/1907.03046v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-behavioral-repertoire-from |
| Repo | |
| Framework | |
Coordinated Joint Multimodal Embeddings for Generalized Audio-Visual Zeroshot Classification and Retrieval of Videos
| Title | Coordinated Joint Multimodal Embeddings for Generalized Audio-Visual Zeroshot Classification and Retrieval of Videos |
| Authors | Kranti Kumar Parida, Neeraj Matiyali, Tanaya Guha, Gaurav Sharma |
| Abstract | We present an audio-visual multimodal approach for the task of zeroshot learning (ZSL) for classification and retrieval of videos. ZSL has been studied extensively in the recent past but has primarily been limited to visual modality and to images. We demonstrate that both audio and visual modalities are important for ZSL for videos. Since a dataset to study the task is currently not available, we also construct an appropriate multimodal dataset with 33 classes containing 156,416 videos, from an existing large scale audio event dataset. We empirically show that the performance improves by adding audio modality for both tasks of zeroshot classification and retrieval, when using multimodal extensions of embedding learning methods. We also propose a novel method to predict the `dominant’ modality using a jointly learned modality attention network. We learn the attention in a semi-supervised setting and thus do not require any additional explicit labelling for the modalities. We provide qualitative validation of the modality specific attention, which also successfully generalizes to unseen test classes. | |
| Tasks | |
| Published | 2019-10-19 |
| URL | https://arxiv.org/abs/1910.08732v1 |
| https://arxiv.org/pdf/1910.08732v1.pdf | |
| PWC | https://paperswithcode.com/paper/coordinated-joint-multimodal-embeddings-for |
| Repo | |
| Framework | |
