January 30, 2020

3046 words 15 mins read

Paper Group ANR 358

A Weighted Functional Object-Oriented Network for Task Planning. Facility Location Problem with Capacity Constraints: Algorithmic and Mechanism Design Perspectives. Effective Integration of Symbolic and Connectionist Approaches through a Hybrid Representation. Software-defined Design Space Exploration for an Efficient DNN Accelerator Architecture. …

A Weighted Functional Object-Oriented Network for Task Planning


Title	A Weighted Functional Object-Oriented Network for Task Planning
Authors	David Paulius, Kelvin Sheng Pei Dong, Yu Sun
Abstract	Prior to this work, we introduced the functional object-oriented network (FOON) as a graphical knowledge representation for manipulations that can be performed by domestic robots. However, up to this point, we did not account for real robot task planning with FOON due to the difficulty in robots performing certain manipulations on its own due to physical limitations. We therefore propose human-robot collaboration (HRC) as a solution to robotic programming with FOON. The knowledge retrieval procedure, used for acquiring a sequence that solves a given problem, is modified to include weights that reflect the robot’s chance of successfully executing motions. To make it easier for the robot, a human can assist to the minimal extent needed to perform the activity to completion by delegating those actions with low success rates to the human to do. From our experiments, we show that tasks can be completed successfully with the aid of the assistant and instruction from the robot while minimizing the effort needed from the human.
Tasks	Robot Task Planning
Published	2019-05-01
URL	https://arxiv.org/abs/1905.00502v2
PDF	https://arxiv.org/pdf/1905.00502v2.pdf
PWC	https://paperswithcode.com/paper/functional-object-oriented-network-1
Repo
Framework

Facility Location Problem with Capacity Constraints: Algorithmic and Mechanism Design Perspectives


Title	Facility Location Problem with Capacity Constraints: Algorithmic and Mechanism Design Perspectives
Authors	Haris Aziz, Hau Chan, Barton E. Lee, Bo Li, Toby Walsh
Abstract	We consider the facility location problem in the one-dimensional setting where each facility can serve a limited number of agents from the algorithmic and mechanism design perspectives. From the algorithmic perspective, we prove that the corresponding optimization problem, where the goal is to locate facilities to minimize either the total cost to all agents or the maximum cost of any agent is NP-hard. However, we show that the problem is fixed-parameter tractable, and the optimal solution can be computed in polynomial time whenever the number of facilities is bounded, or when all facilities have identical capacities. We then consider the problem from a mechanism design perspective where the agents are strategic and need not reveal their true locations. We show that several natural mechanisms studied in the uncapacitated setting either lose strategyproofness or a bound on the solution quality for the total or maximum cost objective. We then propose new mechanisms that are strategyproof and achieve approximation guarantees that almost match the lower bounds.
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.09813v1
PDF	https://arxiv.org/pdf/1911.09813v1.pdf
PWC	https://paperswithcode.com/paper/facility-location-problem-with-capacity
Repo
Framework

Effective Integration of Symbolic and Connectionist Approaches through a Hybrid Representation


Title	Effective Integration of Symbolic and Connectionist Approaches through a Hybrid Representation
Authors	Marcio Moreno, Daniel Civitarese, Rafael Brandao, Renato Cerqueira
Abstract	In this paper, we present our position for a neuralsymbolic integration strategy, arguing in favor of a hybrid representation to promote an effective integration. Such description differs from others fundamentally, since its entities aim at representing AI models in general, allowing to describe both nonsymbolic and symbolic knowledge, the integration between them and their corresponding processors. Moreover, the entities also support representing workflows, leveraging traceability to keep track of every change applied to models and their related entities (e.g., data or concepts) throughout the lifecycle of the models.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08740v1
PDF	https://arxiv.org/pdf/1912.08740v1.pdf
PWC	https://paperswithcode.com/paper/effective-integration-of-symbolic-and
Repo
Framework

Software-defined Design Space Exploration for an Efficient DNN Accelerator Architecture


Title	Software-defined Design Space Exploration for an Efficient DNN Accelerator Architecture
Authors	Ye Yu, Yingmin Li, Shuai Che, Niraj K. Jha, Weifeng Zhang
Abstract	Deep neural networks (DNNs) have been shown to outperform conventional machine learning algorithms across a wide range of applications, e.g., image recognition, object detection, robotics, and natural language processing. However, the high computational complexity of DNNs often necessitates extremely fast and efficient hardware. The problem gets worse as the size of neural networks grows exponentially. As a result, customized hardware accelerators have been developed to accelerate DNN processing without sacrificing model accuracy. However, previous accelerator design studies have not fully considered the characteristics of the target applications, which may lead to sub-optimal architecture designs. On the other hand, new DNN models have been developed for better accuracy, but their compatibility with the underlying hardware accelerator is often overlooked. In this article, we propose an application-driven framework for architectural design space exploration of DNN accelerators. This framework is based on a hardware analytical model of individual DNN operations. It models the accelerator design task as a multi-dimensional optimization problem. We demonstrate that it can be efficaciously used in application-driven accelerator architecture design. Given a target DNN, the framework can generate efficient accelerator design solutions with optimized performance and area. Furthermore, we explore the opportunity to use the framework for accelerator configuration optimization under simultaneous diverse DNN applications. The framework is also capable of improving neural network models to best fit the underlying hardware resources.
Tasks	Object Detection
Published	2019-03-18
URL	https://arxiv.org/abs/1903.07676v2
PDF	https://arxiv.org/pdf/1903.07676v2.pdf
PWC	https://paperswithcode.com/paper/software-defined-design-space-exploration-for
Repo
Framework

Markov versus quantum dynamic models of belief change during evidence monitoring


Title	Markov versus quantum dynamic models of belief change during evidence monitoring
Authors	Jerome R. Busemeyer, Peter D. Kvam, Timothy J. Pleskac
Abstract	Two different dynamic models for belief change during evidence monitoring were evaluated: Markov and quantum. They were empirically tested with an experiment in which participants monitored evidence for an initial period of time, made a probability rating, then monitored more evidence, before making a second rating. The models were qualitatively tested by manipulating the time intervals in a manner that provided a test for interference effects of the first rating on the second. The Markov model predicted no interference whereas the quantum model predicted interference. A quantitative comparison of the two models was also carried out using a generalization criterion method: the parameters were fit to data from one set of time intervals, and then these same parameters were used to predict data from another set of time intervals. The results indicated that some features of both Markov and quantum models are needed to accurately account for the results.
Tasks
Published	2019-05-10
URL	https://arxiv.org/abs/1905.05288v2
PDF	https://arxiv.org/pdf/1905.05288v2.pdf
PWC	https://paperswithcode.com/paper/markov-versus-quantum-dynamic-models-of
Repo
Framework

HumanGAN: generative adversarial network with human-based discriminator and its evaluation in speech perception modeling


Title	HumanGAN: generative adversarial network with human-based discriminator and its evaluation in speech perception modeling
Authors	Kazuki Fujii, Yuki Saito, Shinnosuke Takamichi, Yukino Baba, Hiroshi Saruwatari
Abstract	We propose the HumanGAN, a generative adversarial network (GAN) incorporating human perception as a discriminator. A basic GAN trains a generator to represent a real-data distribution by fooling the discriminator that distinguishes real and generated data. Therefore, the basic GAN cannot represent the outside of a real-data distribution. In the case of speech perception, humans can recognize not only human voices but also processed (i.e., a non-existent human) voices as human voice. Such a human-acceptable distribution is typically wider than a real-data one and cannot be modeled by the basic GAN. To model the human-acceptable distribution, we formulate a backpropagation-based generator training algorithm by regarding human perception as a black-boxed discriminator. The training efficiently iterates generator training by using a computer and discrimination by crowdsourcing. We evaluate our HumanGAN in speech naturalness modeling and demonstrate that it can represent a human-acceptable distribution that is wider than a real-data distribution.
Tasks
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11391v1
PDF	https://arxiv.org/pdf/1909.11391v1.pdf
PWC	https://paperswithcode.com/paper/humangan-generative-adversarial-network-with
Repo
Framework

Building a Massive Corpus for Named Entity Recognition using Free Open Data Sources


Title	Building a Massive Corpus for Named Entity Recognition using Free Open Data Sources
Authors	Daniel Specht Menezes, Pedro Savarese, Ruy Luiz Milidiú
Abstract	With the recent progress in machine learning, boosted by techniques such as deep learning, many tasks can be successfully solved once a large enough dataset is available for training. Nonetheless, human-annotated datasets are often expensive to produce, especially when labels are fine-grained, as is the case of Named Entity Recognition (NER), a task that operates with labels on a word-level. In this paper, we propose a method to automatically generate labeled datasets for NER from public data sources by exploiting links and structured data from DBpedia and Wikipedia. Due to the massive size of these data sources, the resulting dataset – SESAME Available at https://sesame-pt.github.io – is composed of millions of labeled sentences. We detail the method to generate the dataset, report relevant statistics, and design a baseline using a neural network, showing that our dataset helps building better NER predictors.
Tasks	Named Entity Recognition
Published	2019-08-13
URL	https://arxiv.org/abs/1908.05758v1
PDF	https://arxiv.org/pdf/1908.05758v1.pdf
PWC	https://paperswithcode.com/paper/building-a-massive-corpus-for-named-entity
Repo
Framework

BSUV-Net: A Fully-Convolutional Neural Network for Background Subtraction of Unseen Videos


Title	BSUV-Net: A Fully-Convolutional Neural Network for Background Subtraction of Unseen Videos
Authors	M. Ozan Tezcan, Prakash Ishwar, Janusz Konrad
Abstract	Background subtraction is a basic task in computer vision and video processing often applied as a pre-processing step for object tracking, people recognition, etc. Recently, a number of successful background-subtraction algorithms have been proposed, however nearly all of the top-performing ones are supervised. Crucially, their success relies upon the availability of some annotated frames of the test video during training. Consequently, their performance on completely “unseen” videos is undocumented in the literature. In this work, we propose a new, supervised, background-subtraction algorithm for unseen videos (BSUV-Net) based on a fully-convolutional neural network. The input to our network consists of the current frame and two background frames captured at different time scales along with their semantic segmentation maps. In order to reduce the chance of overfitting, we also introduce a new data-augmentation technique which mitigates the impact of illumination difference between the background frames and the current frame. On the CDNet-2014 dataset, BSUV-Net outperforms state-of-the-art algorithms evaluated on unseen videos in terms of several metrics including F-measure, recall and precision.
Tasks	Data Augmentation, Object Tracking, Semantic Segmentation
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11371v2
PDF	https://arxiv.org/pdf/1907.11371v2.pdf
PWC	https://paperswithcode.com/paper/a-fully-convolutional-neural-network-for-2
Repo
Framework

Sparse Elasticity Reconstruction and Clustering using Local Displacement Fields


Title	Sparse Elasticity Reconstruction and Clustering using Local Displacement Fields
Authors	Megumi Nakao, Mitsuki Morita, Tetsuya Matsuda
Abstract	This paper introduces an elasticity reconstruction method based on local displacement observations of elastic bodies. Sparse reconstruction theory is applied to formulate the underdetermined inverse problems of elasticity reconstruction including unobserved areas. An online local clustering scheme called a superelement is proposed to reduce the number of dimensions of the optimization parameters. Alternating the optimization of element boundaries and elasticity parameters enables the elasticity distribution to be estimated with a higher spatial resolution. The simulation experiments show that elasticity distribution is reconstructed based on observations of approximately 10% of the total body. The estimation error was improved when considering the sparseness of the elasticity distribution.
Tasks
Published	2019-02-21
URL	http://arxiv.org/abs/1902.09328v1
PDF	http://arxiv.org/pdf/1902.09328v1.pdf
PWC	https://paperswithcode.com/paper/sparse-elasticity-reconstruction-and
Repo
Framework

Adaptive Routing Between Capsules


Title	Adaptive Routing Between Capsules
Authors	Qiang Ren, Shaohua Shang, Lianghua He
Abstract	Capsule network is the most recent exciting advancement in the deep learning field and represents positional information by stacking features into vectors. The dynamic routing algorithm is used in the capsule network, however, there are some disadvantages such as the inability to stack multiple layers and a large amount of computation. In this paper, we propose an adaptive routing algorithm that can solve the problems mentioned above. First, the low-layer capsules adaptively adjust their direction and length in the routing algorithm and removing the influence of the coupling coefficient on the gradient propagation, so that the network can work when stacked in multiple layers. Then, the iterative process of routing is simplified to reduce the amount of computation and we introduce the gradient coefficient $\lambda$. Further, we tested the performance of our proposed adaptive routing algorithm on CIFAR10, Fashion-MNIST, SVHN and MNIST, while achieving better results than the dynamic routing algorithm.
Tasks
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08119v1
PDF	https://arxiv.org/pdf/1911.08119v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-routing-between-capsules
Repo
Framework

Anytime Heuristic for Weighted Matching Through Altruism-Inspired Behavior


Title	Anytime Heuristic for Weighted Matching Through Altruism-Inspired Behavior
Authors	Panayiotis Danassis, Aris Filos-Ratsikas, Boi Faltings
Abstract	We present a novel anytime heuristic (ALMA), inspired by the human principle of altruism, for solving the assignment problem. ALMA is decentralized, completely uncoupled, and requires no communication between the participants. We prove an upper bound on the convergence speed that is polynomial in the desired number of resources and competing agents per resource; crucially, in the realistic case where the aforementioned quantities are bounded independently of the total number of agents/resources, the convergence time remains constant as the total problem size increases. We have evaluated ALMA under three test cases: (i) an anti-coordination scenario where agents with similar preferences compete over the same set of actions, (ii) a resource allocation scenario in an urban environment, under a constant-time constraint, and finally, (iii) an on-line matching scenario using real passenger-taxi data. In all of the cases, ALMA was able to reach high social welfare, while being orders of magnitude faster than the centralized, optimal algorithm. The latter allows our algorithm to scale to realistic scenarios with hundreds of thousands of agents, e.g., vehicle coordination in urban environments.
Tasks
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09359v1
PDF	http://arxiv.org/pdf/1902.09359v1.pdf
PWC	https://paperswithcode.com/paper/anytime-heuristic-for-weighted-matching
Repo
Framework

Improving Neural Question Generation using World Knowledge


Title	Improving Neural Question Generation using World Knowledge
Authors	Deepak Gupta, Kaheer Suleman, Mahmoud Adada, Andrew McNamara, Justin Harris
Abstract	In this paper, we propose a method for incorporating world knowledge (linked entities and fine-grained entity types) into a neural question generation model. This world knowledge helps to encode additional information related to the entities present in the passage required to generate human-like questions. We evaluate our models on both SQuAD and MS MARCO to demonstrate the usefulness of the world knowledge features. The proposed world knowledge enriched question generation model is able to outperform the vanilla neural question generation model by 1.37 and 1.59 absolute BLEU 4 score on SQuAD and MS MARCO test dataset respectively.
Tasks	Question Generation
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03716v2
PDF	https://arxiv.org/pdf/1909.03716v2.pdf
PWC	https://paperswithcode.com/paper/improving-neural-question-generation-using-1
Repo
Framework

Extension of Sinkhorn Method: Optimal Movement Estimation of Agents Moving at Constant Velocity


Title	Extension of Sinkhorn Method: Optimal Movement Estimation of Agents Moving at Constant Velocity
Authors	Daigo Okada, Naotoshi Nakamura, Takuya Wada, Ayako Iwasaki, Ryo Yamada
Abstract	In the field of bioimaging, an important part of analyzing the motion of objects is tracking. We propose a method that applies the Sinkhorn distance for solving the optimal transport problem to track objects. The advantage of this method is that it can flexibly incorporate various assumptions in tracking as a cost matrix. First, we extend the Sinkhorn distance from two dimensions to three dimensions. Using this three-dimensional distance, we compare the performance of two types of tracking technique, namely tracking that associates objects that are close to each other, which conventionally uses the nearest-neighbor method, and tracking that assumes that the object is moving at constant velocity, using three types of simulation data. The results suggest that when tracking objects moving at constant velocity, our method is superior to conventional nearest-neighbor tracking as long as the added noise is not excessively large. We show that the Sinkhorn method can be applied effectively to object tracking. Our simulation data analysis suggests that when objects are moving at constant velocity, our method, which sets acceleration as a cost, outperforms the traditional nearest-neighbor method in terms of tracking objects. To apply the proposed method to real bioimaging data, it is necessary to set an appropriate cost indicator based on the movement features.
Tasks	Object Tracking
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05036v1
PDF	https://arxiv.org/pdf/1907.05036v1.pdf
PWC	https://paperswithcode.com/paper/extension-of-sinkhorn-method-optimal-movement
Repo
Framework

Hierarchical Routing Mixture of Experts


Title	Hierarchical Routing Mixture of Experts
Authors	Wenbo Zhao, Yang Gao, Shahan Ali Memon, Bhiksha Raj, Rita Singh
Abstract	In regression tasks the distribution of the data is often too complex to be fitted by a single model. In contrast, partition-based models are developed where data is divided and fitted by local models. These models partition the input space and do not leverage the input-output dependency of multimodal-distributed data, and strong local models are needed to make good predictions. Addressing these problems, we propose a binary tree-structured hierarchical routing mixture of experts (HRME) model that has classifiers as non-leaf node experts and simple regression models as leaf node experts. The classifier nodes jointly soft-partition the input-output space based on the natural separateness of multimodal data. This enables simple leaf experts to be effective for prediction. Further, we develop a probabilistic framework for the HRME model, and propose a recursive Expectation-Maximization (EM) based algorithm to learn both the tree structure and the expert models. Experiments on a collection of regression tasks validate the effectiveness of our method compared to a variety of other regression models.
Tasks
Published	2019-03-18
URL	http://arxiv.org/abs/1903.07756v1
PDF	http://arxiv.org/pdf/1903.07756v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-routing-mixture-of-experts
Repo
Framework

Metric Learning with Background Noise Class for Few-shot Detection of Rare Sound Events


Title	Metric Learning with Background Noise Class for Few-shot Detection of Rare Sound Events
Authors	Kazuki Shimada, Yuichiro Koyama, Akira Inoue
Abstract	Few-shot learning systems for sound event recognition have gained interests since they require only a few examples to adapt to new target classes without fine-tuning. However, such systems have only been applied to chunks of sounds for classification or verification. In this paper, we aim to achieve few-shot detection of rare sound events, from query sequence that contain not only the target events but also the other events and background noise. Therefore, it is required to prevent false positive reactions to both the other events and background noise. We propose metric learning with background noise class for the few-shot detection. The contribution is to present the explicit inclusion of background noise as an independent class, a suitable loss function that emphasizes this additional class, and a corresponding sampling strategy that assists training. It provides a feature space where the event classes and the background noise class are sufficiently separated. Evaluations on few-shot detection tasks, using DCASE 2017 task2 and ESC-50, show that our proposed method outperforms metric learning without considering the background noise class. The few-shot detection performance is also comparable to that of the DCASE 2017 task2 baseline system, which requires huge amount of annotated audio data.
Tasks	Few-Shot Learning, Metric Learning
Published	2019-10-30
URL	https://arxiv.org/abs/1910.13724v2
PDF	https://arxiv.org/pdf/1910.13724v2.pdf
PWC	https://paperswithcode.com/paper/metric-learning-with-background-noise-class
Repo
Framework