Paper Group ANR 640
Eye in the Sky: Drone-Based Object Tracking and 3D Localization. Using Logical Specifications of Objectives in Multi-Objective Reinforcement Learning. Radio Resource Allocation in 5G New Radio: A Neural Networks Based Approach). The Quest for Interpretable and Responsible Artificial Intelligence. Maximal Margin Distribution Support Vector Regressio …
Eye in the Sky: Drone-Based Object Tracking and 3D Localization
| Title | Eye in the Sky: Drone-Based Object Tracking and 3D Localization |
| Authors | Haotian Zhang, Gaoang Wang, Zhichao Lei, Jenq-Neng Hwang |
| Abstract | Drones, or general UAVs, equipped with a single camera have been widely deployed to a broad range of applications, such as aerial photography, fast goods delivery and most importantly, surveillance. Despite the great progress achieved in computer vision algorithms, these algorithms are not usually optimized for dealing with images or video sequences acquired by drones, due to various challenges such as occlusion, fast camera motion and pose variation. In this paper, a drone-based multi-object tracking and 3D localization scheme is proposed based on the deep learning based object detection. We first combine a multi-object tracking method called TrackletNet Tracker (TNT) which utilizes temporal and appearance information to track detected objects located on the ground for UAV applications. Then, we are also able to localize the tracked ground objects based on the group plane estimated from the Multi-View Stereo technique. The system deployed on the drone can not only detect and track the objects in a scene, but can also localize their 3D coordinates in meters with respect to the drone camera. The experiments have proved our tracker can reliably handle most of the detected objects captured by drones and achieve favorable 3D localization performance when compared with the state-of-the-art methods. |
| Tasks | Multi-Object Tracking, Object Detection, Object Tracking |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08259v1 |
| https://arxiv.org/pdf/1910.08259v1.pdf | |
| PWC | https://paperswithcode.com/paper/eye-in-the-sky-drone-based-object-tracking |
| Repo | |
| Framework | |
Using Logical Specifications of Objectives in Multi-Objective Reinforcement Learning
| Title | Using Logical Specifications of Objectives in Multi-Objective Reinforcement Learning |
| Authors | Kolby Nottingham, Anand Balakrishnan, Jyotirmoy Deshmukh, Connor Christopherson, David Wingate |
| Abstract | In the multi-objective reinforcement learning (MORL) paradigm, the relative importance of each environment objective is often unknown prior to training, so agents must learn to specialize their behavior to optimize different combinations of environment objectives that are specified post-training. These are typically linear combinations, so the agent is effectively parameterized by a weight vector that describes how to balance competing environment objectives. However, many real world behaviors require non-linear combinations of objectives. Additionally, the conversion between desired behavior and weightings is often unclear. In this work, we explore the use of a language based on propositional logic with quantitative semantics–in place of weight vectors–for specifying non-linear behaviors in an interpretable way. We use a recurrent encoder to encode logical combinations of objectives, and train a MORL agent to generalize over these encodings. We test our agent in several grid worlds with various objectives and show that our agent can generalize to many never-before-seen specifications with performance comparable to single policy baseline agents. We also demonstrate our agent’s ability to generate meaningful policies when presented with novel specifications and quickly specialize to novel specifications. |
| Tasks | |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01723v1 |
| https://arxiv.org/pdf/1910.01723v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-logical-specifications-of-objectives-in |
| Repo | |
| Framework | |
Radio Resource Allocation in 5G New Radio: A Neural Networks Based Approach)
| Title | Radio Resource Allocation in 5G New Radio: A Neural Networks Based Approach) |
| Authors | Madyan Alsenwi, Kitae Kim, Choong Seon Hong |
| Abstract | The minimum frequency-time unit that can be allocated to User Equipments (UEs) in the fifth generation (5G) cellular networks is a Resource Block (RB). A RB is a channel composed of a set of OFDM subcarriers for a given time slot duration. 5G New Radio (NR) allows for a large number of block shapes ranging from 15 kHz to 480 kHz. In this paper, we address the problem of RBs allocation to UEs. The RBs are allocated at the beginning of each time slot based on the channel state of each UE. The problem is formulated based on the Generalized Proportional Fair (GPF) scheduling. Then, we model the problem as a 2-Dimension Hopfield Neural Networks (2D-HNN). Finally, in an attempt to solve the problem, the energy function of 2D-HNN is investigated. Simulation results show the efficiency of the proposed approach. |
| Tasks | |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.05294v1 |
| https://arxiv.org/pdf/1911.05294v1.pdf | |
| PWC | https://paperswithcode.com/paper/radio-resource-allocation-in-5g-new-radio-a |
| Repo | |
| Framework | |
The Quest for Interpretable and Responsible Artificial Intelligence
| Title | The Quest for Interpretable and Responsible Artificial Intelligence |
| Authors | Vaishak Belle |
| Abstract | Artificial Intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives applications in computational biology, finance, law and robotics. However, such a highly positive impact is coupled with significant challenges: How do we understand the decisions suggested by these systems in order that we can trust them? How can they be held accountable for those decisions? In this short survey, we cover some of the motivations and trends in the area that attempt to address such questions. |
| Tasks | |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04527v1 |
| https://arxiv.org/pdf/1910.04527v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-quest-for-interpretable-and-responsible |
| Repo | |
| Framework | |
Maximal Margin Distribution Support Vector Regression with coupled Constraints-based Convex Optimization
| Title | Maximal Margin Distribution Support Vector Regression with coupled Constraints-based Convex Optimization |
| Authors | Gaoyang Li, Jinyu Yang, Chunguo Wu, Qin Ma |
| Abstract | Support vector regression (SVR) is one of the most popular machine learning algorithms aiming to generate the optimal regression curve through maximizing the minimal margin of selected training samples, i.e., support vectors. Recent researchers reveal that maximizing the margin distribution of whole training dataset rather than the minimal margin of a few support vectors, is prone to achieve better generalization performance. However, the margin distribution support vector regression machines suffer difficulties resulted from solving a non-convex quadratic optimization, compared to the margin distribution strategy for support vector classification, This paper firstly proposes a maximal margin distribution model for SVR(MMD-SVR), then implementing coupled constrain factor to convert the non-convex quadratic optimization to a convex problem with linear constrains, which enhance the training feasibility and efficiency for SVR to derived from maximizing the margin distribution. The theoretical and empirical analysis illustrates the superiority of MMD-SVR. In addition, numerical experiments show that MMD-SVR could significantly improve the accuracy of prediction and generate more smooth regression curve with better generalization compared with the classic SVR. |
| Tasks | |
| Published | 2019-05-05 |
| URL | https://arxiv.org/abs/1905.01620v1 |
| https://arxiv.org/pdf/1905.01620v1.pdf | |
| PWC | https://paperswithcode.com/paper/maximal-margin-distribution-support-vector |
| Repo | |
| Framework | |
Is There an Analog of Nesterov Acceleration for MCMC?
| Title | Is There an Analog of Nesterov Acceleration for MCMC? |
| Authors | Yi-An Ma, Niladri Chatterji, Xiang Cheng, Nicolas Flammarion, Peter Bartlett, Michael I. Jordan |
| Abstract | We formulate gradient-based Markov chain Monte Carlo (MCMC) sampling as optimization on the space of probability measures, with Kullback-Leibler (KL) divergence as the objective functional. We show that an underdamped form of the Langevin algorithm performs accelerated gradient descent in this metric. To characterize the convergence of the algorithm, we construct a Lyapunov functional and exploit hypocoercivity of the underdamped Langevin algorithm. As an application, we show that accelerated rates can be obtained for a class of nonconvex functions with the Langevin algorithm. |
| Tasks | |
| Published | 2019-02-04 |
| URL | https://arxiv.org/abs/1902.00996v2 |
| https://arxiv.org/pdf/1902.00996v2.pdf | |
| PWC | https://paperswithcode.com/paper/is-there-an-analog-of-nesterov-acceleration |
| Repo | |
| Framework | |
Intuitionistic Linear Temporal Logics
| Title | Intuitionistic Linear Temporal Logics |
| Authors | Philippe Balbiani, Joseph Boudou, Martín Diéguez, David Fernández-Duque |
| Abstract | We consider intuitionistic variants of linear temporal logic with next', until’ and release' based on expanding posets: partial orders equipped with an order-preserving transition function. This class of structures gives rise to a logic which we denote $\iltl$, and by imposing additional constraints we obtain the logics $\itlb$ of persistent posets and $\itlht$ of here-and-there temporal logic, both of which have been considered in the literature. We prove that $\iltl$ has the effective finite model property and hence is decidable, while $\itlb$ does not have the finite model property. We also introduce notions of bounded bisimulations for these logics and use them to show that the until’ and `release’ operators are not definable in terms of each other, even over the class of persistent posets. | |
| Tasks | |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12893v1 |
| https://arxiv.org/pdf/1912.12893v1.pdf | |
| PWC | https://paperswithcode.com/paper/intuitionistic-linear-temporal-logics |
| Repo | |
| Framework | |
Eliminating Bias in Recommender Systems via Pseudo-Labeling
| Title | Eliminating Bias in Recommender Systems via Pseudo-Labeling |
| Authors | Yuta Saito |
| Abstract | Addressing the non-uniform missing mechanism of rating feedback is critical to build a well-performing recommeder in the real-world systems. To tackle the challenging issue, we first define an ideal loss function that should be optimized to achieve the goal of recommendation. Then, we derive the generalization error bound of the ideal loss that alleviates the variance and the misspecification problems of the previous propensity-based methods. We further propose a meta-learning method minimizing the bound. Empirical evaluation using real-world datasets validates the theoretical findings and demonstrates the practical advantages of the proposed upper bound minimization approach. |
| Tasks | Meta-Learning, Recommendation Systems |
| Published | 2019-09-08 |
| URL | https://arxiv.org/abs/1910.01444v5 |
| https://arxiv.org/pdf/1910.01444v5.pdf | |
| PWC | https://paperswithcode.com/paper/eliminating-bias-in-recommender-systems-via |
| Repo | |
| Framework | |
GASC: Genre-Aware Semantic Change for Ancient Greek
| Title | GASC: Genre-Aware Semantic Change for Ancient Greek |
| Authors | Valerio Perrone, Marco Palma, Simon Hengchen, Alessandro Vatri, Jim Q. Smith, Barbara McGillivray |
| Abstract | Word meaning changes over time, depending on linguistic and extra-linguistic factors. Associating a word’s correct meaning in its historical context is a central challenge in diachronic research, and is relevant to a range of NLP tasks, including information retrieval and semantic search in historical texts. Bayesian models for semantic change have emerged as a powerful tool to address this challenge, providing explicit and interpretable representations of semantic change phenomena. However, while corpora typically come with rich metadata, existing models are limited by their inability to exploit contextual information (such as text genre) beyond the document time-stamp. This is particularly critical in the case of ancient languages, where lack of data and long diachronic span make it harder to draw a clear distinction between polysemy (the fact that a word has several senses) and semantic change (the process of acquiring, losing, or changing senses), and current systems perform poorly on these languages. We develop GASC, a dynamic semantic change model that leverages categorical metadata about the texts’ genre to boost inference and uncover the evolution of meanings in Ancient Greek corpora. In a new evaluation framework, our model achieves improved predictive performance compared to the state of the art. |
| Tasks | Information Retrieval |
| Published | 2019-03-13 |
| URL | https://arxiv.org/abs/1903.05587v2 |
| https://arxiv.org/pdf/1903.05587v2.pdf | |
| PWC | https://paperswithcode.com/paper/gasc-genre-aware-semantic-change-for-ancient |
| Repo | |
| Framework | |
A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translation
| Title | A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translation |
| Authors | Shuoyang Ding, Adithya Renduchintala, Kevin Duh |
| Abstract | Most neural machine translation systems are built upon subword units extracted by methods such as Byte-Pair Encoding (BPE) or wordpiece. However, the choice of number of merge operations is generally made by following existing recipes. In this paper, we conduct a systematic exploration on different numbers of BPE merge operations to understand how it interacts with the model architecture, the strategy to build vocabularies and the language pair. Our exploration could provide guidance for selecting proper BPE configurations in the future. Most prominently: we show that for LSTM-based architectures, it is necessary to experiment with a wide range of different BPE operations as there is no typical optimal BPE configuration, whereas for Transformer architectures, smaller BPE size tends to be a typically optimal choice. We urge the community to make prudent choices with subword merge operations, as our experiments indicate that a sub-optimal BPE configuration alone could easily reduce the system performance by 3-4 BLEU points. |
| Tasks | Machine Translation |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10453v2 |
| https://arxiv.org/pdf/1905.10453v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-call-for-prudent-choice-of-subword-merge |
| Repo | |
| Framework | |
Multiparametric Deep Learning and Radiomics for Tumor Grading and Treatment Response Assessment of Brain Cancer: Preliminary Results
| Title | Multiparametric Deep Learning and Radiomics for Tumor Grading and Treatment Response Assessment of Brain Cancer: Preliminary Results |
| Authors | Vishwa S. Parekh, John Laterra, Chetan Bettegowda, Alex E. Bocchieri, Jay J. Pillai, Michael A. Jacobs |
| Abstract | Radiomics is an exciting new area of texture research for extracting quantitative and morphological characteristics of pathological tissue. However, to date, only single images have been used for texture analysis. We have extended radiomic texture methods to use multiparametric (mp) data to get more complete information from all the images. These mpRadiomic methods could potentially provide a platform for stratification of tumor grade as well as assessment of treatment response in brain tumors. In brain, multiparametric MRI (mpMRI) are based on contrast enhanced T1-weighted imaging (T1WI), T2WI, Fluid Attenuated Inversion Recovery (FLAIR), Diffusion Weighted Imaging (DWI) and Perfusion Weighted Imaging (PWI). Therefore, we applied our multiparametric radiomic framework (mpRadiomic) on 24 patients with brain tumors (8 grade II and 16 grade IV). The mpRadiomic framework classified grade IV tumors from grade II tumors with a sensitivity and specificity of 93% and 100%, respectively, with an AUC of 0.95. For treatment response, the mpRadiomic framework classified pseudo-progression from true-progression with an AUC of 0.93. In conclusion, the mpRadiomic analysis was able to effectively capture the multiparametric brain MRI texture and could be used as potential biomarkers for distinguishing grade IV from grade II tumors as well as determining true-progression from pseudo-progression. |
| Tasks | Texture Classification |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.04049v1 |
| https://arxiv.org/pdf/1906.04049v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiparametric-deep-learning-and-radiomics |
| Repo | |
| Framework | |
Comparative Performance Analysis of Image De-noising Techniques
| Title | Comparative Performance Analysis of Image De-noising Techniques |
| Authors | Vivek Kumar, Atul Samadhiya |
| Abstract | Noise is an important factor which when get added to an image reduces its quality and appearance. So in order to enhance the image qualities, it has to be removed with preserving the textural information and structural features of image. There are different types of noises exist who corrupt the images. Selection of the denoising algorithm is application dependent. Hence, it is necessary to have knowledge about the noise present in the image so as to select the appropriate denoising algorithm. Objective of this paper is to present brief account on types of noises, its types and different noise removal algorithms. In the first section types of noises on the basis of their additive and multiplicative nature are being discussed. In second section a precise classification and analysis of the different potential image denoising algorithm is presented. At the end of paper, a comparative study of all these algorithms in context of performance evaluation is done and concluded with several promising directions for future research work. |
| Tasks | Denoising, Image Denoising |
| Published | 2019-01-19 |
| URL | http://arxiv.org/abs/1901.06529v1 |
| http://arxiv.org/pdf/1901.06529v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparative-performance-analysis-of-image-de |
| Repo | |
| Framework | |
A self-attention based deep learning method for lesion attribute detection from CT reports
| Title | A self-attention based deep learning method for lesion attribute detection from CT reports |
| Authors | Yifan Peng, Ke Yan, Veit Sandfort, Ronald M. Summers, Zhiyong Lu |
| Abstract | In radiology, radiologists not only detect lesions from the medical image, but also describe them with various attributes such as their type, location, size, shape, and intensity. While these lesion attributes are rich and useful in many downstream clinical applications, how to extract them from the radiology reports is less studied. This paper outlines a novel deep learning method to automatically extract attributes of lesions of interest from the clinical text. Different from classical CNN models, we integrated the multi-head self-attention mechanism to handle the long-distance information in the sentence, and to jointly correlate different portions of sentence representation subspaces in parallel. Evaluation on an in-house corpus demonstrates that our method can achieve high performance with 0.848 in precision, 0.788 in recall, and 0.815 in F-score. The new method and constructed corpus will enable us to build automatic systems with a higher-level understanding of the radiological world. |
| Tasks | |
| Published | 2019-04-30 |
| URL | http://arxiv.org/abs/1904.13018v1 |
| http://arxiv.org/pdf/1904.13018v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-self-attention-based-deep-learning-method |
| Repo | |
| Framework | |
Shortest Paths in HSI Space for Color Texture Classification
| Title | Shortest Paths in HSI Space for Color Texture Classification |
| Authors | Mingxin Jin, Yongsheng Dong, Lintao Zheng, Lingfei Liang, Tianyu Wang, Hongyan zhang |
| Abstract | Color texture representation is an important step in the task of texture classification. Shortest paths was used to extract color texture features from RGB and HSV color spaces. In this paper, we propose to use shortest paths in the HSI space to build a texture representation for classification. In particular, two undirected graphs are used to model the H channel and the S and I channels respectively in order to represent a color texture image. Moreover, the shortest paths is constructed by using four pairs of pixels according to different scales and directions of the texture image. Experimental results on colored Brodatz and USPTex databases reveal that our proposed method is effective, and the highest classification accuracy rate is 96.93% in the Brodatz database. |
| Tasks | Texture Classification |
| Published | 2019-04-16 |
| URL | http://arxiv.org/abs/1904.07429v1 |
| http://arxiv.org/pdf/1904.07429v1.pdf | |
| PWC | https://paperswithcode.com/paper/shortest-paths-in-hsi-space-for-color-texture |
| Repo | |
| Framework | |
Behavior Regularized Offline Reinforcement Learning
| Title | Behavior Regularized Offline Reinforcement Learning |
| Authors | Yifan Wu, George Tucker, Ofir Nachum |
| Abstract | In reinforcement learning (RL) research, it is common to assume access to direct online interactions with the environment. However in many real-world applications, access to the environment is limited to a fixed offline dataset of logged experience. In such settings, standard RL algorithms have been shown to diverge or otherwise yield poor performance. Accordingly, recent work has suggested a number of remedies to these issues. In this work, we introduce a general framework, behavior regularized actor critic (BRAC), to empirically evaluate recently proposed methods as well as a number of simple baselines across a variety of offline continuous control tasks. Surprisingly, we find that many of the technical complexities introduced in recent methods are unnecessary to achieve strong performance. Additional ablations provide insights into which design choices matter most in the offline RL setting. |
| Tasks | Continuous Control |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11361v1 |
| https://arxiv.org/pdf/1911.11361v1.pdf | |
| PWC | https://paperswithcode.com/paper/behavior-regularized-offline-reinforcement-1 |
| Repo | |
| Framework | |
