October 16, 2019

3387 words 16 mins read

Paper Group ANR 1104

Extreme Adaptation for Personalized Neural Machine Translation. Interpretable Multi-Objective Reinforcement Learning through Policy Orchestration. TrQuery: An Embedding-based Framework for Recommanding SPARQL Queries. Pattern Recognition Approach to Violin Shapes of MIMO database. Detecting Satire in the News with Machine Learning. CrowdCam: Dynami …

Extreme Adaptation for Personalized Neural Machine Translation


Title	Extreme Adaptation for Personalized Neural Machine Translation
Authors	Paul Michel, Graham Neubig
Abstract	Every person speaks or writes their own flavor of their native language, influenced by a number of factors: the content they tend to talk about, their gender, their social status, or their geographical origin. When attempting to perform Machine Translation (MT), these variations have a significant effect on how the system should perform translation, but this is not captured well by standard one-size-fits-all models. In this paper, we propose a simple and parameter-efficient adaptation technique that only requires adapting the bias of the output softmax to each particular user of the MT system, either directly or through a factored approximation. Experiments on TED talks in three languages demonstrate improvements in translation accuracy, and better reflection of speaker traits in the target text.
Tasks	Machine Translation
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01817v1
PDF	http://arxiv.org/pdf/1805.01817v1.pdf
PWC	https://paperswithcode.com/paper/extreme-adaptation-for-personalized-neural
Repo
Framework

Interpretable Multi-Objective Reinforcement Learning through Policy Orchestration


Title	Interpretable Multi-Objective Reinforcement Learning through Policy Orchestration
Authors	Ritesh Noothigattu, Djallel Bouneffouf, Nicholas Mattei, Rachita Chandra, Piyush Madan, Kush Varshney, Murray Campbell, Moninder Singh, Francesca Rossi
Abstract	Autonomous cyber-physical agents and systems play an increasingly large role in our lives. To ensure that agents behave in ways aligned with the values of the societies in which they operate, we must develop techniques that allow these agents to not only maximize their reward in an environment, but also to learn and follow the implicit constraints of society. These constraints and norms can come from any number of sources including regulations, business process guidelines, laws, ethical principles, social norms, and moral values. We detail a novel approach that uses inverse reinforcement learning to learn a set of unspecified constraints from demonstrations of the task, and reinforcement learning to learn to maximize the environment rewards. More precisely, we assume that an agent can observe traces of behavior of members of the society but has no access to the explicit set of constraints that give rise to the observed behavior. Inverse reinforcement learning is used to learn such constraints, that are then combined with a possibly orthogonal value function through the use of a contextual bandit-based orchestrator that picks a contextually-appropriate choice between the two policies (constraint-based and environment reward-based) when taking actions. The contextual bandit orchestrator allows the agent to mix policies in novel ways, taking the best actions from either a reward maximizing or constrained policy. In addition, the orchestrator is transparent on which policy is being employed at each time step. We test our algorithms using a Pac-Man domain and show that the agent is able to learn to act optimally, act within the demonstrated constraints, and mix these two functions in complex ways.
Tasks
Published	2018-09-21
URL	http://arxiv.org/abs/1809.08343v1
PDF	http://arxiv.org/pdf/1809.08343v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-multi-objective-reinforcement
Repo
Framework

TrQuery: An Embedding-based Framework for Recommanding SPARQL Queries


Title	TrQuery: An Embedding-based Framework for Recommanding SPARQL Queries
Authors	Lijing Zhang, Xiaowang Zhang, Zhiyong Feng
Abstract	In this paper, we present an embedding-based framework (TrQuery) for recommending solutions of a SPARQL query, including approximate solutions when exact querying solutions are not available due to incompleteness or inconsistencies of real-world RDF data. Within this framework, embedding is applied to score solutions together with edit distance so that we could obtain more fine-grained recommendations than those recommendations via edit distance. For instance, graphs of two querying solutions with a similar structure can be distinguished in our proposed framework while the edit distance depending on structural difference becomes unable. To this end, we propose a novel score model built on vector space generated in embedding system to compute the similarity between an approximate subgraph matching and a whole graph matching. Finally, we evaluate our approach on large RDF datasets DBpedia and YAGO, and experimental results show that TrQuery exhibits an excellent behavior in terms of both effectiveness and efficiency.
Tasks	Graph Matching
Published	2018-06-16
URL	http://arxiv.org/abs/1806.06205v1
PDF	http://arxiv.org/pdf/1806.06205v1.pdf
PWC	https://paperswithcode.com/paper/trquery-an-embedding-based-framework-for
Repo
Framework

Pattern Recognition Approach to Violin Shapes of MIMO database


Title	Pattern Recognition Approach to Violin Shapes of MIMO database
Authors	Thomas Peron, Francisco A. Rodrigues, Luciano da F. Costa
Abstract	Since the landmarks established by the Cremonese school in the 16th century, the history of violin design has been marked by experimentation. While great effort has been invested since the early 19th century by the scientific community on researching violin acoustics, substantially less attention has been given to the statistical characterization of how the violin shape evolved over time. In this paper we study the morphology of violins retrieved from the Musical Instrument Museums Online (MIMO) database – the largest freely accessible platform providing information about instruments held in public museums. From the violin images, we derive a set of measurements that reflect relevant geometrical features of the instruments. The application of Principal Component Analysis (PCA) uncovered similarities between violin makers and their respective copyists, as well as among luthiers belonging to the same family lineage, in the context of historical narrative. Combined with a time-windowed approach, thin plate splines visualizations revealed that the average violin outline has remained mostly stable over time, not adhering to any particular trends of design across different periods in music history.
Tasks
Published	2018-08-08
URL	http://arxiv.org/abs/1808.02848v1
PDF	http://arxiv.org/pdf/1808.02848v1.pdf
PWC	https://paperswithcode.com/paper/pattern-recognition-approach-to-violin-shapes
Repo
Framework

Detecting Satire in the News with Machine Learning


Title	Detecting Satire in the News with Machine Learning
Authors	Andreas Stöckl
Abstract	We built models with Logistic Regression and linear Support Vector Machines on a large dataset consisting of regular news articles and news from satirical websites, and showed that such linear classifiers on a corpus with about 60,000 articles can perform with a precision of 98.7% and a recall of 95.2% on a random test set of the news. On the other hand, when testing the classifier on “publication sources” which are completely unknown during training, only an accuracy of 88.2% and an F1-score of 76.3% are achieved. As another result, we showed that the same algorithm can distinguish between news written by the news agency itself and paid articles from customers. Here the results had an accuracy of 99%.
Tasks
Published	2018-10-01
URL	http://arxiv.org/abs/1810.00593v1
PDF	http://arxiv.org/pdf/1810.00593v1.pdf
PWC	https://paperswithcode.com/paper/detecting-satire-in-the-news-with-machine
Repo
Framework

CrowdCam: Dynamic Region Segmentation


Title	CrowdCam: Dynamic Region Segmentation
Authors	Nir Zarrabi, Shai Avidan, Yael Moses
Abstract	We consider the problem of segmenting dynamic regions in CrowdCam images, where a dynamic region is the projection of a moving 3D object on the image plane. Quite often, these regions are the most interesting parts of an image. CrowdCam images is a set of images of the same dynamic event, captured by a group of non-collaborating users. Almost every event of interest today is captured this way. This new type of images raises the need to develop new algorithms tailored specifically for it. We propose a comprehensive solution to the problem. Our solution combines cues that are based on geometry, appearance and proximity. First, geometric reasoning is used to produce rough score maps that determine, for every pixel, how likely it is to be the projection of a static or dynamic scene point. These maps are noisy because CrowdCam images are usually few and far apart both in space and in time. Then, we use similarity in appearance space and proximity in the image plane to encourage neighboring pixels to be labeled similarly as either static or dynamic. We collected a new, and challenging, data set to evaluate our algorithm. Results show that the success score of our algorithm is nearly double that of the current state of the art approach.
Tasks	Dynamic Region Segmentation
Published	2018-11-28
URL	https://arxiv.org/abs/1811.11455v2
PDF	https://arxiv.org/pdf/1811.11455v2.pdf
PWC	https://paperswithcode.com/paper/crowdcam-dynamic-region-segmentation
Repo
Framework

PatchFCN for Intracranial Hemorrhage Detection


Title	PatchFCN for Intracranial Hemorrhage Detection
Authors	Weicheng Kuo, Christian Häne, Esther Yuh, Pratik Mukherjee, Jitendra Malik
Abstract	This paper studies the problem of detecting and segmenting acute intracranial hemorrhage on head computed tomography (CT) scans. We propose to solve both tasks as a semantic segmentation problem using a patch-based fully convolutional network (PatchFCN). This formulation allows us to accurately localize hemorrhages while bypassing the complexity of object detection. Our system demonstrates competitive performance with a human expert and the state-of-the-art on classification tasks (0.976, 0.966 AUC of ROC on retrospective and prospective test sets) and on segmentation tasks (0.785 pixel AP, 0.766 Dice score), while using much less data and a simpler system. In addition, we conduct a series of controlled experiments to understand “why” PatchFCN outperforms standard FCN. Our studies show that PatchFCN finds a good trade-off between batch diversity and the amount of context during training. These findings may also apply to other medical segmentation tasks.
Tasks	Computed Tomography (CT), Object Detection, Semantic Segmentation
Published	2018-06-08
URL	http://arxiv.org/abs/1806.03265v2
PDF	http://arxiv.org/pdf/1806.03265v2.pdf
PWC	https://paperswithcode.com/paper/patchfcn-for-intracranial-hemorrhage
Repo
Framework

BigDataBench: A Scalable and Unified Big Data and AI Benchmark Suite


Title	BigDataBench: A Scalable and Unified Big Data and AI Benchmark Suite
Authors	Wanling Gao, Jianfeng Zhan, Lei Wang, Chunjie Luo, Daoyi Zheng, Xu Wen, Rui Ren, Chen Zheng, Xiwen He, Hainan Ye, Haoning Tang, Zheng Cao, Shujie Zhang, Jiahui Dai
Abstract	Several fundamental changes in technology indicate domain-specific hardware and software co-design is the only path left. In this context, architecture, system, data management, and machine learning communities pay greater attention to innovative big data and AI algorithms, architecture, and systems. Unfortunately, complexity, diversity, frequently-changed workloads, and rapid evolution of big data and AI systems raise great challenges. First, the traditional benchmarking methodology that creates a new benchmark or proxy for every possible workload is not scalable, or even impossible for Big Data and AI benchmarking. Second, it is prohibitively expensive to tailor the architecture to characteristics of one or more application or even a domain of applications. We consider each big data and AI workload as a pipeline of one or more classes of units of computation performed on different initial or intermediate data inputs, each class of which we call a data motif. On the basis of our previous work that identifies eight data motifs taking up most of the run time of a wide variety of big data and AI workloads, we propose a scalable benchmarking methodology that uses the combination of one or more data motifs—to represent diversity of big data and AI workloads. Following this methodology, we present a unified big data and AI benchmark suite—BigDataBench 4.0, publicly available from~\url{http://prof.ict.ac.cn/BigDataBench}. This unified benchmark suite sheds new light on domain-specific hardware and software co-design: tailoring the system and architecture to characteristics of the unified eight data motifs other than one or more application case by case. Also, for the first time, we comprehensively characterize the CPU pipeline efficiency using the benchmarks of seven workload types in BigDataBench 4.0.
Tasks
Published	2018-02-23
URL	http://arxiv.org/abs/1802.08254v2
PDF	http://arxiv.org/pdf/1802.08254v2.pdf
PWC	https://paperswithcode.com/paper/bigdatabench-a-scalable-and-unified-big-data
Repo
Framework

Binary Classification of Alzheimer Disease using sMRI Imaging modality and Deep Learning


Title	Binary Classification of Alzheimer Disease using sMRI Imaging modality and Deep Learning
Authors	Ahsan Bin Tufail, Qiu-Na Zhang, Yong-Kui Ma
Abstract	Alzheimer’s disease (AD) is an irreversible devastative neurodegenerative disorder associated with progressive impairment of memory and cognitive functions. Its early diagnosis is crucial for the development of possible future treatment option(s). Structural magnetic resonance images (sMRI) plays an important role to help in understanding the anatomical changes related to AD especially in its early stages. Conventional methods require the expertise of domain experts and extract hand-picked features such as gray matter substructures and train a classifier to distinguish AD subjects from healthy subjects. Different from these methods, this paper proposes to construct multiple deep 2D convolutional neural networks (2D-CNNs) to learn the various features from local brain images which are combined to make the final classification for AD diagnosis. The whole brain image was passed through two transfer learning architectures; Inception version 3 and Xception; as well as custom Convolutional Neural Network (CNN) built with the help of separable convolutional layers which can automatically learn the generic features from imaging data for classification. Our study is conducted using cross-sectional T1-weighted structural MRI brain images from Open Access Series of Imaging Studies (OASIS) database to maintain the size and contrast over different MRI scans. Experimental results show that the transfer learning approaches exceed the performance of non-transfer learning based approaches demonstrating the effectiveness of these approaches for the binary AD classification task.
Tasks	Transfer Learning
Published	2018-09-09
URL	https://arxiv.org/abs/1809.06209v2
PDF	https://arxiv.org/pdf/1809.06209v2.pdf
PWC	https://paperswithcode.com/paper/binary-classification-of-alzheimer-disease
Repo
Framework

Evolving Deep Convolutional Neural Networks by Variable-length Particle Swarm Optimization for Image Classification


Title	Evolving Deep Convolutional Neural Networks by Variable-length Particle Swarm Optimization for Image Classification
Authors	Bin Wang, Yanan Sun, Bing Xue, Mengjie Zhang
Abstract	Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but the best architecture of a CNN to solve a specific problem can be extremely complicated and hard to design. This paper focuses on utilising Particle Swarm Optimisation (PSO) to automatically search for the optimal architecture of CNNs without any manual work involved. In order to achieve the goal, three improvements are made based on traditional PSO. First, a novel encoding strategy inspired by computer networks which empowers particle vectors to easily encode CNN layers is proposed; Second, in order to allow the proposed method to learn variable-length CNN architectures, a Disabled layer is designed to hide some dimensions of the particle vector to achieve variable-length particles; Third, since the learning process on large data is slow, partial datasets are randomly picked for the evaluation to dramatically speed it up. The proposed algorithm is examined and compared with 12 existing algorithms including the state-of-art methods on three widely used image classification benchmark datasets. The experimental results show that the proposed algorithm is a strong competitor to the state-of-art algorithms in terms of classification error. This is the first work using PSO for automatically evolving the architectures of CNNs.
Tasks	Image Classification
Published	2018-03-17
URL	http://arxiv.org/abs/1803.06492v1
PDF	http://arxiv.org/pdf/1803.06492v1.pdf
PWC	https://paperswithcode.com/paper/evolving-deep-convolutional-neural-networks-1
Repo
Framework

Weakly-Supervised Deep Learning of Heat Transport via Physics Informed Loss


Title	Weakly-Supervised Deep Learning of Heat Transport via Physics Informed Loss
Authors	Rishi Sharma, Amir Barati Farimani, Joe Gomes, Peter Eastman, Vijay Pande
Abstract	In typical machine learning tasks and applications, it is necessary to obtain or create large labeled datasets in order to to achieve high performance. Unfortunately, large labeled datasets are not always available and can be expensive to source, creating a bottleneck towards more widely applicable machine learning. The paradigm of weak supervision offers an alternative that allows for integration of domain-specific knowledge by enforcing constraints that a correct solution to the learning problem will obey over the output space. In this work, we explore the application of this paradigm to 2-D physical systems governed by non-linear differential equations. We demonstrate that knowledge of the partial differential equations governing a system can be encoded into the loss function of a neural network via an appropriately chosen convolutional kernel. We demonstrate this by showing that the steady-state solution to the 2-D heat equation can be learned directly from initial conditions by a convolutional neural network, in the absence of labeled training data. We also extend recent work in the progressive growing of fully convolutional networks to achieve high accuracy (< 1.5% error) at multiple scales of the heat-flow problem, including at the very large scale (1024x1024). Finally, we demonstrate that this method can be used to speed up exact calculation of the solution to the differential equations via finite difference.
Tasks
Published	2018-07-24
URL	http://arxiv.org/abs/1807.11374v2
PDF	http://arxiv.org/pdf/1807.11374v2.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-deep-learning-of-heat
Repo
Framework

Outline Objects using Deep Reinforcement Learning


Title	Outline Objects using Deep Reinforcement Learning
Authors	Zhenxin Wang, Sayan Sarcar, Jingxin Liu, Yilin Zheng, Xiangshi Ren
Abstract	Image segmentation needs both local boundary position information and global object context information. The performance of the recent state-of-the-art method, fully convolutional networks, reaches a bottleneck due to the neural network limit after balancing between the two types of information simultaneously in an end-to-end training style. To overcome this problem, we divide the semantic image segmentation into temporal subtasks. First, we find a possible pixel position of some object boundary; then trace the boundary at steps within a limited length until the whole object is outlined. We present the first deep reinforcement learning approach to semantic image segmentation, called DeepOutline, which outperforms other algorithms in Coco detection leaderboard in the middle and large size person category in Coco val2017 dataset. Meanwhile, it provides an insight into a divide and conquer way by reinforcement learning on computer vision problems.
Tasks	Semantic Segmentation
Published	2018-04-10
URL	http://arxiv.org/abs/1804.04603v2
PDF	http://arxiv.org/pdf/1804.04603v2.pdf
PWC	https://paperswithcode.com/paper/outline-objects-using-deep-reinforcement
Repo
Framework

From Benedict Cumberbatch to Sherlock Holmes: Character Identification in TV series without a Script


Title	From Benedict Cumberbatch to Sherlock Holmes: Character Identification in TV series without a Script
Authors	Arsha Nagrani, Andrew Zisserman
Abstract	The goal of this paper is the automatic identification of characters in TV and feature film material. In contrast to standard approaches to this task, which rely on the weak supervision afforded by transcripts and subtitles, we propose a new method requiring only a cast list. This list is used to obtain images of actors from freely available sources on the web, providing a form of partial supervision for this task. In using images of actors to recognize characters, we make the following three contributions: (i) We demonstrate that an automated semi-supervised learning approach is able to adapt from the actor’s face to the character’s face, including the face context of the hair; (ii) By building voice models for every character, we provide a bridge between frontal faces (for which there is plenty of actor-level supervision) and profile (for which there is very little or none); and (iii) by combining face context and speaker identification, we are able to identify characters with partially occluded faces and extreme facial poses. Results are presented on the TV series ‘Sherlock’ and the feature film ‘Casablanca’. We achieve the state-of-the-art on the Casablanca benchmark, surpassing previous methods that have used the stronger supervision available from transcripts.
Tasks	Speaker Identification
Published	2018-01-31
URL	http://arxiv.org/abs/1801.10442v1
PDF	http://arxiv.org/pdf/1801.10442v1.pdf
PWC	https://paperswithcode.com/paper/from-benedict-cumberbatch-to-sherlock-holmes
Repo
Framework

A Simple Change Comparison Method for Image Sequences Based on Uncertainty Coefficient


Title	A Simple Change Comparison Method for Image Sequences Based on Uncertainty Coefficient
Authors	Ruzhang Zhao, Yajun Fang, Berthold K. P. Horn
Abstract	For identification of change information in image sequences, most studies focus on change detection in one image sequence, while few studies have considered the change level comparison between two different image sequences. Moreover, most studies require the detection of image information in details, for example, object detection. Based on Uncertainty Coefficient(UC), this paper proposes an innovative method CCUC for change comparison between two image sequences. The proposed method is computationally efficient and simple to implement. The change comparison stems from video monitoring system. The limited number of provided screens and a large number of monitoring cameras require the videos or image sequences ordered by change level. We demonstrate this new method by applying it on two publicly available image sequences. The results are able to show the method can distinguish the different change level for sequences.
Tasks	Object Detection
Published	2018-10-14
URL	http://arxiv.org/abs/1810.06055v1
PDF	http://arxiv.org/pdf/1810.06055v1.pdf
PWC	https://paperswithcode.com/paper/a-simple-change-comparison-method-for-image
Repo
Framework

Recognition in Terra Incognita


Title	Recognition in Terra Incognita
Authors	Sara Beery, Grant van Horn, Pietro Perona
Abstract	It is desirable for detection and classification algorithms to generalize to unfamiliar environments, but suitable benchmarks for quantitatively studying this phenomenon are not yet available. We present a dataset designed to measure recognition generalization to novel environments. The images in our dataset are harvested from twenty camera traps deployed to monitor animal populations. Camera traps are fixed at one location, hence the background changes little across images; capture is triggered automatically, hence there is no human bias. The challenge is learning recognition in a handful of locations, and generalizing animal detection and classification to new locations where no training data is available. In our experiments state-of-the-art algorithms show excellent performance when tested at the same location where they were trained. However, we find that generalization to new locations is poor, especially for classification systems.
Tasks
Published	2018-07-13
URL	http://arxiv.org/abs/1807.04975v2
PDF	http://arxiv.org/pdf/1807.04975v2.pdf
PWC	https://paperswithcode.com/paper/recognition-in-terra-incognita
Repo
Framework