Paper Group ANR 888
Doubly Attentive Transformer Machine Translation. Prophit: Causal inverse classification for multiple continuously valued treatment policies. ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension. Interactions as Social Practices: towards a formalization. Soft Locality Preserving Map (SLPM) for Facial Expression Recog …
Doubly Attentive Transformer Machine Translation
Title | Doubly Attentive Transformer Machine Translation |
Authors | Hasan Sait Arslan, Mark Fishel, Gholamreza Anbarjafari |
Abstract | In this paper a doubly attentive transformer machine translation model (DATNMT) is presented in which a doubly-attentive transformer decoder normally joins spatial visual features obtained via pretrained convolutional neural networks, conquering any gap between image captioning and translation. In this framework, the transformer decoder figures out how to take care of source-language words and parts of an image freely by methods for two separate attention components in an Enhanced Multi-Head Attention Layer of doubly attentive transformer, as it generates words in the target language. We find that the proposed model can effectively exploit not just the scarce multimodal machine translation data, but also large general-domain text-only machine translation corpora, or image-text image captioning corpora. The experimental results show that the proposed doubly-attentive transformer-decoder performs better than a single-decoder transformer model, and gives the state-of-the-art results in the English-German multimodal machine translation task. |
Tasks | Image Captioning, Machine Translation, Multimodal Machine Translation |
Published | 2018-07-30 |
URL | http://arxiv.org/abs/1807.11605v1 |
http://arxiv.org/pdf/1807.11605v1.pdf | |
PWC | https://paperswithcode.com/paper/doubly-attentive-transformer-machine |
Repo | |
Framework | |
Prophit: Causal inverse classification for multiple continuously valued treatment policies
Title | Prophit: Causal inverse classification for multiple continuously valued treatment policies |
Authors | Michael T. Lash, Qihang Lin, W. Nick Street |
Abstract | Inverse classification uses an induced classifier as a queryable oracle to guide test instances towards a preferred posterior class label. The result produced from the process is a set of instance-specific feature perturbations, or recommendations, that optimally improve the probability of the class label. In this work, we adopt a causal approach to inverse classification, eliciting treatment policies (i.e., feature perturbations) for models induced with causal properties. In so doing, we solve a long-standing problem of eliciting multiple, continuously valued treatment policies, using an updated framework and corresponding set of assumptions, which we term the inverse classification potential outcomes framework (ICPOF), along with a new measure, referred to as the individual future estimated effects ($i$FEE). We also develop the approximate propensity score (APS), based on Gaussian processes, to weight treatments, much like the inverse propensity score weighting used in past works. We demonstrate the viability of our methods on student performance. |
Tasks | Gaussian Processes |
Published | 2018-02-14 |
URL | http://arxiv.org/abs/1802.04918v1 |
http://arxiv.org/pdf/1802.04918v1.pdf | |
PWC | https://paperswithcode.com/paper/prophit-causal-inverse-classification-for |
Repo | |
Framework | |
ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension
Title | ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension |
Authors | Sheng Zhang, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Kevin Duh, Benjamin Van Durme |
Abstract | We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning. Experiments on this dataset demonstrate that the performance of state-of-the-art MRC systems fall far behind human performance. ReCoRD represents a challenge for future research to bridge the gap between human and machine commonsense reading comprehension. ReCoRD is available at http://nlp.jhu.edu/record. |
Tasks | Machine Reading Comprehension, Reading Comprehension |
Published | 2018-10-30 |
URL | http://arxiv.org/abs/1810.12885v1 |
http://arxiv.org/pdf/1810.12885v1.pdf | |
PWC | https://paperswithcode.com/paper/record-bridging-the-gap-between-human-and |
Repo | |
Framework | |
Interactions as Social Practices: towards a formalization
Title | Interactions as Social Practices: towards a formalization |
Authors | Frank Dignum |
Abstract | Multi-agent models are a suitable starting point to model complex social interactions. However, as the complexity of the systems increase, we argue that novel modeling approaches are needed that can deal with inter-dependencies at different levels of society, where many heterogeneous parties (software agents, robots, humans) are interacting and reacting to each other. In this paper, we present a formalization of a social framework for agents based in the concept of Social Practices as high level specifications of normal (expected) behavior in a given social context. We argue that social practices facilitate the practical reasoning of agents in standard social interactions. |
Tasks | |
Published | 2018-09-24 |
URL | http://arxiv.org/abs/1809.08751v1 |
http://arxiv.org/pdf/1809.08751v1.pdf | |
PWC | https://paperswithcode.com/paper/interactions-as-social-practices-towards-a |
Repo | |
Framework | |
Soft Locality Preserving Map (SLPM) for Facial Expression Recognition
Title | Soft Locality Preserving Map (SLPM) for Facial Expression Recognition |
Authors | Cigdem Turan, Kin-Man Lam, Xiangjian He |
Abstract | For image recognition, an extensive number of methods have been proposed to overcome the high-dimensionality problem of feature vectors being used. These methods vary from unsupervised to supervised, and from statistics to graph-theory based. In this paper, the most popular and the state-of-the-art methods for dimensionality reduction are firstly reviewed, and then a new and more efficient manifold-learning method, named Soft Locality Preserving Map (SLPM), is presented. Furthermore, feature generation and sample selection are proposed to achieve better manifold learning. SLPM is a graph-based subspace-learning method, with the use of k-neighbourhood information and the class information. The key feature of SLPM is that it aims to control the level of spread of the different classes, because the spread of the classes in the underlying manifold is closely connected to the generalizability of the learned subspace. Our proposed manifold-learning method can be applied to various pattern recognition applications, and we evaluate its performances on facial expression recognition. Experiments on databases, such as the Bahcesehir University Multilingual Affective Face Database (BAUM-2), the Extended Cohn-Kanade (CK+) Database, the Japanese Female Facial Expression (JAFFE) Database, and the Taiwanese Facial Expression Image Database (TFEID), show that SLPM can effectively reduce the dimensionality of the feature vectors and enhance the discriminative power of the extracted features for expression recognition. Furthermore, the proposed feature-generation method can improve the generalizability of the underlying manifolds for facial expression recognition. |
Tasks | Dimensionality Reduction, Facial Expression Recognition |
Published | 2018-01-11 |
URL | http://arxiv.org/abs/1801.03754v1 |
http://arxiv.org/pdf/1801.03754v1.pdf | |
PWC | https://paperswithcode.com/paper/soft-locality-preserving-map-slpm-for-facial |
Repo | |
Framework | |
Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms
Title | Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms |
Authors | Jianyu Wang, Gauri Joshi |
Abstract | Communication-efficient SGD algorithms, which allow nodes to perform local updates and periodically synchronize local models, are highly effective in improving the speed and scalability of distributed SGD. However, a rigorous convergence analysis and comparative study of different communication-reduction strategies remains a largely open problem. This paper presents a unified framework called Cooperative SGD that subsumes existing communication-efficient SGD algorithms such as periodic-averaging, elastic-averaging and decentralized SGD. By analyzing Cooperative SGD, we provide novel convergence guarantees for existing algorithms. Moreover, this framework enables us to design new communication-efficient SGD algorithms that strike the best balance between reducing communication overhead and achieving fast error convergence with low error floor. |
Tasks | |
Published | 2018-08-22 |
URL | http://arxiv.org/abs/1808.07576v3 |
http://arxiv.org/pdf/1808.07576v3.pdf | |
PWC | https://paperswithcode.com/paper/cooperative-sgd-a-unified-framework-for-the |
Repo | |
Framework | |
Resilient Computing with Reinforcement Learning on a Dynamical System: Case Study in Sorting
Title | Resilient Computing with Reinforcement Learning on a Dynamical System: Case Study in Sorting |
Authors | Aleksandra Faust, James B. Aimone, Conrad D. James, Lydia Tapia |
Abstract | Robots and autonomous agents often complete goal-based tasks with limited resources, relying on imperfect models and sensor measurements. In particular, reinforcement learning (RL) and feedback control can be used to help a robot achieve a goal. Taking advantage of this body of work, this paper formulates general computation as a feedback-control problem, which allows the agent to autonomously overcome some limitations of standard procedural language programming: resilience to errors and early program termination. Our formulation considers computation to be trajectory generation in the program’s variable space. The computing then becomes a sequential decision making problem, solved with reinforcement learning (RL), and analyzed with Lyapunov stability theory to assess the agent’s resilience and progression to the goal. We do this through a case study on a quintessential computer science problem, array sorting. Evaluations show that our RL sorting agent makes steady progress to an asymptotically stable goal, is resilient to faulty components, and performs less array manipulations than traditional Quicksort and Bubble sort. |
Tasks | Decision Making |
Published | 2018-09-25 |
URL | http://arxiv.org/abs/1809.09261v1 |
http://arxiv.org/pdf/1809.09261v1.pdf | |
PWC | https://paperswithcode.com/paper/resilient-computing-with-reinforcement |
Repo | |
Framework | |
Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions
Title | Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions |
Authors | Stephan Baier, Yunpu Ma, Volker Tresp |
Abstract | Structured scene descriptions of images are useful for the automatic processing and querying of large image databases. We show how the combination of a semantic and a visual statistical model can improve on the task of mapping images to their associated scene description. In this paper we consider scene descriptions which are represented as a set of triples (subject, predicate, object), where each triple consists of a pair of visual objects, which appear in the image, and the relationship between them (e.g. man-riding-elephant, man-wearing-hat). We combine a standard visual model for object detection, based on convolutional neural networks, with a latent variable model for link prediction. We apply multiple state-of-the-art link prediction methods and compare their capability for visual relationship detection. One of the main advantages of link prediction methods is that they can also generalize to triples, which have never been observed in the training data. Our experimental results on the recently published Stanford Visual Relationship dataset, a challenging real world dataset, show that the integration of a semantic model using link prediction methods can significantly improve the results for visual relationship detection. Our combined approach achieves superior performance compared to the state-of-the-art method from the Stanford computer vision group. |
Tasks | Link Prediction, Object Detection |
Published | 2018-09-01 |
URL | http://arxiv.org/abs/1809.00204v1 |
http://arxiv.org/pdf/1809.00204v1.pdf | |
PWC | https://paperswithcode.com/paper/improving-visual-relationship-detection-using |
Repo | |
Framework | |
Scalable Bottom-up Subspace Clustering using FP-Trees for High Dimensional Data
Title | Scalable Bottom-up Subspace Clustering using FP-Trees for High Dimensional Data |
Authors | Minh Tuan Doan, Jianzhong Qi, Sutharshan Rajasegarar, Christopher Leckie |
Abstract | Subspace clustering aims to find groups of similar objects (clusters) that exist in lower dimensional subspaces from a high dimensional dataset. It has a wide range of applications, such as analysing high dimensional sensor data or DNA sequences. However, existing algorithms have limitations in finding clusters in non-disjoint subspaces and scaling to large data, which impinge their applicability in areas such as bioinformatics and the Internet of Things. We aim to address such limitations by proposing a subspace clustering algorithm using a bottom-up strategy. Our algorithm first searches for base clusters in low dimensional subspaces. It then forms clusters in higher-dimensional subspaces using these base clusters, which we formulate as a frequent pattern mining problem. This formulation enables efficient search for clusters in higher-dimensional subspaces, which is done using FP-trees. The proposed algorithm is evaluated against traditional bottom-up clustering algorithms and state-of-the-art subspace clustering algorithms. The experimental results show that the proposed algorithm produces clusters with high accuracy, and scales well to large volumes of data. We also demonstrate the algorithm’s performance using real-life data, including ten genomic datasets and a car parking occupancy dataset. |
Tasks | |
Published | 2018-11-07 |
URL | http://arxiv.org/abs/1811.02722v1 |
http://arxiv.org/pdf/1811.02722v1.pdf | |
PWC | https://paperswithcode.com/paper/scalable-bottom-up-subspace-clustering-using |
Repo | |
Framework | |
Lesion Analysis and Diagnosis with Mask-RCNN
Title | Lesion Analysis and Diagnosis with Mask-RCNN |
Authors | Andrey Sorokin |
Abstract | This project applies Mask R-CNN method to ISIC 2018 challenge tasks: lesion boundary segmentation (task1), lesion attributes detection (task 2), lesion diagnosis (task 3), a solution to the latter is using a trained model for task 1 and a simple voting procedure. |
Tasks | |
Published | 2018-07-10 |
URL | http://arxiv.org/abs/1807.05979v2 |
http://arxiv.org/pdf/1807.05979v2.pdf | |
PWC | https://paperswithcode.com/paper/lesion-analysis-and-diagnosis-with-mask-rcnn |
Repo | |
Framework | |
Stochastic Dynamics for Video Infilling
Title | Stochastic Dynamics for Video Infilling |
Authors | Qiangeng Xu, Hanwang Zhang, Weiyue Wang, Peter N. Belhumeur, Ulrich Neumann |
Abstract | In this paper, we introduce a stochastic dynamics video infilling (SDVI) framework to generate frames between long intervals in a video. Our task differs from video interpolation which aims to produce transitional frames for a short interval between every two frames and increase the temporal resolution. Our task, namely video infilling, however, aims to infill long intervals with plausible frame sequences. Our framework models the infilling as a constrained stochastic generation process and sequentially samples dynamics from the inferred distribution. SDVI consists of two parts: (1) a bi-directional constraint propagation module to guarantee the spatial-temporal coherence among frames, (2) a stochastic sampling process to generate dynamics from the inferred distributions. Experimental results show that SDVI can generate clear frame sequences with varying contents. Moreover, motions in the generated sequence are realistic and able to transfer smoothly from the given start frame to the terminal frame. Our project site is https://xharlie.github.io/projects/project_sites/SDVI/video_results.html |
Tasks | |
Published | 2018-09-01 |
URL | https://arxiv.org/abs/1809.00263v5 |
https://arxiv.org/pdf/1809.00263v5.pdf | |
PWC | https://paperswithcode.com/paper/stochastic-dynamics-for-video-infilling |
Repo | |
Framework | |
Amobee at SemEval-2018 Task 1: GRU Neural Network with a CNN Attention Mechanism for Sentiment Classification
Title | Amobee at SemEval-2018 Task 1: GRU Neural Network with a CNN Attention Mechanism for Sentiment Classification |
Authors | Alon Rozental, Daniel Fleischer |
Abstract | This paper describes the participation of Amobee in the shared sentiment analysis task at SemEval 2018. We participated in all the English sub-tasks and the Spanish valence tasks. Our system consists of three parts: training task-specific word embeddings, training a model consisting of gated-recurrent-units (GRU) with a convolution neural network (CNN) attention mechanism and training stacking-based ensembles for each of the sub-tasks. Our algorithm reached 3rd and 1st places in the valence ordinal classification sub-tasks in English and Spanish, respectively. |
Tasks | Sentiment Analysis, Word Embeddings |
Published | 2018-04-12 |
URL | http://arxiv.org/abs/1804.04380v1 |
http://arxiv.org/pdf/1804.04380v1.pdf | |
PWC | https://paperswithcode.com/paper/amobee-at-semeval-2018-task-1-gru-neural |
Repo | |
Framework | |
Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography
Title | Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography |
Authors | Chang Liu, Xiangrui Zeng, Kaiwen Wang, Qiang Guo, Min Xu |
Abstract | Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells. For systematic recognition and recovery of macromolecular structures captured by CECT, methods for several important tasks such as subtomogram classification and semantic segmentation have been developed. However, the recognition and recovery of macromolecular structures are still very difficult due to high molecular structural diversity, crowding molecular environment, and the imaging limitations of CECT. In this paper, we propose a novel multi-task 3D convolutional neural network model for simultaneous classification, segmentation, and coarse structural recovery of macromolecules of interest in subtomograms. In our model, the learned image features of one task are shared and thereby mutually reinforce the learning of other tasks. Evaluated on realistically simulated and experimental CECT data, our multi-task learning model outperformed all single-task learning methods for classification and segmentation. In addition, we demonstrate that our model can generalize to discover, segment and recover novel structures that do not exist in the training data. |
Tasks | Multi-Task Learning, Semantic Segmentation |
Published | 2018-05-16 |
URL | http://arxiv.org/abs/1805.06332v1 |
http://arxiv.org/pdf/1805.06332v1.pdf | |
PWC | https://paperswithcode.com/paper/multi-task-learning-for-macromolecule |
Repo | |
Framework | |
A General Approach to Domain Adaptation with Applications in Astronomy
Title | A General Approach to Domain Adaptation with Applications in Astronomy |
Authors | Ricardo Vilalta, Kinjal Dhar Gupta, Dainis Boumber, Mikhail M. Meskhi |
Abstract | The ability to build a model on a source task and subsequently adapt such model on a new target task is a pervasive need in many astronomical applications. The problem is generally known as transfer learning in machine learning, where domain adaptation is a popular scenario. An example is to build a predictive model on spectroscopic data to identify Supernovae IA, while subsequently trying to adapt such model on photometric data. In this paper we propose a new general approach to domain adaptation that does not rely on the proximity of source and target distributions. Instead we simply assume a strong similarity in model complexity across domains, and use active learning to mitigate the dependency on source examples. Our work leads to a new formulation for the likelihood as a function of empirical error using a theoretical learning bound; the result is a novel mapping from generalization error to a likelihood estimation. Results using two real astronomical problems, Supernova Ia classification and identification of Mars landforms, show two main advantages with our approach: increased accuracy performance and substantial savings in computational cost. |
Tasks | Active Learning, Domain Adaptation, Transfer Learning |
Published | 2018-12-20 |
URL | http://arxiv.org/abs/1812.08839v1 |
http://arxiv.org/pdf/1812.08839v1.pdf | |
PWC | https://paperswithcode.com/paper/a-general-approach-to-domain-adaptation-with |
Repo | |
Framework | |
Evaluating and Characterizing Incremental Learning from Non-Stationary Data
Title | Evaluating and Characterizing Incremental Learning from Non-Stationary Data |
Authors | Alejandro Cervantes, Christian Gagné, Pedro Isasi, Marc Parizeau |
Abstract | Incremental learning from non-stationary data poses special challenges to the field of machine learning. Although new algorithms have been developed for this, assessment of results and comparison of behaviors are still open problems, mainly because evaluation metrics, adapted from more traditional tasks, can be ineffective in this context. Overall, there is a lack of common testing practices. This paper thus presents a testbed for incremental non-stationary learning algorithms, based on specially designed synthetic datasets. Also, test results are reported for some well-known algorithms to show that the proposed methodology is effective at characterizing their strengths and weaknesses. It is expected that this methodology will provide a common basis for evaluating future contributions in the field. |
Tasks | |
Published | 2018-06-18 |
URL | http://arxiv.org/abs/1806.06610v1 |
http://arxiv.org/pdf/1806.06610v1.pdf | |
PWC | https://paperswithcode.com/paper/evaluating-and-characterizing-incremental |
Repo | |
Framework | |