Paper Group ANR 694
Translational Motion Compensation for Soft Tissue Velocity Images. A general system of differential equations to model first order adaptive algorithms. Embedding Models for Episodic Knowledge Graphs. Knowledge-Based Distant Regularization in Learning Probabilistic Models. Mind Your Language: Abuse and Offense Detection for Code-Switched Languages. …
Translational Motion Compensation for Soft Tissue Velocity Images
| Title | Translational Motion Compensation for Soft Tissue Velocity Images |
| Authors | Christina Koutsoumpa, Jennifer Keegan, David Firmin, Guang-Zhong Yang, Duncan Gillies |
| Abstract | Purpose: Advancements in MRI Tissue Phase Velocity Mapping (TPM) allow for the acquisition of higher quality velocity cardiac images providing better assessment of regional myocardial deformation for accurate disease diagnosis, pre-operative planning and post-operative patient surveillance. Translation of TPM velocities from the scanner’s reference coordinate system to the regional cardiac coordinate system requires decoupling of translational motion and motion due to myocardial deformation. Despite existing techniques for respiratory motion compensation in TPM, there is still a remaining translational velocity component due to the global motion of the beating heart. To compensate for translational motion in cardiac TPM, we propose an image-processing method, which we have evaluated on synthetic data and applied on in vivo TPM data. Methods: Translational motion is estimated from a suitable region of velocities automatically defined in the left-ventricular volume. The region is generated by dilating the medial axis of myocardial masks in each slice and the translational velocity is estimated by integration in this region. The method was evaluated on synthetic data and in vivo data corrupted with a translational velocity component (200% of the maximum measured velocity). Accuracy and robustness were examined and the method was applied on 10 in vivo datasets. Results: The results from synthetic and in vivo corrupted data show excellent performance with an estimation error less than 0.3% and high robustness in both cases. The effectiveness of the method is confirmed with visual observation of results from the 10 datasets. Conclusion: The proposed method is accurate and suitable for translational motion correction of the left ventricular velocity fields. The current method for translational motion compensation could be applied to any annular contracting (tissue) structure. |
| Tasks | Motion Compensation |
| Published | 2018-08-20 |
| URL | http://arxiv.org/abs/1808.06469v1 |
| http://arxiv.org/pdf/1808.06469v1.pdf | |
| PWC | https://paperswithcode.com/paper/translational-motion-compensation-for-soft |
| Repo | |
| Framework | |
A general system of differential equations to model first order adaptive algorithms
| Title | A general system of differential equations to model first order adaptive algorithms |
| Authors | André Belotto da Silva, Maxime Gazeau |
| Abstract | First order optimization algorithms play a major role in large scale machine learning. A new class of methods, called adaptive algorithms, were recently introduced to adjust iteratively the learning rate for each coordinate. Despite great practical success in deep learning, their behavior and performance on more general loss functions are not well understood. In this paper, we derive a non-autonomous system of differential equations, which is the continuous time limit of adaptive optimization methods. We prove global well-posedness of the system and we investigate the numerical time convergence of its forward Euler approximation. We study, furthermore, the convergence of its trajectories and give conditions under which the differential system, underlying all adaptive algorithms, is suitable for optimization. We discuss convergence to a critical point in the non-convex case and give conditions for the dynamics to avoid saddle points and local maxima. For convex and deterministic loss function, we introduce a suitable Lyapunov functional which allow us to study its rate of convergence. Several other properties of both the continuous and discrete systems are briefly discussed. The differential system studied in the paper is general enough to encompass many other classical algorithms (such as Heavy ball and Nesterov’s accelerated method) and allow us to recover several known results for these algorithms. |
| Tasks | |
| Published | 2018-10-31 |
| URL | https://arxiv.org/abs/1810.13108v2 |
| https://arxiv.org/pdf/1810.13108v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-system-of-differential-equations-to |
| Repo | |
| Framework | |
Embedding Models for Episodic Knowledge Graphs
| Title | Embedding Models for Episodic Knowledge Graphs |
| Authors | Yunpu Ma, Volker Tresp, Erik Daxberger |
| Abstract | In recent years a number of large-scale triple-oriented knowledge graphs have been generated and various models have been proposed to perform learning in those graphs. Most knowledge graphs are static and reflect the world in its current state. In reality, of course, the state of the world is changing: a healthy person becomes diagnosed with a disease and a new president is inaugurated. In this paper, we extend models for static knowledge graphs to temporal knowledge graphs. This enables us to store episodic data and to generalize to new facts (inductive learning). We generalize leading learning models for static knowledge graphs (i.e., Tucker, RESCAL, HolE, ComplEx, DistMult) to temporal knowledge graphs. In particular, we introduce a new tensor model, ConT, with superior generalization performance. The performances of all proposed models are analyzed on two different datasets: the Global Database of Events, Language, and Tone (GDELT) and the database for Integrated Conflict Early Warning System (ICEWS). We argue that temporal knowledge graph embeddings might be models also for cognitive episodic memory (facts we remember and can recollect) and that a semantic memory (current facts we know) can be generated from episodic memory by a marginalization operation. We validate this episodic-to-semantic projection hypothesis with the ICEWS dataset. |
| Tasks | Knowledge Graph Embeddings, Knowledge Graphs |
| Published | 2018-06-30 |
| URL | http://arxiv.org/abs/1807.00228v2 |
| http://arxiv.org/pdf/1807.00228v2.pdf | |
| PWC | https://paperswithcode.com/paper/embedding-models-for-episodic-knowledge |
| Repo | |
| Framework | |
Knowledge-Based Distant Regularization in Learning Probabilistic Models
| Title | Knowledge-Based Distant Regularization in Learning Probabilistic Models |
| Authors | Naoya Takeishi, Kosuke Akimoto |
| Abstract | Exploiting the appropriate inductive bias based on the knowledge of data is essential for achieving good performance in statistical machine learning. In practice, however, the domain knowledge of interest often provides information on the relationship of data attributes only distantly, which hinders direct utilization of such domain knowledge in popular regularization methods. In this paper, we propose the knowledge-based distant regularization framework, in which we utilize the distant information encoded in a knowledge graph for regularization of probabilistic model estimation. In particular, we propose to impose prior distributions on model parameters specified by knowledge graph embeddings. As an instance of the proposed framework, we present the factor analysis model with the knowledge-based distant regularization. We show the results of preliminary experiments on the improvement of the generalization capability of such model. |
| Tasks | Knowledge Graph Embeddings |
| Published | 2018-06-29 |
| URL | http://arxiv.org/abs/1806.11332v1 |
| http://arxiv.org/pdf/1806.11332v1.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-based-distant-regularization-in |
| Repo | |
| Framework | |
Mind Your Language: Abuse and Offense Detection for Code-Switched Languages
| Title | Mind Your Language: Abuse and Offense Detection for Code-Switched Languages |
| Authors | Raghav Kapoor, Yaman Kumar, Kshitij Rajput, Rajiv Ratn Shah, Ponnurangam Kumaraguru, Roger Zimmermann |
| Abstract | In multilingual societies like the Indian subcontinent, use of code-switched languages is much popular and convenient for the users. In this paper, we study offense and abuse detection in the code-switched pair of Hindi and English (i.e. Hinglish), the pair that is the most spoken. The task is made difficult due to non-fixed grammar, vocabulary, semantics and spellings of Hinglish language. We apply transfer learning and make a LSTM based model for hate speech classification. This model surpasses the performance shown by the current best models to establish itself as the state-of-the-art in the unexplored domain of Hinglish offensive text classification.We also release our model and the embeddings trained for research purposes |
| Tasks | Abuse Detection, Transfer Learning |
| Published | 2018-09-23 |
| URL | http://arxiv.org/abs/1809.08652v1 |
| http://arxiv.org/pdf/1809.08652v1.pdf | |
| PWC | https://paperswithcode.com/paper/mind-your-language-abuse-and-offense |
| Repo | |
| Framework | |
Characterization of Visual Object Representations in Rat Primary Visual Cortex
| Title | Characterization of Visual Object Representations in Rat Primary Visual Cortex |
| Authors | Sebastiano Vascon, Ylenia Parin, Eis Annavini, Mattia D’Andola, Davide Zoccolan, Marcello Pelillo |
| Abstract | For most animal species, quick and reliable identification of visual objects is critical for survival. This applies also to rodents, which, in recent years, have become increasingly popular models of visual functions. For this reason in this work we analyzed how various properties of visual objects are represented in rat primary visual cortex (V1). The analysis has been carried out through supervised (classification) and unsupervised (clustering) learning methods. We assessed quantitatively the discrimination capabilities of V1 neurons by demonstrating how photometric properties (luminosity and object position in the scene) can be derived directly from the neuronal responses. |
| Tasks | |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.01193v1 |
| http://arxiv.org/pdf/1810.01193v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterization-of-visual-object |
| Repo | |
| Framework | |
Deep Face Quality Assessment
| Title | Deep Face Quality Assessment |
| Authors | Vishal Agarwal |
| Abstract | Face image quality is an important factor in facial recognition systems as its verification and recognition accuracy is highly dependent on the quality of image presented. Rejecting low quality images can significantly increase the accuracy of any facial recognition system. In this project, a simple approach is presented to train a deep convolutional neural network to perform end-to-end face image quality assessment. The work is done in 2 stages : First, generation of quality score label and secondly, training a deep convolutional neural network in a supervised manner to predict quality score between 0 and 1. The generation of quality labels is done by comparing the face image with a template of best quality images and then evaluating the normalized score based on the similarity. |
| Tasks | Image Quality Assessment |
| Published | 2018-11-11 |
| URL | http://arxiv.org/abs/1811.04346v1 |
| http://arxiv.org/pdf/1811.04346v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-face-quality-assessment |
| Repo | |
| Framework | |
Towards Verifying Semantic Roles Co-occurrence
| Title | Towards Verifying Semantic Roles Co-occurrence |
| Authors | Aliaksandr Huminski, Hao Zhang, Gangeshwar Krishnamurthy |
| Abstract | Semantic role theory considers roles as a small universal set of unanalyzed entities. It means that formally there are no restrictions on role combinations. We argue that the semantic roles co-occur in verb representations. It means that there are hidden restrictions on role combinations. To demonstrate that a practical and evidence-based approach has been built on in-depth analysis of the largest verb database VerbNet. The consequences of this approach are considered. |
| Tasks | |
| Published | 2018-10-09 |
| URL | http://arxiv.org/abs/1810.03875v1 |
| http://arxiv.org/pdf/1810.03875v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-verifying-semantic-roles-co |
| Repo | |
| Framework | |
Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
| Title | Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting |
| Authors | Hippolyt Ritter, Aleksandar Botev, David Barber |
| Abstract | We introduce the Kronecker factored online Laplace approximation for overcoming catastrophic forgetting in neural networks. The method is grounded in a Bayesian online learning framework, where we recursively approximate the posterior after every task with a Gaussian, leading to a quadratic penalty on changes to the weights. The Laplace approximation requires calculating the Hessian around a mode, which is typically intractable for modern architectures. In order to make our method scalable, we leverage recent block-diagonal Kronecker factored approximations to the curvature. Our algorithm achieves over 90% test accuracy across a sequence of 50 instantiations of the permuted MNIST dataset, substantially outperforming related methods for overcoming catastrophic forgetting. |
| Tasks | |
| Published | 2018-05-20 |
| URL | http://arxiv.org/abs/1805.07810v1 |
| http://arxiv.org/pdf/1805.07810v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-structured-laplace-approximations-for |
| Repo | |
| Framework | |
KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings
| Title | KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings |
| Authors | Yuyu Zhang, Hanjun Dai, Kamil Toraman, Le Song |
| Abstract | The AI2 Reasoning Challenge (ARC), a new benchmark dataset for question answering (QA) has been recently released. ARC only contains natural science questions authored for human exams, which are hard to answer and require advanced logic reasoning. On the ARC Challenge Set, existing state-of-the-art QA systems fail to significantly outperform random baseline, reflecting the difficult nature of this task. In this paper, we propose a novel framework for answering science exam questions, which mimics human solving process in an open-book exam. To address the reasoning challenge, we construct contextual knowledge graphs respectively for the question itself and supporting sentences. Our model learns to reason with neural embeddings of both knowledge graphs. Experiments on the ARC Challenge Set show that our model outperforms the previous state-of-the-art QA systems. |
| Tasks | Knowledge Graph Embeddings, Knowledge Graphs, Question Answering |
| Published | 2018-05-31 |
| URL | http://arxiv.org/abs/1805.12393v1 |
| http://arxiv.org/pdf/1805.12393v1.pdf | |
| PWC | https://paperswithcode.com/paper/kg2-learning-to-reason-science-exam-questions |
| Repo | |
| Framework | |
Sheep identity recognition, age and weight estimation datasets
| Title | Sheep identity recognition, age and weight estimation datasets |
| Authors | Aya Salama Abdelhady, Aboul Ella Hassanenin, Aly Fahmy |
| Abstract | Increased interest of scientists, producers and consumers in sheep identification has been stimulated by the dramatic increase in population and the urge to increase productivity. The world population is expected to exceed 9.6 million in 2050. For this reason, awareness is raised towards the necessity of effective livestock production. Sheep is considered as one of the main of food resources. Most of the research now is directed towards developing real time applications that facilitate sheep identification for breed management and gathering related information like weight and age. Weight and age are key matrices in assessing the effectiveness of production. For this reason, visual analysis proved recently its significant success over other approaches. Visual analysis techniques need enough images for testing and study completion. For this reason, collecting sheep images database is a vital step to fulfill such objective. We provide here datasets for testing and comparing such algorithms which are under development. Our collected dataset consists of 416 color images for different features of sheep in different postures. Images were collected fifty two sheep at a range of year from three months to six years. For each sheep, two images were captured for both sides of the body, two images for both sides of the face, one image from the top view, one image for the hip and one image for the teeth. The collected images cover different illumination, quality levels and angle of rotation. The allocated data set can be used to test sheep identification, weigh estimation, and age detection algorithms. Such algorithms are crucial for disease management, animal assessment and ownership. |
| Tasks | |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.04017v1 |
| http://arxiv.org/pdf/1806.04017v1.pdf | |
| PWC | https://paperswithcode.com/paper/sheep-identity-recognition-age-and-weight |
| Repo | |
| Framework | |
Optimizing Sponsored Search Ranking Strategy by Deep Reinforcement Learning
| Title | Optimizing Sponsored Search Ranking Strategy by Deep Reinforcement Learning |
| Authors | Li He, Liang Wang, Kaipeng Liu, Bo Wu, Weinan Zhang |
| Abstract | Sponsored search is an indispensable business model and a major revenue contributor of almost all the search engines. From the advertisers’ side, participating in ranking the search results by paying for the sponsored search advertisement to attract more awareness and purchase facilitates their commercial goal. From the users’ side, presenting personalized advertisement reflecting their propensity would make their online search experience more satisfactory. Sponsored search platforms rank the advertisements by a ranking function to determine the list of advertisements to show and the charging price for the advertisers. Hence, it is crucial to find a good ranking function which can simultaneously satisfy the platform, the users and the advertisers. Moreover, advertisements showing positions under different queries from different users may associate with advertisement candidates of different bid price distributions and click probability distributions, which requires the ranking functions to be optimized adaptively to the traffic characteristics. In this work, we proposed a generic framework to optimize the ranking functions by deep reinforcement learning methods. The framework is composed of two parts: an offline learning part which initializes the ranking functions by learning from a simulated advertising environment, allowing adequate exploration of the ranking function parameter space without hurting the performance of the commercial platform. An online learning part which further optimizes the ranking functions by adapting to the online data distribution. Experimental results on a large-scale sponsored search platform confirm the effectiveness of the proposed method. |
| Tasks | |
| Published | 2018-03-20 |
| URL | http://arxiv.org/abs/1803.07347v3 |
| http://arxiv.org/pdf/1803.07347v3.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-sponsored-search-ranking-strategy |
| Repo | |
| Framework | |
Network Distance Based on Laplacian Flows on Graphs
| Title | Network Distance Based on Laplacian Flows on Graphs |
| Authors | Dianbin Bao, Kisung You, Lizhen Lin |
| Abstract | Distance plays a fundamental role in measuring similarity between objects. Various visualization techniques and learning tasks in statistics and machine learning such as shape matching, classification, dimension reduction and clustering often rely on some distance or similarity measure. It is of tremendous importance to have a distance that can incorporate the underlying structure of the object. In this paper, we focus on proposing such a distance between network objects. Our key insight is to define a distance based on the long term diffusion behavior of the whole network. We first introduce a dynamic system on graphs called Laplacian flow. Based on this Laplacian flow, a new version of diffusion distance between networks is proposed. We will demonstrate the utility of the distance and its advantage over various existing distances through explicit examples. The distance is also applied to subsequent learning tasks such as clustering network objects. |
| Tasks | Dimensionality Reduction |
| Published | 2018-10-05 |
| URL | http://arxiv.org/abs/1810.02906v1 |
| http://arxiv.org/pdf/1810.02906v1.pdf | |
| PWC | https://paperswithcode.com/paper/network-distance-based-on-laplacian-flows-on |
| Repo | |
| Framework | |
Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery
| Title | Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery |
| Authors | Seyed Majid Azimi, Eleonora Vig, Reza Bahmanyar, Marco Körner, Peter Reinartz |
| Abstract | Automatic multi-class object detection in remote sensing images in unconstrained scenarios is of high interest for several applications including traffic monitoring and disaster management. The huge variation in object scale, orientation, category, and complex backgrounds, as well as the different camera sensors pose great challenges for current algorithms. In this work, we propose a new method consisting of a novel joint image cascade and feature pyramid network with multi-size convolution kernels to extract multi-scale strong and weak semantic features. These features are fed into rotation-based region proposal and region of interest networks to produce object detections. Finally, rotational non-maximum suppression is applied to remove redundant detections. During training, we minimize joint horizontal and oriented bounding box loss functions, as well as a novel loss that enforces oriented boxes to be rectangular. Our method achieves 68.16% mAP on horizontal and 72.45% mAP on oriented bounding box detection tasks on the challenging DOTA dataset, outperforming all published methods by a large margin (+6% and +12% absolute improvement, respectively). Furthermore, it generalizes to two other datasets, NWPU VHR-10 and UCAS-AOD, and achieves competitive results with the baselines even when trained on DOTA. Our method can be deployed in multi-class object detection applications, regardless of the image and object scales and orientations, making it a great choice for unconstrained aerial and satellite imagery. |
| Tasks | Object Detection, Object Detection In Aerial Images |
| Published | 2018-07-07 |
| URL | http://arxiv.org/abs/1807.02700v3 |
| http://arxiv.org/pdf/1807.02700v3.pdf | |
| PWC | https://paperswithcode.com/paper/towards-multi-class-object-detection-in |
| Repo | |
| Framework | |
On the Calibration of Nested Dichotomies for Large Multiclass Tasks
| Title | On the Calibration of Nested Dichotomies for Large Multiclass Tasks |
| Authors | Tim Leathart, Eibe Frank, Bernhard Pfahringer, Geoffrey Holmes |
| Abstract | Nested dichotomies are used as a method of transforming a multiclass classification problem into a series of binary problems. A tree structure is induced that recursively splits the set of classes into subsets, and a binary classification model learns to discriminate between the two subsets of classes at each node. In this paper, we demonstrate that these nested dichotomies typically exhibit poor probability calibration, even when the base binary models are well calibrated. We also show that this problem is exacerbated when the binary models are poorly calibrated. We discuss the effectiveness of different calibration strategies and show that accuracy and log-loss can be significantly improved by calibrating both the internal base models and the full nested dichotomy structure, especially when the number of classes is high. |
| Tasks | Calibration |
| Published | 2018-09-08 |
| URL | http://arxiv.org/abs/1809.02744v3 |
| http://arxiv.org/pdf/1809.02744v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-calibration-of-nested-dichotomies-for |
| Repo | |
| Framework | |
