October 17, 2019

3310 words 16 mins read

Paper Group ANR 718

Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks. Dual Control Memory Augmented Neural Networks for Treatment Recommendations. Decomposition Methods with Deep Corrections for Reinforcement Learning. Weak detection in the spiked Wigner model. Explicit Feedbacks Meet with Implicit Feedbacks : …

Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks


Title	Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks
Authors	Tony C. W Mok, Albert C. S Chung
Abstract	There is a common belief that the successful training of deep neural networks requires many annotated training samples, which are often expensive and difficult to obtain especially in the biomedical imaging field. While it is often easy for researchers to use data augmentation to expand the size of training sets, constructing and generating generic augmented data that is able to teach the network the desired invariance and robustness properties using traditional data augmentation techniques is challenging in practice. In this paper, we propose a novel automatic data augmentation method that uses generative adversarial networks to learn augmentations that enable machine learning based method to learn the available annotated samples more efficiently. The architecture consists of a coarse-to-fine generator to capture the manifold of the training sets and generate generic augmented data. In our experiments, we show the efficacy of our approach on a Magnetic Resonance Imaging (MRI) image, achieving improvements of 3.5% Dice coefficient on the BRATS15 Challenge dataset as compared to traditional augmentation approaches. Also, our proposed method successfully boosts a common segmentation network to reach the state-of-the-art performance on the BRATS15 Challenge.
Tasks	Brain Tumor Segmentation, Data Augmentation
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11291v2
PDF	http://arxiv.org/pdf/1805.11291v2.pdf
PWC	https://paperswithcode.com/paper/learning-data-augmentation-for-brain-tumor
Repo
Framework

Dual Control Memory Augmented Neural Networks for Treatment Recommendations


Title	Dual Control Memory Augmented Neural Networks for Treatment Recommendations
Authors	Hung Le, Truyen Tran, Svetha Venkatesh
Abstract	Machine-assisted treatment recommendations hold a promise to reduce physician time and decision errors. We formulate the task as a sequence-to-sequence prediction model that takes the entire time-ordered medical history as input, and predicts a sequence of future clinical procedures and medications. It is built on the premise that an effective treatment plan may have long-term dependencies from previous medical history. We approach the problem by using a memory-augmented neural network, in particular, by leveraging the recent differentiable neural computer that consists of a neural controller and an external memory module. But differing from the original model, we use dual controllers, one for encoding the history followed by another for decoding the treatment sequences. In the encoding phase, the memory is updated as new input is read; at the end of this phase, the memory holds not only the medical history but also the information about the current illness. During the decoding phase, the memory is write-protected. The decoding controller generates a treatment sequence, one treatment option at a time. The resulting dual controller write-protected memory-augmented neural network is demonstrated on the MIMIC-III dataset on two tasks: procedure prediction and medication prescription. The results show improved performance over both traditional bag-of-words and sequence-to-sequence methods.
Tasks
Published	2018-02-11
URL	http://arxiv.org/abs/1802.03689v1
PDF	http://arxiv.org/pdf/1802.03689v1.pdf
PWC	https://paperswithcode.com/paper/dual-control-memory-augmented-neural-networks
Repo
Framework

Decomposition Methods with Deep Corrections for Reinforcement Learning


Title	Decomposition Methods with Deep Corrections for Reinforcement Learning
Authors	Maxime Bouton, Kyle Julian, Alireza Nakhaei, Kikuo Fujimura, Mykel J. Kochenderfer
Abstract	Decomposition methods have been proposed to approximate solutions to large sequential decision making problems. In contexts where an agent interacts with multiple entities, utility decomposition can be used to separate the global objective into local tasks considering each individual entity independently. An arbitrator is then responsible for combining the individual utilities and selecting an action in real time to solve the global problem. Although these techniques can perform well empirically, they rely on strong assumptions of independence between the local tasks and sacrifice the optimality of the global solution. This paper proposes an approach that improves upon such approximate solutions by learning a correction term represented by a neural network. We demonstrate this approach on a fisheries management problem where multiple boats must coordinate to maximize their catch over time as well as on a pedestrian avoidance problem for autonomous driving. In each problem, decomposition methods can scale to multiple boats or pedestrians by using strategies involving one entity. We verify empirically that the proposed correction method significantly improves the decomposition method and outperforms a policy trained on the full scale problem without utility decomposition.
Tasks	Autonomous Driving, Decision Making, Problem Decomposition, Representation Learning
Published	2018-02-06
URL	http://arxiv.org/abs/1802.01772v2
PDF	http://arxiv.org/pdf/1802.01772v2.pdf
PWC	https://paperswithcode.com/paper/utility-decomposition-with-deep-corrections
Repo
Framework

Weak detection in the spiked Wigner model


Title	Weak detection in the spiked Wigner model
Authors	Hye Won Chung, Ji Oon Lee
Abstract	We consider the weak detection problem in a rank-one spiked Wigner data matrix where the signal-to-noise ratio is small so that reliable detection is impossible. We propose a hypothesis test on the presence of the signal by utilizing the linear spectral statistics of the data matrix. The test is data-driven and does not require prior knowledge about the distribution of the signal or the noise. When the noise is Gaussian, the proposed test is optimal in the sense that its error matches that of the likelihood ratio test, which minimizes the sum of the Type-I and Type-II errors. If the density of the noise is known and non-Gaussian, the error of the test can be lowered by applying an entrywise transformation to the data matrix. We establish a central limit theorem for the linear spectral statistics of general rank-one spiked Wigner matrices as an intermediate step.
Tasks
Published	2018-09-28
URL	https://arxiv.org/abs/1809.10827v3
PDF	https://arxiv.org/pdf/1809.10827v3.pdf
PWC	https://paperswithcode.com/paper/weak-detection-of-signal-in-the-spiked-wigner
Repo
Framework

Explicit Feedbacks Meet with Implicit Feedbacks : A Combined Approach for Recommendation System


Title	Explicit Feedbacks Meet with Implicit Feedbacks : A Combined Approach for Recommendation System
Authors	Supriyo Mandal, Abyayananda Maiti
Abstract	Recommender systems recommend items more accurately by analyzing users’ potential interest on different brands’ items. In conjunction with users’ rating similarity, the presence of users’ implicit feedbacks like clicking items, viewing items specifications, watching videos etc. have been proved to be helpful for learning users’ embedding, that helps better rating prediction of users. Most existing recommender systems focus on modeling of ratings and implicit feedbacks ignoring users’ explicit feedbacks. Explicit feedbacks can be used to validate the reliability of the particular users and can be used to learn about the users’ characteristic. Users’ characteristic mean what type of reviewers they are. In this paper, we explore three different models for recommendation with more accuracy focusing on users’ explicit feedbacks and implicit feedbacks. First one is RHC-PMF that predicts users’ rating more accurately based on user’s three explicit feedbacks (rating, helpfulness score and centrality) and second one is RV-PMF, where user’s implicit feedback (view relationship) is considered. Last one is RHCV-PMF, where both type of feedbacks are considered. In this model users’ explicit feedbacks’ similarity indicate the similarity of their reliability and characteristic and implicit feedback’s similarity indicates their preference similarity. Extensive experiments on real world dataset, i.e. Amazon.com online review dataset shows that our models perform better compare to base-line models in term of users’ rating prediction. RHCV-PMF model also performs better rating prediction compare to baseline models for cold start users and cold start items.
Tasks	Recommendation Systems
Published	2018-10-29
URL	http://arxiv.org/abs/1810.12770v1
PDF	http://arxiv.org/pdf/1810.12770v1.pdf
PWC	https://paperswithcode.com/paper/explicit-feedbacks-meet-with-implicit
Repo
Framework

A Hybrid Framework for Tumor Saliency Estimation


Title	A Hybrid Framework for Tumor Saliency Estimation
Authors	Fei Xu, Min Xian, Yingtao Zhang, Kuan Huang, H. D. Cheng, Boyu Zhang, Jianrui Ding, Chunping Ning, Ying Wang
Abstract	Automatic tumor segmentation of breast ultrasound (BUS) image is quite challenging due to the complicated anatomic structure of breast and poor image quality. Most tumor segmentation approaches achieve good performance on BUS images collected in controlled settings; however, the performance degrades greatly with BUS images from different sources. Tumor saliency estimation (TSE) has attracted increasing attention to solving the problem by modeling radiologists’ attention mechanism. In this paper, we propose a novel hybrid framework for TSE, which integrates both high-level domain-knowledge and robust low-level saliency assumptions and can overcome drawbacks caused by direct mapping in traditional TSE approaches. The new framework integrated the Neutro-Connectedness (NC) map, the adaptive-center, the correlation and the layer structure-based weighted map. The experimental results demonstrate that the proposed approach outperforms state-of-the-art TSE methods.
Tasks	Saliency Prediction
Published	2018-06-27
URL	http://arxiv.org/abs/1806.10696v1
PDF	http://arxiv.org/pdf/1806.10696v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-framework-for-tumor-saliency
Repo
Framework

Retrieval and Registration of Long-Range Overlapping Frames for Scalable Mosaicking of In Vivo Fetoscopy


Title	Retrieval and Registration of Long-Range Overlapping Frames for Scalable Mosaicking of In Vivo Fetoscopy
Authors	Loïc Peter, Marcel Tella-Amo, Dzhoshkun Ismail Shakir, George Attilakos, Ruwan Wimalasundera, Jan Deprest, Sébastien Ourselin, Tom Vercauteren
Abstract	Purpose: The standard clinical treatment of Twin-to-Twin Transfusion Syndrome consists in the photo-coagulation of undesired anastomoses located on the placenta which are responsible to a blood transfer between the two twins. While being the standard of care procedure, fetoscopy suffers from a limited field-of-view of the placenta resulting in missed anastomoses. To facilitate the task of the clinician, building a global map of the placenta providing a larger overview of the vascular network is highly desired. Methods: To overcome the challenging visual conditions inherent to in vivo sequences (low contrast, obstructions or presence of artifacts, among others), we propose the following contributions: (i) robust pairwise registration is achieved by aligning the orientation of the image gradients, and (ii) difficulties regarding long-range consistency (e.g. due to the presence of outliers) is tackled via a bag-of-word strategy, which identifies overlapping frames of the sequence to be registered regardless of their respective location in time. Results: In addition to visual difficulties, in vivo sequences are characterised by the intrinsic absence of gold standard. We present mosaics motivating qualitatively our methodological choices and demonstrating their promising aspect. We also demonstrate semi-quantitatively, via visual inspection of registration results, the efficacy of our registration approach in comparison to two standard baselines. Conclusion: This paper proposes the first approach for the construction of mosaics of placenta in in vivo fetoscopy sequences. Robustness to visual challenges during registration and long-range temporal consistency are proposed, offering first positive results on in vivo data for which standard mosaicking techniques are not applicable.
Tasks
Published	2018-02-28
URL	http://arxiv.org/abs/1802.10554v1
PDF	http://arxiv.org/pdf/1802.10554v1.pdf
PWC	https://paperswithcode.com/paper/retrieval-and-registration-of-long-range
Repo
Framework

Socially Aware Kalman Neural Networks for Trajectory Prediction


Title	Socially Aware Kalman Neural Networks for Trajectory Prediction
Authors	Ce Ju, Zheng Wang, Xiaoyu Zhang
Abstract	Trajectory prediction is a critical technique in the navigation of robots and autonomous vehicles. However, the complex traffic and dynamic uncertainties yield challenges in the effectiveness and robustness in modeling. We purpose a data-driven approach socially aware Kalman neural networks (SAKNN) where the interaction layer and the Kalman layer are embedded in the architecture, resulting in a class of architectures with huge potential to directly learn from high variance sensor input and robustly generate low variance outcomes. The evaluation of our approach on NGSIM dataset demonstrates that SAKNN performs state-of-the-art on prediction effectiveness in a relatively long-term horizon and significantly improves the signal-to-noise ratio of the predicted signal.
Tasks	Autonomous Vehicles, Trajectory Prediction
Published	2018-09-14
URL	https://arxiv.org/abs/1809.05408v4
PDF	https://arxiv.org/pdf/1809.05408v4.pdf
PWC	https://paperswithcode.com/paper/socially-aware-kalman-neural-networks-for
Repo
Framework

Artificial Intelligence for Long-Term Robot Autonomy: A Survey


Title	Artificial Intelligence for Long-Term Robot Autonomy: A Survey
Authors	Lars Kunze, Nick Hawes, Tom Duckett, Marc Hanheide, Tomáš Krajník
Abstract	Autonomous systems will play an essential role in many applications across diverse domains including space, marine, air, field, road, and service robotics. They will assist us in our daily routines and perform dangerous, dirty and dull tasks. However, enabling robotic systems to perform autonomously in complex, real-world scenarios over extended time periods (i.e. weeks, months, or years) poses many challenges. Some of these have been investigated by sub-disciplines of Artificial Intelligence (AI) including navigation & mapping, perception, knowledge representation & reasoning, planning, interaction, and learning. The different sub-disciplines have developed techniques that, when re-integrated within an autonomous system, can enable robots to operate effectively in complex, long-term scenarios. In this paper, we survey and discuss AI techniques as ‘enablers’ for long-term robot autonomy, current progress in integrating these techniques within long-running robotic systems, and the future challenges and opportunities for AI in long-term autonomy.
Tasks
Published	2018-07-13
URL	http://arxiv.org/abs/1807.05196v1
PDF	http://arxiv.org/pdf/1807.05196v1.pdf
PWC	https://paperswithcode.com/paper/artificial-intelligence-for-long-term-robot
Repo
Framework

Robots as Powerful Allies for the Study of Embodied Cognition from the Bottom Up


Title	Robots as Powerful Allies for the Study of Embodied Cognition from the Bottom Up
Authors	Matej Hoffmann, Rolf Pfeifer
Abstract	A large body of compelling evidence has been accumulated demonstrating that embodiment - the agent’s physical setup, including its shape, materials, sensors and actuators - is constitutive for any form of cognition and as a consequence, models of cognition need to be embodied. In contrast to methods from empirical sciences to study cognition, robots can be freely manipulated and virtually all key variables of their embodiment and control programs can be systematically varied. As such, they provide an extremely powerful tool of investigation. We present a robotic bottom-up or developmental approach, focusing on three stages: (a) low-level behaviors like walking and reflexes, (b) learning regularities in sensorimotor spaces, and (c) human-like cognition. We also show that robotic based research is not only a productive path to deepening our understanding of cognition, but that robots can strongly benefit from human-like cognition in order to become more autonomous, robust, resilient, and safe.
Tasks
Published	2018-01-15
URL	http://arxiv.org/abs/1801.04819v1
PDF	http://arxiv.org/pdf/1801.04819v1.pdf
PWC	https://paperswithcode.com/paper/robots-as-powerful-allies-for-the-study-of
Repo
Framework

Model Approximation Using Cascade of Tree Decompositions


Title	Model Approximation Using Cascade of Tree Decompositions
Authors	Navid Tafaghodi Khajavi, Anthony Kuh
Abstract	In this paper, we present a general, multistage framework for graphical model approximation using a cascade of models such as trees. In particular, we look at the problem of covariance matrix approximation for Gaussian distributions as linear transformations of tree models. This is a new way to decompose the covariance matrix. Here, we propose an algorithm which incorporates the Cholesky factorization method to compute the decomposition matrix and thus can approximate a simple graphical model using a cascade of the Cholesky factorization of the tree approximation transformations. The Cholesky decomposition enables us to achieve a tree structure factor graph at each cascade stage of the algorithm which facilitates the use of the message passing algorithm since the approximated graph has less loops compared to the original graph. The overall graph is a cascade of factor graphs with each factor graph being a tree. This is a different perspective on the approximation model, and algorithms such as Gaussian belief propagation can be used on this overall graph. Here, we present theoretical result that guarantees the convergence of the proposed model approximation using the cascade of tree decompositions. In the simulations, we look at synthetic and real data and measure the performance of the proposed framework by comparing the KL divergences.
Tasks
Published	2018-08-10
URL	http://arxiv.org/abs/1808.03504v1
PDF	http://arxiv.org/pdf/1808.03504v1.pdf
PWC	https://paperswithcode.com/paper/model-approximation-using-cascade-of-tree
Repo
Framework

Minimax optimal rates for Mondrian trees and forests


Title	Minimax optimal rates for Mondrian trees and forests
Authors	Jaouad Mourtada, Stéphane Gaïffas, Erwan Scornet
Abstract	Introduced by Breiman, Random Forests are widely used classification and regression algorithms. While being initially designed as batch algorithms, several variants have been proposed to handle online learning. One particular instance of such forests is the \emph{Mondrian Forest}, whose trees are built using the so-called Mondrian process, therefore allowing to easily update their construction in a streaming fashion. In this paper, we provide a thorough theoretical study of Mondrian Forests in a batch learning setting, based on new results about Mondrian partitions. Our results include consistency and convergence rates for Mondrian Trees and Forests, that turn out to be minimax optimal on the set of $s$-H"older function with $s \in (0,1]$ (for trees and forests) and $s \in (1,2]$ (for forests only), assuming a proper tuning of their complexity parameter in both cases. Furthermore, we prove that an adaptive procedure (to the unknown $s \in (0, 2]$) can be constructed by combining Mondrian Forests with a standard model aggregation algorithm. These results are the first demonstrating that some particular random forests achieve minimax rates \textit{in arbitrary dimension}. Owing to their remarkably simple distributional properties, which lead to minimax rates, Mondrian trees are a promising basis for more sophisticated yet theoretically sound random forests variants.
Tasks
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05784v2
PDF	http://arxiv.org/pdf/1803.05784v2.pdf
PWC	https://paperswithcode.com/paper/minimax-optimal-rates-for-mondrian-trees-and
Repo
Framework

Hybrid Feature Based SLAM Prototype


Title	Hybrid Feature Based SLAM Prototype
Authors	V. I Mebin Jose, D. J Binoj
Abstract	The development of data innovation as of late and the expanded limit, has permitted the acquaintance of artificial vision connected with SLAM, offering ascend to what is known as Visual SLAM. The objective of this paper is to build up a route framework dependent on Visual SLAM to get a robot to a fundamental and new condition, have the capacity to set and make a three-dimensional guide thereof, utilizing just as sources of info recording your way with a stereo vision camera. The consequence of this analysis is that the framework Visual SLAM together with the combination of Fast SLAM (combination of kalman with particulate filter and SIFT) perceive and recognize characteristic points in images so adequately exact and unambiguous. This framework uses MATLAB, since its adaptability and comfort for performing a wide range of tests. The program has been tested by inserting a prerecorded video input with a camera stereo in which a course is done by an office environment. The algorithm initially locates points of interest in a stereo frame captured by the camera. These will be located in 3D and they associate an identification descriptor. In the next frame, the camera likewise identified points of interest and it will be compared which of them have been previously detected by comparing their descriptors. This process is known as “data association” and its successful completion is fundamental to the SLAM algorithm. The position data of the robot and points interest stored in data structures known as “particles” that evolve independently. Its management is very important for the proper functioning of the algorithm Fast SLAM. The results are found to be satisfactory.
Tasks
Published	2018-10-16
URL	http://arxiv.org/abs/1810.07230v2
PDF	http://arxiv.org/pdf/1810.07230v2.pdf
PWC	https://paperswithcode.com/paper/hybrid-feature-based-slam-prototype
Repo
Framework

Multi-Step Knowledge-Aided Iterative ESPRIT for Direction Finding


Title	Multi-Step Knowledge-Aided Iterative ESPRIT for Direction Finding
Authors	S. F. B. Pinto, R. C. de Lamare
Abstract	In this work, we propose a subspace-based algorithm for DOA estimation which iteratively reduces the disturbance factors of the estimated data covariance matrix and incorporates prior knowledge which is gradually obtained on line. An analysis of the MSE of the reshaped data covariance matrix is carried out along with comparisons between computational complexities of the proposed and existing algorithms. Simulations focusing on closely-spaced sources, where they are uncorrelated and correlated, illustrate the improvements achieved.
Tasks
Published	2018-05-01
URL	http://arxiv.org/abs/1805.00169v1
PDF	http://arxiv.org/pdf/1805.00169v1.pdf
PWC	https://paperswithcode.com/paper/multi-step-knowledge-aided-iterative-esprit
Repo
Framework

A Supervised Geometry-Aware Mapping Approach for Classification of Hyperspectral Images


Title	A Supervised Geometry-Aware Mapping Approach for Classification of Hyperspectral Images
Authors	Ramanarayan Mohanty, S L Happy, Aurobinda Routray
Abstract	The lack of proper class discrimination among the Hyperspectral (HS) data points poses a potential challenge in HS classification. To address this issue, this paper proposes an optimal geometry-aware transformation for enhancing the classification accuracy. The underlying idea of this method is to obtain a linear projection matrix by solving a nonlinear objective function based on the intrinsic geometrical structure of the data. The objective function is constructed to quantify the discrimination between the points from dissimilar classes on the projected data space. Then the obtained projection matrix is used to linearly map the data to more discriminative space. The effectiveness of the proposed transformation is illustrated with three benchmark real-world HS data sets. The experiments reveal that the classification and dimensionality reduction methods on the projected discriminative space outperform their counterpart in the original space.
Tasks	Classification Of Hyperspectral Images, Dimensionality Reduction
Published	2018-07-07
URL	http://arxiv.org/abs/1807.02682v1
PDF	http://arxiv.org/pdf/1807.02682v1.pdf
PWC	https://paperswithcode.com/paper/a-supervised-geometry-aware-mapping-approach
Repo
Framework