Paper Group ANR 973
Quantile Propagation for Wasserstein-Approximate Gaussian Processes. A Novel Multiple Classifier Generation and Combination Framework Based on Fuzzy Clustering and Individualized Ensemble Construction. Scene and Environment Monitoring Using Aerial Imagery and Deep Learning. A Stable Nuclear Future? The Impact of Autonomous Systems and Artificial In …
Quantile Propagation for Wasserstein-Approximate Gaussian Processes
| Title | Quantile Propagation for Wasserstein-Approximate Gaussian Processes |
| Authors | Rui Zhang, Christian J. Walder, Edwin V. Bonilla, Marian-Andrei Rizoiu, Lexing Xie |
| Abstract | We develop a new approximate Bayesian inference method for Gaussian process models with factorized non-Gaussian likelihoods. Our method—dubbed Quantile Propagation (QP)—is similar to expectation propagation (EP) but minimizes the L_2 Wasserstein distance rather than the Kullback-Leibler (KL) divergence. We consider the case where likelihood factors are approximated by a Gaussian form. We show that QP matches quantile functions rather than moments as in EP and has the same mean update but a smaller variance update than EP, thereby alleviating the over-estimation of the posterior variance exhibited by EP. Crucially, QP has the same favorable locality property as EP, and thereby admits an efficient algorithm. Experiments on classification and Poisson regression tasks demonstrate that QP outperforms both EP and variational Bayes. |
| Tasks | Bayesian Inference, Gaussian Processes |
| Published | 2019-12-21 |
| URL | https://arxiv.org/abs/1912.10200v2 |
| https://arxiv.org/pdf/1912.10200v2.pdf | |
| PWC | https://paperswithcode.com/paper/quantile-propagation-for-wasserstein |
| Repo | |
| Framework | |
A Novel Multiple Classifier Generation and Combination Framework Based on Fuzzy Clustering and Individualized Ensemble Construction
| Title | A Novel Multiple Classifier Generation and Combination Framework Based on Fuzzy Clustering and Individualized Ensemble Construction |
| Authors | Zhen Gao, Maryam Zand, Jianhua Ruan |
| Abstract | Multiple classifier system (MCS) has become a successful alternative for improving classification performance. However, studies have shown inconsistent results for different MCSs, and it is often difficult to predict which MCS algorithm works the best on a particular problem. We believe that the two crucial steps of MCS - base classifier generation and multiple classifier combination, need to be designed coordinately to produce robust results. In this work, we show that for different testing instances, better classifiers may be trained from different subdomains of training instances including, for example, neighboring instances of the testing instance, or even instances far away from the testing instance. To utilize this intuition, we propose Individualized Classifier Ensemble (ICE). ICE groups training data into overlapping clusters, builds a classifier for each cluster, and then associates each training instance to the top-performing models while taking into account model types and frequency. In testing, ICE finds the k most similar training instances for a testing instance, then predicts class label of the testing instance by averaging the prediction from models associated with these training instances. Evaluation results on 49 benchmarks show that ICE has a stable improvement on a significant proportion of datasets over existing MCS methods. ICE provides a novel choice of utilizing internal patterns among instances to improve classification, and can be easily combined with various classification models and applied to many application domains. |
| Tasks | |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1907.13353v1 |
| https://arxiv.org/pdf/1907.13353v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-multiple-classifier-generation-and |
| Repo | |
| Framework | |
Scene and Environment Monitoring Using Aerial Imagery and Deep Learning
| Title | Scene and Environment Monitoring Using Aerial Imagery and Deep Learning |
| Authors | Mahdi Maktabdar Oghaz, Manzoor Razaak, Hamideh Kerdegari, Vasileios Argyriou, Paolo Remagnino |
| Abstract | Unmanned Aerial vehicles (UAV) are a promising technology for smart farming related applications. Aerial monitoring of agriculture farms with UAV enables key decision-making pertaining to crop monitoring. Advancements in deep learning techniques have further enhanced the precision and reliability of aerial imagery based analysis. The capabilities to mount various kinds of sensors (RGB, spectral cameras) on UAV allows remote crop analysis applications such as vegetation classification and segmentation, crop counting, yield monitoring and prediction, crop mapping, weed detection, disease and nutrient deficiency detection and others. A significant amount of studies are found in the literature that explores UAV for smart farming applications. In this paper, a review of studies applying deep learning on UAV imagery for smart farming is presented. Based on the application, we have classified these studies into five major groups including: vegetation identification, classification and segmentation, crop counting and yield predictions, crop mapping, weed detection and crop disease and nutrient deficiency detection. An in depth critical analysis of each study is provided. |
| Tasks | Decision Making |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02809v1 |
| https://arxiv.org/pdf/1906.02809v1.pdf | |
| PWC | https://paperswithcode.com/paper/scene-and-environment-monitoring-using-aerial |
| Repo | |
| Framework | |
A Stable Nuclear Future? The Impact of Autonomous Systems and Artificial Intelligence
| Title | A Stable Nuclear Future? The Impact of Autonomous Systems and Artificial Intelligence |
| Authors | Michael C. Horowitz, Paul Scharre, Alexander Velez-Green |
| Abstract | The potential for advances in information-age technologies to undermine nuclear deterrence and influence the potential for nuclear escalation represents a critical question for international politics. One challenge is that uncertainty about the trajectory of technologies such as autonomous systems and artificial intelligence (AI) makes assessments difficult. This paper evaluates the relative impact of autonomous systems and artificial intelligence in three areas: nuclear command and control, nuclear delivery platforms and vehicles, and conventional applications of autonomous systems with consequences for nuclear stability. We argue that countries may be more likely to use risky forms of autonomy when they fear that their second-strike capabilities will be undermined. Additionally, the potential deployment of uninhabited, autonomous nuclear delivery platforms and vehicles could raise the prospect for accidents and miscalculation. Conventional military applications of autonomous systems could simultaneously influence nuclear force postures and first-strike stability in previously unanticipated ways. In particular, the need to fight at machine speed and the cognitive risk introduced by automation bias could increase the risk of unintended escalation. Finally, used properly, there should be many applications of more autonomous systems in nuclear operations that can increase reliability, reduce the risk of accidents, and buy more time for decision-makers in a crisis. |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05291v2 |
| https://arxiv.org/pdf/1912.05291v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-stable-nuclear-future-the-impact-of |
| Repo | |
| Framework | |
Learning to Avoid Poor Images: Towards Task-aware C-arm Cone-beam CT Trajectories
| Title | Learning to Avoid Poor Images: Towards Task-aware C-arm Cone-beam CT Trajectories |
| Authors | Jan-Nico Zaech, Cong Gao, Bastian Bier, Russell Taylor, Andreas Maier, Nassir Navab, Mathias Unberath |
| Abstract | Metal artifacts in computed tomography (CT) arise from a mismatch between physics of image formation and idealized assumptions during tomographic reconstruction. These artifacts are particularly strong around metal implants, inhibiting widespread adoption of 3D cone-beam CT (CBCT) despite clear opportunity for intra-operative verification of implant positioning, e.g. in spinal fusion surgery. On synthetic and real data, we demonstrate that much of the artifact can be avoided by acquiring better data for reconstruction in a task-aware and patient-specific manner, and describe the first step towards the envisioned task-aware CBCT protocol. The traditional short-scan CBCT trajectory is planar, with little room for scene-specific adjustment. We extend this trajectory by autonomously adjusting out-of-plane angulation. This enables C-arm source trajectories that are scene-specific in that they avoid acquiring “poor images”, characterized by beam hardening, photon starvation, and noise. The recommendation of ideal out-of-plane angulation is performed on-the-fly using a deep convolutional neural network that regresses a detectability-rank derived from imaging physics. |
| Tasks | Computed Tomography (CT) |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08868v1 |
| https://arxiv.org/pdf/1909.08868v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-avoid-poor-images-towards-task |
| Repo | |
| Framework | |
Audio-Visual Target Speaker Extraction on Multi-Talker Environment using Event-Driven Cameras
| Title | Audio-Visual Target Speaker Extraction on Multi-Talker Environment using Event-Driven Cameras |
| Authors | Ander Arriandiaga, Giovanni Morrone, Luca Pasa, Leonardo Badino, Chiara Bartolozzi |
| Abstract | In this work, we propose a new method to address audio-visual target speaker extraction in multi-talker environments using event-driven cameras. All audio-visual speech separation approaches use a frame-based video to extract visual features. However, these frame-based cameras usually work at 30 frames per second. This limitation makes it difficult to process an audio-visual signal with low latency. In order to overcome this limitation, we propose using event-driven cameras due to their high temporal resolution and low latency. Recent work showed that the use of landmark motion features is very important in order to get good results on audio-visual speech separation. Thus, we use event-driven vision sensors from which the extraction of motion is available at lower latency computational cost. A stacked Bidirectional LSTM is trained to predict an Ideal Amplitude Mask before post-processing to get a clean audio signal. The performance of our model is close to those yielded in frame-based fashion. |
| Tasks | Speech Separation |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02671v1 |
| https://arxiv.org/pdf/1912.02671v1.pdf | |
| PWC | https://paperswithcode.com/paper/audio-visual-target-speaker-extraction-on |
| Repo | |
| Framework | |
Dynamic Spectral Residual Superpixels
| Title | Dynamic Spectral Residual Superpixels |
| Authors | Jianchao Zhang, Angelica I. Aviles-Rivero, Daniel Heydecker, Xiosheng Zhuang, Raymond Chan, Carola-Bibiane Schönlieb |
| Abstract | We consider the problem of segmenting an image into superpixels in the context of $k$-means clustering, in which we wish to decompose an image into local, homogeneous regions corresponding to the underlying objects. Our novel approach builds upon the widely used Simple Linear Iterative Clustering (SLIC), and incorporate a measure of objects’ structure based on the spectral residual of an image. Based on this combination, we propose a modified initialisation scheme and search metric, which helps keeps fine-details. This combination leads to better adherence to object boundaries, while preventing unnecessary segmentation of large, uniform areas, while remaining computationally tractable in comparison to other methods. We demonstrate through numerical and visual experiments that our approach outperforms the state-of-the-art techniques. |
| Tasks | |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04794v1 |
| https://arxiv.org/pdf/1910.04794v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-spectral-residual-superpixels |
| Repo | |
| Framework | |
Adaptive Prior Selection for Repertoire-based Online Adaptation in Robotics
| Title | Adaptive Prior Selection for Repertoire-based Online Adaptation in Robotics |
| Authors | Rituraj Kaushik, Pierre Desreumaux, Jean-Baptiste Mouret |
| Abstract | Repertoire-based learning is a data-efficient adaptation approach based on a two-step process in which (1) a large and diverse set of policies is learned in simulation, and (2) a planning or learning algorithm chooses the most appropriate policies according to the current situation (e.g., a damaged robot, a new object, etc.). In this paper, we relax the assumption of previous works that a single repertoire is enough for adaptation. Instead, we generate repertoires for many different situations (e.g., with a missing leg, on different floors, etc.) and let our algorithm selects the most useful prior. Our main contribution is an algorithm, APROL (Adaptive Prior selection for Repertoire-based Online Learning) to plan the next action by incorporating these priors when the robot has no information about the current situation. We evaluate APROL on two simulated tasks: (1) pushing unknown objects of various shapes and sizes with a robotic arm and (2) a goal reaching task with a damaged hexapod robot. We compare with “Reset-free Trial and Error” (RTE) and various single repertoire-based baselines. The results show that APROL solves both the tasks in less interaction time than the baselines. Additionally, we demonstrate APROL on a real, damaged hexapod that quickly learns to pick compensatory policies to reach a goal by avoiding obstacles in the path. |
| Tasks | Meta-Learning |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07029v3 |
| https://arxiv.org/pdf/1907.07029v3.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-prior-selection-for-repertoire-based |
| Repo | |
| Framework | |
Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds
| Title | Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds |
| Authors | Igor Labutov, Bishan Yang, Anusha Prakash, Amos Azaria |
| Abstract | Question Answering (QA), as a research field, has primarily focused on either knowledge bases (KBs) or free text as a source of knowledge. These two sources have historically shaped the kinds of questions that are asked over these sources, and the methods developed to answer them. In this work, we look towards a practical use-case of QA over user-instructed knowledge that uniquely combines elements of both structured QA over knowledge bases, and unstructured QA over narrative, introducing the task of multi-relational QA over personal narrative. As a first step towards this goal, we make three key contributions: (i) we generate and release TextWorldsQA, a set of five diverse datasets, where each dataset contains dynamic narrative that describes entities and relations in a simulated world, paired with variably compositional questions over that knowledge, (ii) we perform a thorough evaluation and analysis of several state-of-the-art QA models and their variants at this task, and (iii) we release a lightweight Python-based framework we call TextWorlds for easily generating arbitrary additional worlds and narrative, with the goal of allowing the community to create and share a growing collection of diverse worlds as a test-bed for this task. |
| Tasks | Question Answering, Reading Comprehension |
| Published | 2019-02-25 |
| URL | http://arxiv.org/abs/1902.09093v1 |
| http://arxiv.org/pdf/1902.09093v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-relational-question-answering-from |
| Repo | |
| Framework | |
Trajectories of Blocked Community Members: Redemption, Recidivism and Departure
| Title | Trajectories of Blocked Community Members: Redemption, Recidivism and Departure |
| Authors | Jonathan P. Chang, Cristian Danescu-Niculescu-Mizil |
| Abstract | Community norm violations can impair constructive communication and collaboration online. As a defense mechanism, community moderators often address such transgressions by temporarily blocking the perpetrator. Such actions, however, come with the cost of potentially alienating community members. Given this tradeoff, it is essential to understand to what extent, and in which situations, this common moderation practice is effective in reinforcing community rules. In this work, we introduce a computational framework for studying the future behavior of blocked users on Wikipedia. After their block expires, they can take several distinct paths: they can reform and adhere to the rules, but they can also recidivate, or straight-out abandon the community. We reveal that these trajectories are tied to factors rooted both in the characteristics of the blocked individual and in whether they perceived the block to be fair and justified. Based on these insights, we formulate a series of prediction tasks aiming to determine which of these paths a user is likely to take after being blocked for their first offense, and demonstrate the feasibility of these new tasks. Overall, this work builds towards a more nuanced approach to moderation by highlighting the tradeoffs that are in play. |
| Tasks | |
| Published | 2019-02-22 |
| URL | http://arxiv.org/abs/1902.08628v1 |
| http://arxiv.org/pdf/1902.08628v1.pdf | |
| PWC | https://paperswithcode.com/paper/trajectories-of-blocked-community-members |
| Repo | |
| Framework | |
Estimating skeleton-based gait abnormality index by sparse deep auto-encoder
| Title | Estimating skeleton-based gait abnormality index by sparse deep auto-encoder |
| Authors | Trong Nguyen Nguyen, Huu Hung Huynh, Jean Meunier |
| Abstract | This paper proposes an approach estimating a gait abnormality index based on skeletal information provided by a depth camera. Differently from related works where the extraction of hand-crafted features is required to describe gait characteristics, our method automatically performs that stage with the support of a deep auto-encoder. In order to get visually interpretable features, we embedded a constraint of sparsity into the model. Similarly to most gait-related studies, the temporal factor is also considered as a post-processing in our system. This method provided promising results when experimenting on a dataset containing nearly one hundred thousand skeleton samples. |
| Tasks | |
| Published | 2019-08-17 |
| URL | https://arxiv.org/abs/1908.07415v1 |
| https://arxiv.org/pdf/1908.07415v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-skeleton-based-gait-abnormality |
| Repo | |
| Framework | |
Geolocation of an aircraft using image registration coupling modes for autonomous navigation
| Title | Geolocation of an aircraft using image registration coupling modes for autonomous navigation |
| Authors | Nima Ziaei |
| Abstract | This paper proposes to study an alternative technology to the GPS system on fixed wing aircraft using the aerial shots of landscapes from a ventral monocular camera integrated into the aircraft and based on the technology of image registration for aircraft geolocation purpose. Different types of use of the image registration technology exist: the relative registration and the absolute registration. The relative one is able to readjust position of the aircraft from two successive aerial shots by knowing the aircraft s position of image 1 and the overlap between the two images. The absolute registration compare a real time aerial shot with pre-referenced images stored in a database and permit the geolocation of the aircraft in comparing aerial shot with images of the database. Each kind of image registration technology has its own flaw preventing it to be used alone for aircraft geolocation. This study proposes to evaluate, according to different physical parameters ( aircraft speed, flight altitude, density of image points of interest), the coupling of these different types of image registration. Finally, this study also aims to quantify some image registration performances, particularly its execution time or its drift. |
| Tasks | Autonomous Navigation, Image Registration |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.02875v1 |
| https://arxiv.org/pdf/1909.02875v1.pdf | |
| PWC | https://paperswithcode.com/paper/geolocation-of-an-aircraft-using-image |
| Repo | |
| Framework | |
Learning to Sample Hard Instances for Graph Algorithms
| Title | Learning to Sample Hard Instances for Graph Algorithms |
| Authors | Ryoma Sato, Makoto Yamada, Hisashi Kashima |
| Abstract | Hard instances, which require a long time for a specific algorithm to solve, help (1) analyze the algorithm for accelerating it and (2) build a good benchmark for evaluating the performance of algorithms. There exist several efforts for automatic generation of hard instances. For example, evolutionary algorithms have been utilized to generate hard instances. However, they generate only finite number of hard instances. The merit of such methods is limited because it is difficult to extract meaningful patterns from small number of instances. We seek for a probabilistic generator of hard instances. Once the generative distribution of hard instances is obtained, we can sample a variety of hard instances to build a benchmark, and we can extract meaningful patterns of hard instances from sampled instances. The existing methods for modeling the hard instance distribution rely on parameters or rules that are found by domain experts; however, they are specific to the problem. Hence, it is challenging to model the distribution for general cases. In this paper, we focus on graph problems. We propose HiSampler, the hard instance sampler, to model the hard instance distribution of graph algorithms. HiSampler makes it possible to obtain the distribution of hard instances without hand-engineered features. To the best of our knowledge, this is the first method to learn the distribution of hard instances using machine learning. Through experiments, we demonstrate that our proposed method can generate instances that are a few to several orders of magnitude harder than the random-based approach in many settings. In particular, our method outperforms rule-based algorithms in the 3-coloring problem. |
| Tasks | |
| Published | 2019-02-26 |
| URL | https://arxiv.org/abs/1902.09700v2 |
| https://arxiv.org/pdf/1902.09700v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-find-hard-instances-of-graph |
| Repo | |
| Framework | |
Automating Vitiligo Skin Lesion Segmentation Using Convolutional Neural Networks
| Title | Automating Vitiligo Skin Lesion Segmentation Using Convolutional Neural Networks |
| Authors | Makena Low, Priyanka Raina |
| Abstract | For several skin conditions such as vitiligo, accurate segmentation of lesions from skin images is the primary measure of disease progression and severity. Existing methods for vitiligo lesion segmentation require manual intervention. Unfortunately, manual segmentation is time and labor-intensive, as well as irreproducible between physicians. We introduce a convolutional neural network (CNN) that quickly and robustly performs vitiligo skin lesion segmentation. Our CNN has a U-Net architecture with a modified contracting path. We use the CNN to generate an initial segmentation of the lesion, then refine it by running the watershed algorithm on high-confidence pixels. We train the network on 247 images with a variety of lesion sizes, complexity, and anatomical sites. The network with our modifications noticeably outperforms the state-of-the-art U-Net, with a Jaccard Index (JI) score of 73.6% (compared to 36.7%). Moreover, our method requires only a few seconds for segmentation, in contrast with the previously proposed semi-autonomous watershed approach, which requires 2-29 minutes per image. |
| Tasks | Lesion Segmentation |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.08350v1 |
| https://arxiv.org/pdf/1912.08350v1.pdf | |
| PWC | https://paperswithcode.com/paper/automating-vitiligo-skin-lesion-segmentation |
| Repo | |
| Framework | |
LionForests: Local Interpretation of Random Forests
| Title | LionForests: Local Interpretation of Random Forests |
| Authors | Ioannis Mollas, Nick Bassiliades, Ioannis Vlahavas, Grigorios Tsoumakas |
| Abstract | Towards a future where machine learning systems will integrate into every aspect of people’s lives, researching methods to interpret such systems is necessary, instead of focusing exclusively on enhancing their performance. Enriching the trust between these systems and people will accelerate this integration process. Many medical and retail banking/finance applications use state-of-the-art machine learning techniques to predict certain aspects of new instances. Tree ensembles, like random forests, are widely acceptable solutions on these tasks, while at the same time they are avoided due to their black-box uninterpretable nature, creating an unreasonable paradox. In this paper, we provide a methodology for shedding light on the predictions of the misjudged family of tree ensemble algorithms. Using classic unsupervised learning techniques and an enhanced similarity metric, to wander among transparent trees inside a forest following breadcrumbs, the interpretable essence of tree ensembles arises. An interpretation provided by these systems using our approach, which we call “LionForests”, can be a simple, comprehensive rule. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.08780v2 |
| https://arxiv.org/pdf/1911.08780v2.pdf | |
| PWC | https://paperswithcode.com/paper/lionforests-local-interpretation-of-random |
| Repo | |
| Framework | |
