Paper Group ANR 1472
A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors. Dynamically optimal treatment allocation using Reinforcement Learning. Pruning Deep Neural Networks Architectures with Evolution Strategy. Intentional Computational Level Design. Instance Shadow Detection. Using Persistent Homology to Quantify a Diurnal Cycle i …
A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors
| Title | A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors |
| Authors | Tong Qin, Shaozu Cao, Jie Pan, Shaojie Shen |
| Abstract | Accurate state estimation is a fundamental problem for autonomous robots. To achieve locally accurate and globally drift-free state estimation, multiple sensors with complementary properties are usually fused together. Local sensors (camera, IMU, LiDAR, etc) provide precise pose within a small region, while global sensors (GPS, magnetometer, barometer, etc) supply noisy but globally drift-free localization in a large-scale environment. In this paper, we propose a sensor fusion framework to fuse local states with global sensors, which achieves locally accurate and globally drift-free pose estimation. Local estimations, produced by existing VO/VIO approaches, are fused with global sensors in a pose graph optimization. Within the graph optimization, local estimations are aligned into a global coordinate. Meanwhile, the accumulated drifts are eliminated. We evaluate the performance of our system on public datasets and with real-world experiments. Results are compared against other state-of-the-art algorithms. We highlight that our system is a general framework, which can easily fuse various global sensors in a unified pose graph optimization. Our implementations are open source\footnote{https://github.com/HKUST-Aerial-Robotics/VINS-Fusion}. |
| Tasks | Pose Estimation, Sensor Fusion |
| Published | 2019-01-11 |
| URL | http://arxiv.org/abs/1901.03642v1 |
| http://arxiv.org/pdf/1901.03642v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-optimization-based-framework-for-1 |
| Repo | |
| Framework | |
Dynamically optimal treatment allocation using Reinforcement Learning
| Title | Dynamically optimal treatment allocation using Reinforcement Learning |
| Authors | Karun Adusumilli, Friedrich Geiecke, Claudio Schilter |
| Abstract | Devising guidance on how to assign individuals to treatment is an important goal of empirical research. In practice individuals often arrive sequentially, and the planner faces various constraints such as limited budget/capacity, or borrowing constraints, or the need to place people in a queue. For instance, a governmental body may receive a budget outlay at the beginning of an year, and it may need to decide how best to allocate resources within the year to individuals who arrive sequentially. In this and other examples involving inter-temporal trade-offs, previous work on devising optimal policy rules in a static context is either not applicable, or is sub-optimal. Here we show how one can use offline observational data to estimate an optimal policy rule that maximizes ex-ante expected welfare in this dynamic context. We allow the class of policy rules to be restricted for computational, legal or incentive compatibility reasons. The problem is equivalent to one of optimal control under a constrained policy class, and we exploit recent developments in Reinforcement Learning (RL) to propose an algorithm to solve this. The algorithm is easily implementable and computationally efficient, with speedups achieved through multiple RL agents learning in parallel processes. We also characterize the statistical regret from using our estimated policy rule. To do this, we show that a Partial Differential Equation (PDE) characterizes the evolution of the value function under each policy. The data enables us to obtain a sample version of the PDE that provides estimates of these value functions. The estimated policy rule is the one with the maximal estimated value function. Using the theory of viscosity solutions to PDEs we show that the policy regret decays at a $n^{-1/2}$ rate in most examples; this is the same rate as that obtained in the static case. |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://arxiv.org/abs/1904.01047v2 |
| https://arxiv.org/pdf/1904.01047v2.pdf | |
| PWC | https://paperswithcode.com/paper/dynamically-optimal-treatment-allocation |
| Repo | |
| Framework | |
Pruning Deep Neural Networks Architectures with Evolution Strategy
| Title | Pruning Deep Neural Networks Architectures with Evolution Strategy |
| Authors | Francisco Erivaldo Fernandes Junior, Gary G. Yen |
| Abstract | Currently, Deep Neural Networks (DNNs) are used to solve all kinds of problems in the field of machine learning and artificial intelligence due to their learning and adaptation capabilities. However, most of the successful DNN models have a high computational complexity, which makes them difficult to deploy on mobile or embedded platforms. This has prompted many researchers to develop algorithms and approaches to help reduce the computational complexity of such models. One of them is called filter pruning where convolution filters are eliminated to reduce the number of parameters and, consequently, the computational complexity of the given model. In the present work, we propose a novel algorithm to perform filter pruning by using Multi-Objective Evolution Strategy (ES) algorithm, called DeepPruningES. Our approach avoids the need for using any knowledge during the pruning procedure and helps decision makers by returning three pruned DNN models with different trade-offs between performance and computational complexity. We show that DeepPruningES can significantly reduce a model’s computational complexity by testing it on three DNN architectures: Convolutional Neural Networks, Residual Neural Networks, and Densely Connected Neural Networks. |
| Tasks | |
| Published | 2019-12-24 |
| URL | https://arxiv.org/abs/1912.11527v1 |
| https://arxiv.org/pdf/1912.11527v1.pdf | |
| PWC | https://paperswithcode.com/paper/pruning-deep-neural-networks-architectures |
| Repo | |
| Framework | |
Intentional Computational Level Design
| Title | Intentional Computational Level Design |
| Authors | Ahmed Khalifa, Michael Cerny Green, Gabriella Barros, Julian Togelius |
| Abstract | The procedural generation of levels and content in video games is a challenging AI problem. Often such generation relies on an intelligent way of evaluating the content being generated so that constraints are satisfied and/or objectives maximized. In this work, we address the problem of creating levels that are not only playable but also revolve around specific mechanics in the game. We use constrained evolutionary algorithms and quality-diversity algorithms to generate small sections of Super Mario Bros levels called scenes, using three different simulation approaches: Limited Agents, Punishing Model, and Mechanics Dimensions. All three approaches are able to create scenes that give opportunity for a player to encounter or use targeted mechanics with different properties. We conclude by discussing the advantages and disadvantages of each approach and compare them to each other. |
| Tasks | |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08972v1 |
| http://arxiv.org/pdf/1904.08972v1.pdf | |
| PWC | https://paperswithcode.com/paper/intentional-computational-level-design |
| Repo | |
| Framework | |
Instance Shadow Detection
| Title | Instance Shadow Detection |
| Authors | Tianyu Wang, Xiaowei Hu, Qiong Wang, Pheng-Ann Heng, Chi-Wing Fu |
| Abstract | Instance shadow detection is a brand new problem, aiming to find shadow instances paired with object instances. To approach it, we first prepare a new dataset called SOBA, named after Shadow-OBject Association, with 3,623 pairs of shadow and object instances in 1,000 photos, each with individual labeled masks. Second, we design LISA, named after Light-guided Instance Shadow-object Association, an end-to-end framework to automatically predict the shadow and object instances, together with the shadow-object associations and light direction. Then, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results. In our evaluations, we formulate a new metric named the shadow-object average precision to measure the performance of our results. Further, we conducted various experiments and demonstrate our method’s applicability on light direction estimation and photo editing. |
| Tasks | Shadow Detection |
| Published | 2019-11-16 |
| URL | https://arxiv.org/abs/1911.07034v1 |
| https://arxiv.org/pdf/1911.07034v1.pdf | |
| PWC | https://paperswithcode.com/paper/instance-shadow-detection |
| Repo | |
| Framework | |
Using Persistent Homology to Quantify a Diurnal Cycle in Hurricane Felix
| Title | Using Persistent Homology to Quantify a Diurnal Cycle in Hurricane Felix |
| Authors | Sarah Tymochko, Elizabeth Munch, Jason Dunion, Kristen Corbosiero, Ryan Torn |
| Abstract | The diurnal cycle of tropical cyclones (TCs) is a daily cycle in clouds that appears in satellite images and may have implications for TC structure and intensity. The diurnal pattern can be seen in infrared (IR) satellite imagery as cyclical pulses in the cloud field that propagate radially outward from the center of nearly all Atlantic-basin TCs. These diurnal pulses, a distinguishing characteristic of the TC diurnal cycle, begin forming in the storm’s inner core near sunset each day and appear as a region of cooling cloud-top temperatures. The area of cooling takes on a ring-like appearance as cloud-top warming occurs on its inside edge and the cooling moves away from the storm overnight, reaching several hundred kilometers from the circulation center by the following afternoon. The state-of-the-art TC diurnal cycle measurement has a limited ability to analyze the behavior beyond qualitative observations. We present a method for quantifying the TC diurnal cycle using one-dimensional persistent homology, a tool from Topological Data Analysis, by tracking maximum persistence and quantifying the cycle using the discrete Fourier transform. Using Geostationary Operational Environmental Satellite IR imagery data from Hurricane Felix (2007), our method is able to detect an approximate daily cycle. |
| Tasks | Topological Data Analysis |
| Published | 2019-02-17 |
| URL | https://arxiv.org/abs/1902.06202v2 |
| https://arxiv.org/pdf/1902.06202v2.pdf | |
| PWC | https://paperswithcode.com/paper/using-persistent-homology-to-quantify-a |
| Repo | |
| Framework | |
DeepMask: an algorithm for cloud and cloud shadow detection in optical satellite remote sensing images using deep residual network
| Title | DeepMask: an algorithm for cloud and cloud shadow detection in optical satellite remote sensing images using deep residual network |
| Authors | Ke Xu, Kaiyu Guan, Jian Peng, Yunan Luo, Sibo Wang |
| Abstract | Detecting and masking cloud and cloud shadow from satellite remote sensing images is a pervasive problem in the remote sensing community. Accurate and efficient detection of cloud and cloud shadow is an essential step to harness the value of remotely sensed data for almost all downstream analysis. DeepMask, a new algorithm for cloud and cloud shadow detection in optical satellite remote sensing imagery, is proposed in this study. DeepMask utilizes ResNet, a deep convolutional neural network, for pixel-level cloud mask generation. The algorithm is trained and evaluated on the Landsat 8 Cloud Cover Assessment Validation Dataset distributed across 8 different land types. Compared with CFMask, the most widely used cloud detection algorithm, land-type-specific DeepMask models achieve higher accuracy across all land types. The average accuracy is 93.56%, compared with 85.36% from CFMask. DeepMask also achieves 91.02% accuracy on all-land-type dataset. Compared with other CNN-based cloud mask algorithms, DeepMask benefits from the parsimonious architecture and the residual connection of ResNet. It is compatible with input of any size and shape. DeepMask still maintains high performance when using only red, green, blue, and NIR bands, indicating its potential to be applied to other satellite platforms that only have limited optical bands. |
| Tasks | Cloud Detection, Shadow Detection |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03607v1 |
| https://arxiv.org/pdf/1911.03607v1.pdf | |
| PWC | https://paperswithcode.com/paper/deepmask-an-algorithm-for-cloud-and-cloud |
| Repo | |
| Framework | |
Collective Entity Alignment via Adaptive Features
| Title | Collective Entity Alignment via Adaptive Features |
| Authors | Weixin Zeng, Xiang Zhao, Jiuyang Tang, Xuemin Lin |
| Abstract | Entity alignment (EA) identifies entities that refer to the same real-world object but locate in different knowledge graphs (KGs), and has been harnessed for KG construction and integration. When generating EA results, current solutions treat entities independently and fail to take into account the interdependence between entities. To fill this gap, we propose a collective EA framework. We first employ three representative features, i.e., structural, semantic and string signals, which are adapted to capture different aspects of the similarity between entities in heterogeneous KGs. In order to make collective EA decisions, we formulate EA as the classical stable matching problem, which is further effectively solved by deferred acceptance algorithm. Our proposal is evaluated on both cross-lingual and mono-lingual EA benchmarks against state-of-the-art solutions, and the empirical results verify its effectiveness and superiority. |
| Tasks | Entity Alignment, Knowledge Graphs |
| Published | 2019-12-18 |
| URL | https://arxiv.org/abs/1912.08404v3 |
| https://arxiv.org/pdf/1912.08404v3.pdf | |
| PWC | https://paperswithcode.com/paper/collective-embedding-based-entity-alignment |
| Repo | |
| Framework | |
CUR Decompositions, Approximations, and Perturbations
| Title | CUR Decompositions, Approximations, and Perturbations |
| Authors | Keaton Hamm, Longxiu Huang |
| Abstract | This article discusses a useful tool in dimensionality reduction and low-rank matrix approximation called the CUR decomposition. Various viewpoints of this method in the literature are synergized and are compared and contrasted; included in this is a new characterization of exact CUR decompositions. A novel perturbation analysis is performed on CUR approximations of noisy versions of low-rank matrices, which compares them with the putative CUR decomposition of the underlying low-rank part. Additionally, we give new column and row sampling results which allow one to conclude that a CUR decomposition of a low-rank matrix is attained with high probability. We then illustrate the stability of these sampling methods under the perturbations studied before, and provide numerical illustrations of the methods and bounds discussed. |
| Tasks | Dimensionality Reduction |
| Published | 2019-03-22 |
| URL | http://arxiv.org/abs/1903.09698v2 |
| http://arxiv.org/pdf/1903.09698v2.pdf | |
| PWC | https://paperswithcode.com/paper/cur-decompositions-approximations-and |
| Repo | |
| Framework | |
Toward Simulating Environments in Reinforcement Learning Based Recommendations
| Title | Toward Simulating Environments in Reinforcement Learning Based Recommendations |
| Authors | Xiangyu Zhao, Long Xia, Lixin Zou, Dawei Yin, Jiliang Tang |
| Abstract | With the recent advances in Reinforcement Learning (RL), there have been tremendous interests in employing RL for recommender systems. However, directly training and evaluating a new RL-based recommendation algorithm needs to collect users’ real-time feedback in the real system, which is time and efforts consuming and could negatively impact on users’ experiences. Thus, it calls for a user simulator that can mimic real users’ behaviors where we can pre-train and evaluate new recommendation algorithms. Simulating users’ behaviors in a dynamic system faces immense challenges – (i) the underlining item distribution is complex, and (ii) historical logs for each user are limited. In this paper, we develop a user simulator base on Generative Adversarial Network (GAN). To be specific, the generator captures the underlining distribution of users’ historical logs and generates realistic logs that can be considered as augmentations of real logs; while the discriminator not only distinguishes real and fake logs but also predicts users’ behaviors. The experimental results based on real-world e-commerce data demonstrate the effectiveness of the proposed simulator. |
| Tasks | Recommendation Systems |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1906.11462v2 |
| https://arxiv.org/pdf/1906.11462v2.pdf | |
| PWC | https://paperswithcode.com/paper/toward-simulating-environments-in |
| Repo | |
| Framework | |
Characterizing Deep Learning Training Workloads on Alibaba-PAI
| Title | Characterizing Deep Learning Training Workloads on Alibaba-PAI |
| Authors | Mengdi Wang, Chen Meng, Guoping Long, Chuan Wu, Jun Yang, Wei Lin, Yangqing Jia |
| Abstract | Modern deep learning models have been exploited in various domains, including computer vision (CV), natural language processing (NLP), search and recommendation. In practical AI clusters, workloads training these models are run using software frameworks such as TensorFlow, Caffe, PyTorch and CNTK. One critical issue for efficiently operating practical AI clouds, is to characterize the computing and data transfer demands of these workloads, and more importantly, the training performance given the underlying software framework and hardware configurations. In this paper, we characterize deep learning training workloads from Platform of Artificial Intelligence (PAI) in Alibaba. We establish an analytical framework to investigate detailed execution time breakdown of various workloads using different training architectures, to identify performance bottleneck. Results show that weight/gradient communication during training takes almost 62% of the total execution time among all our workloads on average. The computation part, involving both GPU computing and memory access, are not the biggest bottleneck based on collective behavior of the workloads. We further evaluate attainable performance of the workloads on various potential software/hardware mappings, and explore implications on software architecture selection and hardware configurations. We identify that 60% of PS/Worker workloads can be potentially sped up when ported to the AllReduce architecture exploiting the high-speed NVLink for GPU interconnect, and on average 1.7X speedup can be achieved when Ethernet bandwidth is upgraded from 25 Gbps to 100 Gbps. |
| Tasks | |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.05930v1 |
| https://arxiv.org/pdf/1910.05930v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterizing-deep-learning-training |
| Repo | |
| Framework | |
Wide-Area Land Cover Mapping with Sentinel-1 Imagery using Deep Learning Semantic Segmentation Models
| Title | Wide-Area Land Cover Mapping with Sentinel-1 Imagery using Deep Learning Semantic Segmentation Models |
| Authors | Sanja Šćepanović, Oleg Antropov, Pekka Laurila, Vladimir Ignatenko, Jaan Praks |
| Abstract | Land cover mapping is essential for monitoring the environment and understanding the effects of human activities on it. The automatic approaches to land cover mapping (i.e., image segmentation) mostly used traditional machine learning. On the natural images, deep learning has outperformed traditional machine learning on a range of tasks, including the image segmentation. On remote sensing images, recent studies are demonstrating successful application of specific deep learning models or their adaptations to particular small-scale mapping tasks (e.g., to classify wetland complexes). However, it is not readily clear which of the existing models for natural images are the best candidates to be taken for the particular remote sensing task and data. In this study, we answer that question for mapping the fundamental land cover classes using the satellite imaging radar data. We took ESA Sentinel-1 C-band SAR images available at no cost to users as representative data. CORINE land cover map was used as a reference, and the models were trained to distinguish between the 5 Level-1 CORINE classes. We selected seven among the state-of-the-art semantic segmentation models so that they cover a diverse set of approaches. We used 14 ESA Sentinel-1 scenes acquired during the summer season in Finland, which are representative of the land cover in the country. Upon the benchmarking, all the models demonstrated solid performance. The best model, FC-DenseNet (Fully Convolutional DenseNets), achieved the overall accuracy of 90.7%. Overall, our results indicate that the semantic segmentation models are suitable for efficient wide-area mapping using satellite SAR imagery. Our results also provide baseline accuracy against which the newly proposed models should be evaluated and suggest the DenseNet-based models are the first candidate for this task. |
| Tasks | Image Classification, Semantic Segmentation |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05067v2 |
| https://arxiv.org/pdf/1912.05067v2.pdf | |
| PWC | https://paperswithcode.com/paper/wide-area-land-cover-mapping-with-sentinel-1 |
| Repo | |
| Framework | |
Performance Analysis of Machine Learning Techniques to Predict Diabetes Mellitus
| Title | Performance Analysis of Machine Learning Techniques to Predict Diabetes Mellitus |
| Authors | Md. Faisal Faruque, Asaduzzaman, Iqbal H. Sarker |
| Abstract | Diabetes mellitus is a common disease of human body caused by a group of metabolic disorders where the sugar levels over a prolonged period is very high. It affects different organs of the human body which thus harm a large number of the body’s system, in particular the blood veins and nerves. Early prediction in such disease can be controlled and save human life. To achieve the goal, this research work mainly explores various risk factors related to this disease using machine learning techniques. Machine learning techniques provide efficient result to extract knowledge by constructing predicting models from diagnostic medical datasets collected from the diabetic patients. Extracting knowledge from such data can be useful to predict diabetic patients. In this work, we employ four popular machine learning algorithms, namely Support Vector Machine (SVM), Naive Bayes (NB), K-Nearest Neighbor (KNN) and C4.5 Decision Tree, on adult population data to predict diabetic mellitus. Our experimental results show that C4.5 decision tree achieved higher accuracy compared to other machine learning techniques. |
| Tasks | |
| Published | 2019-01-10 |
| URL | http://arxiv.org/abs/1902.10028v1 |
| http://arxiv.org/pdf/1902.10028v1.pdf | |
| PWC | https://paperswithcode.com/paper/performance-analysis-of-machine-learning |
| Repo | |
| Framework | |
Adversarial Robustness Guarantees for Classification with Gaussian Processes
| Title | Adversarial Robustness Guarantees for Classification with Gaussian Processes |
| Authors | Arno Blaas, Andrea Patane, Luca Laurenti, Luca Cardelli, Marta Kwiatkowska, Stephen Roberts |
| Abstract | We investigate adversarial robustness of Gaussian Process Classification (GPC) models. Given a compact subset of the input space $T\subseteq \mathbb{R}^d$ enclosing a test point $x^*$ and a GPC trained on a dataset $\mathcal{D}$, we aim to compute the minimum and the maximum classification probability for the GPC over all the points in $T$. In order to do so, we show how functions lower- and upper-bounding the GPC output in $T$ can be derived, and implement those in a branch and bound optimisation algorithm. For any error threshold $\epsilon > 0$ selected a priori, we show that our algorithm is guaranteed to reach values $\epsilon$-close to the actual values in finitely many iterations. We apply our method to investigate the robustness of GPC models on a 2D synthetic dataset, the SPAM dataset and a subset of the MNIST dataset, providing comparisons of different GPC training techniques, and show how our method can be used for interpretability analysis. Our empirical analysis suggests that GPC robustness increases with more accurate posterior estimation. |
| Tasks | Gaussian Processes |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11876v3 |
| https://arxiv.org/pdf/1905.11876v3.pdf | |
| PWC | https://paperswithcode.com/paper/robustness-quantification-for-classification |
| Repo | |
| Framework | |
Leveraging Uncertainty in Deep Learning for Selective Classification
| Title | Leveraging Uncertainty in Deep Learning for Selective Classification |
| Authors | Mehmet Yigit Yildirim, Mert Ozer, Hasan Davulcu |
| Abstract | The wide and rapid adoption of deep learning by practitioners brought unintended consequences in many situations such as in the infamous case of Google Photos’ racist image recognition algorithm; thus, necessitated the utilization of the quantified uncertainty for each prediction. There have been recent efforts towards quantifying uncertainty in conventional deep learning methods (e.g., dropout as Bayesian approximation); however, their optimal use in decision making is often overlooked and understudied. In this study, we propose a mixed-integer programming framework for classification with reject option (also known as selective classification), that investigates and combines model uncertainty and predictive mean to identify optimal classification and rejection regions. Our results indicate superior performance of our framework both in non-rejected accuracy and rejection quality on several publicly available datasets. Moreover, we extend our framework to cost-sensitive settings and show that our approach outperforms industry standard methods significantly for online fraud management in real-world settings. |
| Tasks | Decision Making |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09509v1 |
| https://arxiv.org/pdf/1905.09509v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-uncertainty-in-deep-learning-for |
| Repo | |
| Framework | |
