Paper Group ANR 1184
Evaluating MAP-Elites on Constrained Optimization Problems. Efficient Semi-Supervised Learning for Natural Language Understanding by Optimizing Diversity. An Online Evolving Framework for Modeling the Safe Autonomous Vehicle Control System via Online Recognition of Latent Risks. Automated Rib Fracture Detection of Postmortem Computed Tomography Ima …
Evaluating MAP-Elites on Constrained Optimization Problems
| Title | Evaluating MAP-Elites on Constrained Optimization Problems |
| Authors | Stefano Fioravanzo, Giovanni Iacca |
| Abstract | Constrained optimization problems are often characterized by multiple constraints that, in the practice, must be satisfied with different tolerance levels. While some constraints are hard and as such must be satisfied with zero-tolerance, others may be soft, such that non-zero violations are acceptable. Here, we evaluate the applicability of MAP-Elites to “illuminate” constrained search spaces by mapping them into feature spaces where each feature corresponds to a different constraint. On the one hand, MAP-Elites implicitly preserves diversity, thus allowing a good exploration of the search space. On the other hand, it provides an effective visualization that facilitates a better understanding of how constraint violations correlate with the objective function. We demonstrate the feasibility of this approach on a large set of benchmark problems, in various dimensionalities, and with different algorithmic configurations. As expected, numerical results show that a basic version of MAP-Elites cannot compete on all problems (especially those with equality constraints) with state-of-the-art algorithms that use gradient information or advanced constraint handling techniques. Nevertheless, it has a higher potential at finding constraint violations vs. objectives trade-offs and providing new problem information. As such, it could be used in the future as an effective building-block for designing new constrained optimization algorithms. |
| Tasks | |
| Published | 2019-02-02 |
| URL | http://arxiv.org/abs/1902.00703v4 |
| http://arxiv.org/pdf/1902.00703v4.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-map-elites-on-constrained |
| Repo | |
| Framework | |
Efficient Semi-Supervised Learning for Natural Language Understanding by Optimizing Diversity
| Title | Efficient Semi-Supervised Learning for Natural Language Understanding by Optimizing Diversity |
| Authors | Eunah Cho, He Xie, John P. Lalor, Varun Kumar, William M. Campbell |
| Abstract | Expanding new functionalities efficiently is an ongoing challenge for single-turn task-oriented dialogue systems. In this work, we explore functionality-specific semi-supervised learning via self-training. We consider methods that augment training data automatically from unlabeled data sets in a functionality-targeted manner. In addition, we examine multiple techniques for efficient selection of augmented utterances to reduce training time and increase diversity. First, we consider paraphrase detection methods that attempt to find utterance variants of labeled training data with good coverage. Second, we explore sub-modular optimization based on n-grams features for utterance selection. Experiments show that functionality-specific self-training is very effective for improving system performance. In addition, methods optimizing diversity can reduce training data in many cases to 50% with little impact on performance. |
| Tasks | Task-Oriented Dialogue Systems |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04196v1 |
| https://arxiv.org/pdf/1910.04196v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-semi-supervised-learning-for |
| Repo | |
| Framework | |
An Online Evolving Framework for Modeling the Safe Autonomous Vehicle Control System via Online Recognition of Latent Risks
| Title | An Online Evolving Framework for Modeling the Safe Autonomous Vehicle Control System via Online Recognition of Latent Risks |
| Authors | Teawon Han, Dimitar Filev, Umit Ozguner |
| Abstract | An online evolving framework is proposed to support modeling the safe Automated Vehicle (AV) control system by making the controller able to recognize unexpected situations and react appropriately by choosing a better action. Within the framework, the evolving Finite State Machine (e-FSM), which is an online model able to (1) determine states uniquely as needed, (2) recognize states, and (3) identify state-transitions, is introduced. In this study, the e-FSM’s capabilities are explained and illustrated by simulating a simple car-following scenario. As a vehicle controller, the Intelligent Driver Model (IDM) is implemented, and different sets of IDM parameters are assigned to the following vehicle for simulating various situations (including the collision). While simulating the car-following scenario, e-FSM recognizes and determines the states and identifies the transition matrices by suggested methods. To verify if e-FSM can recognize and determine states uniquely, we analyze whether the same state is recognized under the identical situation. The difference between probability distributions of predicted and recognized states is measured by the Jensen-Shannon divergence (JSD) method to validate the accuracy of identified transition-matrices. As shown in the results, the Dead-End state which has latent-risk of the collision is uniquely determined and consistently recognized. Also, the probability distributions of the predicted state are significantly similar to the recognized state, declaring that the state-transitions are precisely identified. |
| Tasks | |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10823v1 |
| https://arxiv.org/pdf/1908.10823v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-online-evolving-framework-for-modeling-the |
| Repo | |
| Framework | |
Automated Rib Fracture Detection of Postmortem Computed Tomography Images Using Machine Learning Techniques
| Title | Automated Rib Fracture Detection of Postmortem Computed Tomography Images Using Machine Learning Techniques |
| Authors | Samuel Gunz, Svenja Erne, Eric J. Rawdon, Garyfalia Ampanozi, Till Sieberth, Raffael Affolter, Lars C. Ebert, Akos Dobay |
| Abstract | Imaging techniques is widely used for medical diagnostics. This leads in some cases to a real bottleneck when there is a lack of medical practitioners and the images have to be manually processed. In such a situation there is a need to reduce the amount of manual work by automating part of the analysis. In this article, we investigate the potential of a machine learning algorithm for medical image processing by computing a topological invariant classifier. First, we select retrospectively from our database of postmortem computed tomography images of rib fractures. The images are prepared by applying a rib unfolding tool that flattens the rib cage to form a two-dimensional projection. We compare the results of our analysis with two independent convolutional neural network models. In the case of the neural network model, we obtain an $F_1$ Score of 0.73. To access the performance of our classifier, we compute the relative proportion of images that were not shared between the two classes. We obtain a precision of 0.60 for the images with rib fractures. |
| Tasks | |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05467v1 |
| https://arxiv.org/pdf/1908.05467v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-rib-fracture-detection-of |
| Repo | |
| Framework | |
GraspNet: A Large-Scale Clustered and Densely Annotated Dataset for Object Grasping
| Title | GraspNet: A Large-Scale Clustered and Densely Annotated Dataset for Object Grasping |
| Authors | Hao-Shu Fang, Chenxi Wang, Minghao Gou, Cewu Lu |
| Abstract | Object grasping is critical for many applications, which is also a challenging computer vision problem. However, for the clustered scene, current researches suffer from the problems of insufficient training data and the lacking of evaluation benchmarks. In this work, we contribute a large-scale grasp pose detection dataset with a unified evaluation system. Our dataset contains 87,040 RGBD images with over 370 million grasp poses. Meanwhile, our evaluation system directly reports whether a grasping is successful or not by analytic computation, which is able to evaluate any kind of grasp poses without exhausted labeling pose ground-truth. We conduct extensive experiments to show that our dataset and evaluation system can align well with real-world experiments. Our dataset, source code and models will be made publicly available. |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/1912.13470v2 |
| https://arxiv.org/pdf/1912.13470v2.pdf | |
| PWC | https://paperswithcode.com/paper/graspnet-a-large-scale-clustered-and-densely |
| Repo | |
| Framework | |
Construction of the similarity matrix for the spectral clustering method: numerical experiments
| Title | Construction of the similarity matrix for the spectral clustering method: numerical experiments |
| Authors | Paola Favati, Grazia Lotti, Ornella Menchi, Francesco Romani |
| Abstract | Spectral clustering is a powerful method for finding structure in a dataset through the eigenvectors of a similarity matrix. It often outperforms traditional clustering algorithms such as $k$-means when the structure of the individual clusters is highly non-convex. Its accuracy depends on how the similarity between pairs of data points is defined. Two important items contribute to the construction of the similarity matrix: the sparsity of the underlying weighted graph, which depends mainly on the distances among data points, and the similarity function. When a Gaussian similarity function is used, the choice of the scale parameter $\sigma$ can be critical. In this paper we examine both items, the sparsity and the selection of suitable $\sigma$'s, based either directly on the graph associated to the dataset or on the minimal spanning tree (MST) of the graph. An extensive numerical experimentation on artificial and real-world datasets has been carried out to compare the performances of the methods. |
| Tasks | |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1904.11352v1 |
| http://arxiv.org/pdf/1904.11352v1.pdf | |
| PWC | https://paperswithcode.com/paper/construction-of-the-similarity-matrix-for-the |
| Repo | |
| Framework | |
On-line and on-board planning and perception for quadrupedal locomotion
| Title | On-line and on-board planning and perception for quadrupedal locomotion |
| Authors | Carlos Mastalli, Ioannis Havoutis, Alexander W. Winkler, Darwin G. Caldwell, Claudio Semini |
| Abstract | We present a legged motion planning approach for quadrupedal locomotion over challenging terrain. We decompose the problem into body action planning and footstep planning. We use a lattice representation together with a set of defined body movement primitives for computing a body action plan. The lattice representation allows us to plan versatile movements that ensure feasibility for every possible plan. To this end, we propose a set of rules that define the footstep search regions and footstep sequence given a body action. We use Anytime Repairing A* (ARA*) search that guarantees bounded suboptimal plans. Our main contribution is a planning approach that generates on-line versatile movements. Experimental trials demonstrate the performance of our planning approach in a set of challenging terrain conditions. The terrain information and plans are computed on-line and on-board. |
| Tasks | Motion Planning |
| Published | 2019-04-07 |
| URL | http://arxiv.org/abs/1904.03693v1 |
| http://arxiv.org/pdf/1904.03693v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-line-and-on-board-planning-and-perception |
| Repo | |
| Framework | |
Utilizing the Instability in Weakly Supervised Object Detection
| Title | Utilizing the Instability in Weakly Supervised Object Detection |
| Authors | Yan Gao, Boxiao Liu, Nan Guo, Xiaochun Ye, Fang Wan, Haihang You, Dongrui Fan |
| Abstract | Weakly supervised object detection (WSOD) focuses on training object detector with only image-level annotations, and is challenging due to the gap between the supervision and the objective. Most of existing approaches model WSOD as a multiple instance learning (MIL) problem. However, we observe that the result of MIL based detector is unstable, i.e., the most confident bounding boxes change significantly when using different initializations. We quantitatively demonstrate the instability by introducing a metric to measure it, and empirically analyze the reason of instability. Although the instability seems harmful for detection task, we argue that it can be utilized to improve the performance by fusing the results of differently initialized detectors. To implement this idea, we propose an end-to-end framework with multiple detection branches, and introduce a simple fusion strategy. We further propose an orthogonal initialization method to increase the difference between detection branches. By utilizing the instability, we achieve 52.6% and 48.0% mAP on the challenging PASCAL VOC 2007 and 2012 datasets, which are both the new state-of-the-arts. |
| Tasks | Multiple Instance Learning, Object Detection, Weakly Supervised Object Detection |
| Published | 2019-06-14 |
| URL | https://arxiv.org/abs/1906.06023v1 |
| https://arxiv.org/pdf/1906.06023v1.pdf | |
| PWC | https://paperswithcode.com/paper/utilizing-the-instability-in-weakly |
| Repo | |
| Framework | |
Automatic Classification of Pathology Reports using TF-IDF Features
| Title | Automatic Classification of Pathology Reports using TF-IDF Features |
| Authors | Shivam Kalra, Larry Li, Hamid R. Tizhoosh |
| Abstract | A Pathology report is arguably one of the most important documents in medicine containing interpretive information about the visual findings from the patient’s biopsy sample. Each pathology report has a retention period of up to 20 years after the treatment of a patient. Cancer registries process and encode high volumes of free-text pathology reports for surveillance of cancer and tumor diseases all across the world. In spite of their extremely valuable information they hold, pathology reports are not used in any systematic way to facilitate computational pathology. Therefore, in this study, we investigate automated machine-learning techniques to identify/predict the primary diagnosis (based on ICD-O code) from pathology reports. We performed experiments by extracting the TF-IDF features from the reports and classifying them using three different methods—SVM, XGBoost, and Logistic Regression. We constructed a new dataset with 1,949 pathology reports arranged into 37 ICD-O categories, collected from four different primary sites, namely lung, kidney, thymus, and testis. The reports were manually transcribed into text format after collecting them as PDF files from NCI Genomic Data Commons public dataset. We subsequently pre-processed the reports by removing irrelevant textual artifacts produced by OCR software. The highest classification accuracy we achieved was 92% using XGBoost classifier on TF-IDF feature vectors, the linear SVM scored 87% accuracy. Furthermore, the study shows that TF-IDF vectors are suitable for highlighting the important keywords within a report which can be helpful for the cancer research and diagnostic workflow. The results are encouraging in demonstrating the potential of machine learning methods for classification and encoding of pathology reports. |
| Tasks | Optical Character Recognition |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.07406v1 |
| http://arxiv.org/pdf/1903.07406v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-classification-of-pathology-reports |
| Repo | |
| Framework | |
Explaining Anomalies Detected by Autoencoders Using SHAP
| Title | Explaining Anomalies Detected by Autoencoders Using SHAP |
| Authors | Liat Antwarg, Bracha Shapira, Lior Rokach |
| Abstract | Anomaly detection algorithms are often thought to be limited because they don’t facilitate the process of validating results performed by domain experts. In Contrast, deep learning algorithms for anomaly detection, such as autoencoders, point out the outliers, saving experts the time-consuming task of examining normal cases in order to find anomalies. Most outlier detection algorithms output a score for each instance in the database. The top-k most intense outliers are returned to the user for further inspection; however the manual validation of results becomes challenging without additional clues. An explanation of why an instance is anomalous enables the experts to focus their investigation on most important anomalies and may increase their trust in the algorithm. Recently, a game theory-based framework known as SHapley Additive exPlanations (SHAP) has been shown to be effective in explaining various supervised learning models. In this research, we extend SHAP to explain anomalies detected by an autoencoder, an unsupervised model. The proposed method extracts and visually depicts both the features that most contributed to the anomaly and those that offset it. A preliminary experimental study using real world data demonstrates the usefulness of the proposed method in assisting the domain experts to understand the anomaly and filtering out the uninteresting anomalies, aiming at minimizing the false positive rate of detected anomalies. |
| Tasks | Anomaly Detection, Outlier Detection |
| Published | 2019-03-06 |
| URL | http://arxiv.org/abs/1903.02407v1 |
| http://arxiv.org/pdf/1903.02407v1.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-anomalies-detected-by-autoencoders |
| Repo | |
| Framework | |
Implementation of batched Sinkhorn iterations for entropy-regularized Wasserstein loss
| Title | Implementation of batched Sinkhorn iterations for entropy-regularized Wasserstein loss |
| Authors | Thomas Viehmann |
| Abstract | In this report, we review the calculation of entropy-regularised Wasserstein loss introduced by Cuturi and document a practical implementation in PyTorch. Code is available at https://github.com/t-vi/pytorch-tvmisc/blob/master/wasserstein-distance/Pytorch_Wasserstein.ipynb |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.01729v2 |
| https://arxiv.org/pdf/1907.01729v2.pdf | |
| PWC | https://paperswithcode.com/paper/implementation-of-batched-sinkhorn-iterations |
| Repo | |
| Framework | |
LSTM-based Flow Prediction
| Title | LSTM-based Flow Prediction |
| Authors | Hongzhi Wang, Yang Song, Shihan Tang |
| Abstract | In this paper, a method of prediction on continuous time series variables from the production or flow – an LSTM algorithm based on multivariate tuning – is proposed. The algorithm improves the traditional LSTM algorithm and converts the time series data into supervised learning sequences regarding industrial data’s features. The main innovation of this paper consists in introducing the concepts of periodic measurement and time window in the industrial prediction problem, especially considering industrial data with time series characteristics. Experiments using real-world datasets show that the prediction accuracy is improved, 54.05% higher than that of traditional LSTM algorithm. |
| Tasks | Time Series |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03571v1 |
| https://arxiv.org/pdf/1908.03571v1.pdf | |
| PWC | https://paperswithcode.com/paper/lstm-based-flow-prediction |
| Repo | |
| Framework | |
Probability Logic
| Title | Probability Logic |
| Authors | Niki Pfeifer |
| Abstract | This chapter presents probability logic as a rationality framework for human reasoning under uncertainty. Selected formal-normative aspects of probability logic are discussed in the light of experimental evidence. Specifically, probability logic is characterized as a generalization of bivalent truth-functional propositional logic (short “logic”), as being connexive, and as being nonmonotonic. The chapter discusses selected argument forms and associated uncertainty propagation rules. Throughout the chapter, the descriptive validity of probability logic is compared to logic, which was used as the gold standard of reference for assessing the rationality of human reasoning in the 20th century. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06624v1 |
| https://arxiv.org/pdf/1910.06624v1.pdf | |
| PWC | https://paperswithcode.com/paper/probability-logic |
| Repo | |
| Framework | |
Companion Surface of Danger Cylinder and its Role in Solution Variation of P3P Problem
| Title | Companion Surface of Danger Cylinder and its Role in Solution Variation of P3P Problem |
| Authors | Bo wang, Hao Hu, Caixia Zhang |
| Abstract | Traditionally the danger cylinder is intimately related to the solution stability in P3P problem. In this work, we show that the danger cylinder is also closely related to the multiple-solution phenomenon. More specifically, we show when the optical center lies on the danger cylinder, of the 3 possible P3P solutions, i.e., one double solution, and two other solutions, the optical center of the double solution still lies on the danger cylinder, but the optical centers of the other two solutions no longer lie on the danger cylinder. And when the optical center moves on the danger cylinder, accordingly the optical centers of the two other solutions of the corresponding P3P problem form a new surface, characterized by a polynomial equation of degree 12 in the optical center coordinates, called the Companion Surface of Danger Cylinder (CSDC). That means the danger cylinder always has a companion surface. For the significance of CSDC, we show that when the optical center passes through the CSDC, the number of solutions of P3P problem must change by 2. That means CSDC acts as a delimitating surface of the P3P solution space. These new findings shed some new lights on the P3P multi-solution phenomenon, an important issue in PnP study. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.08598v1 |
| https://arxiv.org/pdf/1906.08598v1.pdf | |
| PWC | https://paperswithcode.com/paper/companion-surface-of-danger-cylinder-and-its |
| Repo | |
| Framework | |
Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency
| Title | Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency |
| Authors | Guillaume Rochette, Chris Russell, Richard Bowden |
| Abstract | We present a novel data-driven regularizer for weakly-supervised learning of 3D human pose estimation that eliminates the drift problem that affects existing approaches. We do this by moving the stereo reconstruction problem into the loss of the network itself. This avoids the need to reconstruct 3D data prior to training and unlike previous semi-supervised approaches, avoids the need for a warm-up period of supervised training. The conceptual and implementational simplicity of our approach is fundamental to its appeal. Not only is it straightforward to augment many weakly-supervised approaches with our additional re-projection based loss, but it is obvious how it shapes reconstructions and prevents drift. As such we believe it will be a valuable tool for any researcher working in weakly-supervised 3D reconstruction. Evaluating on Panoptic, the largest multi-camera and markerless dataset available, we obtain an accuracy that is essentially indistinguishable from a strongly-supervised approach making full use of 3D groundtruth in training. |
| Tasks | 3D Human Pose Estimation, 3D Pose Estimation, 3D Reconstruction, Pose Estimation |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06119v1 |
| https://arxiv.org/pdf/1909.06119v1.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-3d-pose-estimation-from-a |
| Repo | |
| Framework | |
