Paper Group ANR 393
Consequence-based Reasoning for Description Logics with Disjunction, Inverse Roles, Number Restrictions, and Nominals. The modal age of Statistics. Integrated Object Detection and Tracking with Tracklet-Conditioned Detection. Fine-grained Video Attractiveness Prediction Using Multimodal Deep Learning on a Large Real-world Dataset. Segmentation of A …
Consequence-based Reasoning for Description Logics with Disjunction, Inverse Roles, Number Restrictions, and Nominals
Title | Consequence-based Reasoning for Description Logics with Disjunction, Inverse Roles, Number Restrictions, and Nominals |
Authors | David Tena Cucala, Bernardo Cuenca Grau, Ian Horrocks |
Abstract | We present a consequence-based calculus for concept subsumption and classification in the description logic ALCHOIQ, which extends ALC with role hierarchies, inverse roles, number restrictions, and nominals. By using standard transformations, our calculus extends to SROIQ, which covers all of OWL 2 DL except for datatypes. A key feature of our calculus is its pay-as-you-go behaviour: unlike existing algorithms, our calculus is worst-case optimal for all the well-known proper fragments of ALCHOIQ, albeit not for the full logic. |
Tasks | |
Published | 2018-05-03 |
URL | http://arxiv.org/abs/1805.01396v1 |
http://arxiv.org/pdf/1805.01396v1.pdf | |
PWC | https://paperswithcode.com/paper/consequence-based-reasoning-for-description |
Repo | |
Framework | |
The modal age of Statistics
Title | The modal age of Statistics |
Authors | José E. Chacón |
Abstract | Recently, a number of statistical problems have found an unexpected solution by inspecting them through a “modal point of view”. These include classical tasks such as clustering or regression. This has led to a renewed interest in estimation and inference for the mode. This paper offers an extensive survey of the traditional approaches to mode estimation and explores the consequences of applying this modern modal methodology to other, seemingly unrelated, fields. |
Tasks | |
Published | 2018-07-08 |
URL | http://arxiv.org/abs/1807.02789v1 |
http://arxiv.org/pdf/1807.02789v1.pdf | |
PWC | https://paperswithcode.com/paper/the-modal-age-of-statistics |
Repo | |
Framework | |
Integrated Object Detection and Tracking with Tracklet-Conditioned Detection
Title | Integrated Object Detection and Tracking with Tracklet-Conditioned Detection |
Authors | Zheng Zhang, Dazhi Cheng, Xizhou Zhu, Stephen Lin, Jifeng Dai |
Abstract | Accurate detection and tracking of objects is vital for effective video understanding. In previous work, the two tasks have been combined in a way that tracking is based heavily on detection, but the detection benefits marginally from the tracking. To increase synergy, we propose to more tightly integrate the tasks by conditioning the object detection in the current frame on tracklets computed in prior frames. With this approach, the object detection results not only have high detection responses, but also improved coherence with the existing tracklets. This greater coherence leads to estimated object trajectories that are smoother and more stable than the jittered paths obtained without tracklet-conditioned detection. Over extensive experiments, this approach is shown to achieve state-of-the-art performance in terms of both detection and tracking accuracy, as well as noticeable improvements in tracking stability. |
Tasks | Object Detection, Video Object Detection, Video Understanding |
Published | 2018-11-27 |
URL | http://arxiv.org/abs/1811.11167v1 |
http://arxiv.org/pdf/1811.11167v1.pdf | |
PWC | https://paperswithcode.com/paper/integrated-object-detection-and-tracking-with |
Repo | |
Framework | |
Fine-grained Video Attractiveness Prediction Using Multimodal Deep Learning on a Large Real-world Dataset
Title | Fine-grained Video Attractiveness Prediction Using Multimodal Deep Learning on a Large Real-world Dataset |
Authors | Xinpeng Chen, Jingyuan Chen, Lin Ma, Jian Yao, Wei Liu, Jiebo Luo, Tong Zhang |
Abstract | Nowadays, billions of videos are online ready to be viewed and shared. Among an enormous volume of videos, some popular ones are widely viewed by online users while the majority attract little attention. Furthermore, within each video, different segments may attract significantly different numbers of views. This phenomenon leads to a challenging yet important problem, namely fine-grained video attractiveness prediction. However, one major obstacle for such a challenging problem is that no suitable benchmark dataset currently exists. To this end, we construct the first fine-grained video attractiveness dataset, which is collected from one of the most popular video websites in the world. In total, the constructed FVAD consists of 1,019 drama episodes with 780.6 hours covering different categories and a wide variety of video contents. Apart from the large amount of videos, hundreds of millions of user behaviors during watching videos are also included, such as “view counts”, “fast-forward”, “fast-rewind”, and so on, where “view counts” reflects the video attractiveness while other engagements capture the interactions between the viewers and videos. First, we demonstrate that video attractiveness and different engagements present different relationships. Second, FVAD provides us an opportunity to study the fine-grained video attractiveness prediction problem. We design different sequential models to perform video attractiveness prediction by relying solely on video contents. The sequential models exploit the multimodal relationships between visual and audio components of the video contents at different levels. Experimental results demonstrate the effectiveness of our proposed sequential models with different visual and audio representations, the necessity of incorporating the two modalities, and the complementary behaviors of the sequential prediction models at different levels. |
Tasks | |
Published | 2018-04-04 |
URL | http://arxiv.org/abs/1804.01373v2 |
http://arxiv.org/pdf/1804.01373v2.pdf | |
PWC | https://paperswithcode.com/paper/fine-grained-video-attractiveness-prediction |
Repo | |
Framework | |
Segmentation of Arterial Walls in Intravascular Ultrasound Cross-Sectional Images Using Extremal Region Selection
Title | Segmentation of Arterial Walls in Intravascular Ultrasound Cross-Sectional Images Using Extremal Region Selection |
Authors | Mehdi Faraji, Irene Cheng, Iris Naudin, Anup Basu |
Abstract | Intravascular Ultrasound (IVUS) is an intra-operative imaging modality that facilitates observing and appraising the vessel wall structure of the human coronary arteries. Segmentation of arterial wall boundaries from the IVUS images is not only crucial for quantitative analysis of the vessel walls and plaque characteristics, but is also necessary for generating 3D reconstructed models of the artery. The aim of this study is twofold. Firstly, we investigate the feasibility of using a recently proposed region detector, namely Extremal Region of Extremum Level (EREL) to delineate the luminal and media-adventitia borders in IVUS frames acquired by 20 MHz probes. Secondly, we propose a region selection strategy to label two ERELs as lumen and media based on the stability of their textural information. We extensively evaluated our selection strategy on the test set of a standard publicly available dataset containing 326 IVUS B-mode images. We showed that in the best case, the average Hausdorff Distances (HD) between the extracted ERELs and the actual lumen and media were $0.22$ mm and $0.45$ mm, respectively. The results of our experiments revealed that our selection strategy was able to segment the lumen with $\le 0.3$ mm HD to the gold standard even though the images contained major artifacts such as bifurcations, shadows, and side branches. Moreover, when there was no artifact, our proposed method was able to delineate media-adventitia boundaries with $0.31$ mm HD to the gold standard. Furthermore, our proposed segmentation method runs in time that is linear in the number of pixels in each frame. Based on the results of this work, by using a 20 MHz IVUS probe with controlled pullback, not only can we now analyze the internal structure of human arteries more accurately, but also segment each frame during the pullback procedure because of the low run time of our proposed segmentation method. |
Tasks | |
Published | 2018-06-10 |
URL | http://arxiv.org/abs/1806.03695v1 |
http://arxiv.org/pdf/1806.03695v1.pdf | |
PWC | https://paperswithcode.com/paper/segmentation-of-arterial-walls-in |
Repo | |
Framework | |
Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back
Title | Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back |
Authors | Elliot Meyerson, Risto Miikkulainen |
Abstract | Deep multitask learning boosts performance by sharing learned structure across related tasks. This paper adapts ideas from deep multitask learning to the setting where only a single task is available. The method is formalized as pseudo-task augmentation, in which models are trained with multiple decoders for each task. Pseudo-tasks simulate the effect of training towards closely-related tasks drawn from the same universe. In a suite of experiments, pseudo-task augmentation is shown to improve performance on single-task learning problems. When combined with multitask learning, further improvements are achieved, including state-of-the-art performance on the CelebA dataset, showing that pseudo-task augmentation and multitask learning have complementary value. All in all, pseudo-task augmentation is a broadly applicable and efficient way to boost performance in deep learning systems. |
Tasks | |
Published | 2018-03-11 |
URL | http://arxiv.org/abs/1803.04062v2 |
http://arxiv.org/pdf/1803.04062v2.pdf | |
PWC | https://paperswithcode.com/paper/pseudo-task-augmentation-from-deep-multitask |
Repo | |
Framework | |
Credit Default Mining Using Combined Machine Learning and Heuristic Approach
Title | Credit Default Mining Using Combined Machine Learning and Heuristic Approach |
Authors | Sheikh Rabiul Islam, William Eberle, Sheikh Khaled Ghafoor |
Abstract | Predicting potential credit default accounts in advance is challenging. Traditional statistical techniques typically cannot handle large amounts of data and the dynamic nature of fraud and humans. To tackle this problem, recent research has focused on artificial and computational intelligence based approaches. In this work, we present and validate a heuristic approach to mine potential default accounts in advance where a risk probability is precomputed from all previous data and the risk probability for recent transactions are computed as soon they happen. Beside our heuristic approach, we also apply a recently proposed machine learning approach that has not been applied previously on our targeted dataset [15]. As a result, we find that these applied approaches outperform existing state-of-the-art approaches. |
Tasks | |
Published | 2018-07-02 |
URL | http://arxiv.org/abs/1807.01176v1 |
http://arxiv.org/pdf/1807.01176v1.pdf | |
PWC | https://paperswithcode.com/paper/credit-default-mining-using-combined-machine |
Repo | |
Framework | |
SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
Title | SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification |
Authors | Xing Fan, Wei Jiang, Hao Luo, Mengjuan Fei |
Abstract | Many current successful Person Re-Identification(ReID) methods train a model with the softmax loss function to classify images of different persons and obtain the feature vectors at the same time. However, the underlying feature embedding space is ignored. In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously. A balanced sampling strategy is also introduced. Finally, we propose a convolutional neural network called SphereReID adopting Sphere Softmax and training a single model end-to-end with a new warming-up learning rate schedule on four challenging datasets including Market-1501, DukeMTMC-reID, CHHK-03, and CUHK-SYSU. Experimental results demonstrate that this single model outperforms the state-of-the-art methods on all four datasets without fine-tuning or re-ranking. For example, it achieves 94.4% rank-1 accuracy on Market-1501 and 83.9% rank-1 accuracy on DukeMTMC-reID. The code and trained weights of our model will be released. |
Tasks | Person Re-Identification |
Published | 2018-07-02 |
URL | http://arxiv.org/abs/1807.00537v1 |
http://arxiv.org/pdf/1807.00537v1.pdf | |
PWC | https://paperswithcode.com/paper/spherereid-deep-hypersphere-manifold |
Repo | |
Framework | |
Non-Linear Temporal Subspace Representations for Activity Recognition
Title | Non-Linear Temporal Subspace Representations for Activity Recognition |
Authors | Anoop Cherian, Suvrit Sra, Stephen Gould, Richard Hartley |
Abstract | Representations that can compactly and effectively capture the temporal evolution of semantic content are important to computer vision and machine learning algorithms that operate on multi-variate time-series data. We investigate such representations motivated by the task of human action recognition. Here each data instance is encoded by a multivariate feature (such as via a deep CNN) where action dynamics are characterized by their variations in time. As these features are often non-linear, we propose a novel pooling method, kernelized rank pooling, that represents a given sequence compactly as the pre-image of the parameters of a hyperplane in a reproducing kernel Hilbert space, projections of data onto which captures their temporal order. We develop this idea further and show that such a pooling scheme can be cast as an order-constrained kernelized PCA objective. We then propose to use the parameters of a kernelized low-rank feature subspace as the representation of the sequences. We cast our formulation as an optimization problem on generalized Grassmann manifolds and then solve it efficiently using Riemannian optimization techniques. We present experiments on several action recognition datasets using diverse feature modalities and demonstrate state-of-the-art results. |
Tasks | Activity Recognition, Temporal Action Localization, Time Series |
Published | 2018-03-27 |
URL | http://arxiv.org/abs/1803.11064v1 |
http://arxiv.org/pdf/1803.11064v1.pdf | |
PWC | https://paperswithcode.com/paper/non-linear-temporal-subspace-representations |
Repo | |
Framework | |
Attack Strength vs. Detectability Dilemma in Adversarial Machine Learning
Title | Attack Strength vs. Detectability Dilemma in Adversarial Machine Learning |
Authors | Christopher Frederickson, Michael Moore, Glenn Dawson, Robi Polikar |
Abstract | As the prevalence and everyday use of machine learning algorithms, along with our reliance on these algorithms grow dramatically, so do the efforts to attack and undermine these algorithms with malicious intent, resulting in a growing interest in adversarial machine learning. A number of approaches have been developed that can render a machine learning algorithm ineffective through poisoning or other types of attacks. Most attack algorithms typically use sophisticated optimization approaches, whose objective function is designed to cause maximum damage with respect to accuracy and performance of the algorithm with respect to some task. In this effort, we show that while such an objective function is indeed brutally effective in causing maximum damage on an embedded feature selection task, it often results in an attack mechanism that can be easily detected with an embarrassingly simple novelty or outlier detection algorithm. We then propose an equally simple yet elegant solution by adding a regularization term to the attacker’s objective function that penalizes outlying attack points. |
Tasks | Feature Selection, Outlier Detection |
Published | 2018-02-20 |
URL | http://arxiv.org/abs/1802.07295v1 |
http://arxiv.org/pdf/1802.07295v1.pdf | |
PWC | https://paperswithcode.com/paper/attack-strength-vs-detectability-dilemma-in |
Repo | |
Framework | |
Outlier Detection for Robust Multi-dimensional Scaling
Title | Outlier Detection for Robust Multi-dimensional Scaling |
Authors | Leonid Blouvshtein, Daniel Cohen-Or |
Abstract | Multi-dimensional scaling (MDS) plays a central role in data-exploration, dimensionality reduction and visualization. State-of-the-art MDS algorithms are not robust to outliers, yielding significant errors in the embedding even when only a handful of outliers are present. In this paper, we introduce a technique to detect and filter outliers based on geometric reasoning. We test the validity of triangles formed by three points, and mark a triangle as broken if its triangle inequality does not hold. The premise of our work is that unlike inliers, outlier distances tend to break many triangles. Our method is tested and its performance is evaluated on various datasets and distributions of outliers. We demonstrate that for a reasonable amount of outliers, e.g., under $20%$, our method is effective, and leads to a high embedding quality. |
Tasks | Dimensionality Reduction, Outlier Detection |
Published | 2018-02-07 |
URL | http://arxiv.org/abs/1802.02341v1 |
http://arxiv.org/pdf/1802.02341v1.pdf | |
PWC | https://paperswithcode.com/paper/outlier-detection-for-robust-multi |
Repo | |
Framework | |
Image Reassembly Combining Deep Learning and Shortest Path Problem
Title | Image Reassembly Combining Deep Learning and Shortest Path Problem |
Authors | M. -M. Paumard, D. Picard, H. Tabia |
Abstract | This paper addresses the problem of reassembling images from disjointed fragments. More specifically, given an unordered set of fragments, we aim at reassembling one or several possibly incomplete images. The main contributions of this work are: 1) several deep neural architectures to predict the relative position of image fragments that outperform the previous state of the art; 2) casting the reassembly problem into the shortest path in a graph problem for which we provide several construction algorithms depending on available information; 3) a new dataset of images taken from the Metropolitan Museum of Art (MET) dedicated to image reassembly for which we provide a clear setup and a strong baseline. |
Tasks | |
Published | 2018-09-04 |
URL | http://arxiv.org/abs/1809.00898v1 |
http://arxiv.org/pdf/1809.00898v1.pdf | |
PWC | https://paperswithcode.com/paper/image-reassembly-combining-deep-learning-and |
Repo | |
Framework | |
Overcoming Missing and Incomplete Modalities with Generative Adversarial Networks for Building Footprint Segmentation
Title | Overcoming Missing and Incomplete Modalities with Generative Adversarial Networks for Building Footprint Segmentation |
Authors | Benjamin Bischke, Patrick Helber, Florian König, Damian Borth, Andreas Dengel |
Abstract | The integration of information acquired with different modalities, spatial resolution and spectral bands has shown to improve predictive accuracies. Data fusion is therefore one of the key challenges in remote sensing. Most prior work focusing on multi-modal fusion, assumes that modalities are always available during inference. This assumption limits the applications of multi-modal models since in practice the data collection process is likely to generate data with missing, incomplete or corrupted modalities. In this paper, we show that Generative Adversarial Networks can be effectively used to overcome the problems that arise when modalities are missing or incomplete. Focusing on semantic segmentation of building footprints with missing modalities, our approach achieves an improvement of about 2% on the Intersection over Union (IoU) against the same network that relies only on the available modality. |
Tasks | Semantic Segmentation |
Published | 2018-08-09 |
URL | http://arxiv.org/abs/1808.03195v1 |
http://arxiv.org/pdf/1808.03195v1.pdf | |
PWC | https://paperswithcode.com/paper/overcoming-missing-and-incomplete-modalities |
Repo | |
Framework | |
Towards Distributed Coevolutionary GANs
Title | Towards Distributed Coevolutionary GANs |
Authors | Abdullah Al-Dujaili, Tom Schmiedlechner, and Erik Hemberg, Una-May O’Reilly |
Abstract | Generative Adversarial Networks (GANs) have become one of the dominant methods for deep generative modeling. Despite their demonstrated success on multiple vision tasks, GANs are difficult to train and much research has been dedicated towards understanding and improving their gradient-based learning dynamics. Here, we investigate the use of coevolution, a class of black-box (gradient-free) co-optimization techniques and a powerful tool in evolutionary computing, as a supplement to gradient-based GAN training techniques. Experiments on a simple model that exhibits several of the GAN gradient-based dynamics (e.g., mode collapse, oscillatory behavior, and vanishing gradients) show that coevolution is a promising framework for escaping degenerate GAN training behaviors. |
Tasks | |
Published | 2018-07-21 |
URL | http://arxiv.org/abs/1807.08194v3 |
http://arxiv.org/pdf/1807.08194v3.pdf | |
PWC | https://paperswithcode.com/paper/towards-distributed-coevolutionary-gans |
Repo | |
Framework | |
Clustering with Outlier Removal
Title | Clustering with Outlier Removal |
Authors | Hongfu Liu, Jun Li, Yue Wu, Yun Fu |
Abstract | Cluster analysis and outlier detection are strongly coupled tasks in data mining area. Cluster structure can be easily destroyed by few outliers; on the contrary, outliers are defined by the concept of cluster, which are recognized as the points belonging to none of the clusters. Unfortunately, most existing studies do not notice the coupled relationship between these two task and handle them separately. In light of this, we consider the joint cluster analysis and outlier detection problem, and propose the Clustering with Outlier Removal (COR) algorithm. Generally speaking, the original space is transformed into the binary space via generating basic partitions in order to define clusters. Then an objective function based Holoentropy is designed to enhance the compactness of each cluster with a few outliers removed. With further analyses on the objective function, only partial of the problem can be handled by K-means optimization. To provide an integrated solution, an auxiliary binary matrix is nontrivally introduced so that COR completely and efficiently solves the challenging problem via a unified K-means– with theoretical supports. Extensive experimental results on numerous data sets in various domains demonstrate the effectiveness and efficiency of COR significantly over state-of-the-art methods in terms of cluster validity and outlier detection. Some key factors in COR are further analyzed for practical use. Finally, an application on flight trajectory is provided to demonstrate the effectiveness of COR in the real-world scenario. |
Tasks | Outlier Detection |
Published | 2018-01-05 |
URL | https://arxiv.org/abs/1801.01899v2 |
https://arxiv.org/pdf/1801.01899v2.pdf | |
PWC | https://paperswithcode.com/paper/clustering-with-outlier-removal |
Repo | |
Framework | |