July 29, 2019

3287 words 16 mins read

Paper Group ANR 39

Towards Structured Analysis of Broadcast Badminton Videos. To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection. Trans-allelic model for prediction of peptide:MHC-II interactions. A semi-supervised fuzzy GrowCut algorithm to segment and classify regions of interest of mammographic images. CNN Cascades for Segmenting Whole S …

Towards Structured Analysis of Broadcast Badminton Videos


Title	Towards Structured Analysis of Broadcast Badminton Videos
Authors	Anurag Ghosh, Suriya Singh, C. V. Jawahar
Abstract	Sports video data is recorded for nearly every major tournament but remains archived and inaccessible to large scale data mining and analytics. It can only be viewed sequentially or manually tagged with higher-level labels which is time consuming and prone to errors. In this work, we propose an end-to-end framework for automatic attributes tagging and analysis of sport videos. We use commonly available broadcast videos of matches and, unlike previous approaches, does not rely on special camera setups or additional sensors. Our focus is on Badminton as the sport of interest. We propose a method to analyze a large corpus of badminton broadcast videos by segmenting the points played, tracking and recognizing the players in each point and annotating their respective badminton strokes. We evaluate the performance on 10 Olympic matches with 20 players and achieved 95.44% point segmentation accuracy, 97.38% player detection score (mAP@0.5), 97.98% player identification accuracy, and stroke segmentation edit scores of 80.48%. We further show that the automatically annotated videos alone could enable the gameplay analysis and inference by computing understandable metrics such as player’s reaction time, speed, and footwork around the court, etc.
Tasks
Published	2017-12-23
URL	http://arxiv.org/abs/1712.08714v1
PDF	http://arxiv.org/pdf/1712.08714v1.pdf
PWC	https://paperswithcode.com/paper/towards-structured-analysis-of-broadcast
Repo
Framework

To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection


Title	To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection
Authors	Eshed Ohn-Bar, Mohan M. Trivedi
Abstract	We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on the relationship between modeling capacity of the weak learners, dataset size, and dataset properties. A set of novel experiments on the Caltech Pedestrian Detection benchmark results in the best known performance among non-CNN techniques while operating at fast run-time speed. Furthermore, the performance is on par with deep architectures (9.71% log-average miss rate), while using only HOG+LUV channels as features. The conclusions from this study are shown to generalize over different object detection domains as demonstrated on the FDDB face detection benchmark (93.37% accuracy). Despite the impressive performance, this study reveals the limited modeling capacity of the common boosted trees model, motivating a need for architectural changes in order to compete with multi-level and very deep architectures.
Tasks	Face Detection, Object Detection, Pedestrian Detection
Published	2017-01-06
URL	http://arxiv.org/abs/1701.01692v1
PDF	http://arxiv.org/pdf/1701.01692v1.pdf
PWC	https://paperswithcode.com/paper/to-boost-or-not-to-boost-on-the-limits-of
Repo
Framework

Trans-allelic model for prediction of peptide:MHC-II interactions


Title	Trans-allelic model for prediction of peptide:MHC-II interactions
Authors	A. M. Degoot, Faraimunashe Chirove, Wilfred Ndifon
Abstract	Major histocompatibility complex class two (MHC-II) molecules are trans-membrane proteins and key components of the cellular immune system. Upon recognition of foreign peptides expressed on the MHC-II binding groove, helper T cells mount an immune response against invading pathogens. Therefore, mechanistic identification and knowledge of physico-chemical features that govern interactions between peptides and MHC-II molecules is useful for the design of effective epitope-based vaccines, as well as for understanding of immune responses. In this paper, we present a comprehensive trans-allelic prediction model, a generalized version of our previous biophysical model, that can predict peptide interactions for all three human MHC-II loci (HLA-DR, HLA-DP and HLA-DQ), using both peptide sequence data and structural information of MHC-II molecules. The advantage of this approach over other machine learning models is that it offers a simple and plausible physical explanation for peptide-MHC-II interactions. We train the model using a benchmark experimental dataset, and measure its predictive performance using novel data. Despite its relative simplicity, we find that the model has comparable performance to the state-of-the-art method. Focusing on the physical bases of peptide-MHC binding, we find support for previous theoretical predictions about the contributions of certain binding pockets to the binding energy. Additionally, we find that binding pockets P 4 and P 5 of HLA-DP, which were not previously considered as primary anchors, do make strong contributions to the binding energy. Together, the results indicate that our model can serve as a useful complement to alternative approaches to predicting peptide-MHC interactions.
Tasks
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00351v1
PDF	http://arxiv.org/pdf/1712.00351v1.pdf
PWC	https://paperswithcode.com/paper/trans-allelic-model-for-prediction-of
Repo
Framework

A semi-supervised fuzzy GrowCut algorithm to segment and classify regions of interest of mammographic images


Title	A semi-supervised fuzzy GrowCut algorithm to segment and classify regions of interest of mammographic images
Authors	Filipe Rolim Cordeiro, Wellington Pinheiro dos Santos, Abel Guilhermino da Silva Filho
Abstract	According to the World Health Organization, breast cancer is the most common form of cancer in women. It is the second leading cause of death among women round the world, becoming the most fatal form of cancer. Mammographic image segmentation is a fundamental task to support image analysis and diagnosis, taking into account shape analysis of mammary lesions and their borders. However, mammogram segmentation is a very hard process, once it is highly dependent on the types of mammary tissues. In this work we present a new semi-supervised segmentation algorithm based on the modification of the GrowCut algorithm to perform automatic mammographic image segmentation once a region of interest is selected by a specialist. In our proposal, we used fuzzy Gaussian membership functions to modify the evolution rule of the original GrowCut algorithm, in order to estimate the uncertainty of a pixel being object or background. The main impact of the proposed method is the significant reduction of expert effort in the initialization of seed points of GrowCut to perform accurate segmentation, once it removes the need of selection of background seeds. We also constructed an automatic point selection process based on the simulated annealing optimization method, avoiding the need of human intervention. The proposed approach was qualitatively compared with other state-of-the-art segmentation techniques, considering the shape of segmented regions. In order to validate our proposal, we built an image classifier using a classical multilayer perceptron. We used Zernike moments to extract segmented image features. This analysis employed 685 mammograms from IRMA breast cancer database, using fat and fibroid tissues. Results show that the proposed technique could achieve a classification rate of 91.28% for fat tissues, evidencing the feasibility of our approach.
Tasks	Semantic Segmentation
Published	2017-12-03
URL	http://arxiv.org/abs/1801.01443v1
PDF	http://arxiv.org/pdf/1801.01443v1.pdf
PWC	https://paperswithcode.com/paper/a-semi-supervised-fuzzy-growcut-algorithm-to
Repo
Framework

CNN Cascades for Segmenting Whole Slide Images of the Kidney


Title	CNN Cascades for Segmenting Whole Slide Images of the Kidney
Authors	Michael Gadermayr, Ann-Kathrin Dombrowski, Barbara Mara Klinkhammer, Peter Boor, Dorit Merhof
Abstract	Due to the increasing availability of whole slide scanners facilitating digitization of histopathological tissue, there is a strong demand for the development of computer based image analysis systems. In this work, the focus is on the segmentation of the glomeruli constituting a highly relevant structure in renal histopathology, which has not been investigated before in combination with CNNs. We propose two different CNN cascades for segmentation applications with sparse objects. These approaches are applied to the problem of glomerulus segmentation and compared with conventional fully-convolutional networks. Overall, with the best performing cascade approach, single CNNs are outperformed and a pixel-level Dice similarity coefficient of 0.90 is obtained. Combined with qualitative and further object-level analyses the obtained results are assessed as excellent also compared to recent approaches. In conclusion, we can state that especially one of the proposed cascade networks proved to be a highly powerful tool for segmenting the renal glomeruli providing best segmentation accuracies and also keeping the computing time at a low level.
Tasks
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00251v1
PDF	http://arxiv.org/pdf/1708.00251v1.pdf
PWC	https://paperswithcode.com/paper/cnn-cascades-for-segmenting-whole-slide
Repo
Framework

QuaSI: Quantile Sparse Image Prior for Spatio-Temporal Denoising of Retinal OCT Data


Title	QuaSI: Quantile Sparse Image Prior for Spatio-Temporal Denoising of Retinal OCT Data
Authors	Franziska Schirrmacher, Thomas Köhler, Lennart Husvogt, James G. Fujimoto, Joachim Hornegger, Andreas K. Maier
Abstract	Optical coherence tomography (OCT) enables high-resolution and non-invasive 3D imaging of the human retina but is inherently impaired by speckle noise. This paper introduces a spatio-temporal denoising algorithm for OCT data on a B-scan level using a novel quantile sparse image (QuaSI) prior. To remove speckle noise while preserving image structures of diagnostic relevance, we implement our QuaSI prior via median filter regularization coupled with a Huber data fidelity model in a variational approach. For efficient energy minimization, we develop an alternating direction method of multipliers (ADMM) scheme using a linearization of median filtering. Our spatio-temporal method can handle both, denoising of single B-scans and temporally consecutive B-scans, to gain volumetric OCT data with enhanced signal-to-noise ratio. Our algorithm based on 4 B-scans only achieved comparable performance to averaging 13 B-scans and outperformed other current denoising methods.
Tasks	Denoising
Published	2017-03-08
URL	http://arxiv.org/abs/1703.02942v1
PDF	http://arxiv.org/pdf/1703.02942v1.pdf
PWC	https://paperswithcode.com/paper/quasi-quantile-sparse-image-prior-for-spatio
Repo
Framework

Detecting Adversarial Samples Using Density Ratio Estimates


Title	Detecting Adversarial Samples Using Density Ratio Estimates
Authors	Lovedeep Gondara
Abstract	Machine learning models, especially based on deep architectures are used in everyday applications ranging from self driving cars to medical diagnostics. It has been shown that such models are dangerously susceptible to adversarial samples, indistinguishable from real samples to human eye, adversarial samples lead to incorrect classifications with high confidence. Impact of adversarial samples is far-reaching and their efficient detection remains an open problem. We propose to use direct density ratio estimation as an efficient model agnostic measure to detect adversarial samples. Our proposed method works equally well with single and multi-channel samples, and with different adversarial sample generation methods. We also propose a method to use density ratio estimates for generating adversarial samples with an added constraint of preserving density ratio.
Tasks	Self-Driving Cars
Published	2017-05-05
URL	http://arxiv.org/abs/1705.02224v4
PDF	http://arxiv.org/pdf/1705.02224v4.pdf
PWC	https://paperswithcode.com/paper/detecting-adversarial-samples-using-density
Repo
Framework

GP-Unet: Lesion Detection from Weak Labels with a 3D Regression Network


Title	GP-Unet: Lesion Detection from Weak Labels with a 3D Regression Network
Authors	Florian Dubost, Gerda Bortsova, Hieab Adams, Arfan Ikram, Wiro Niessen, Meike Vernooij, Marleen De Bruijne
Abstract	We propose a novel convolutional neural network for lesion detection from weak labels. Only a single, global label per image - the lesion count - is needed for training. We train a regression network with a fully convolutional architecture combined with a global pooling layer to aggregate the 3D output into a scalar indicating the lesion count. When testing on unseen images, we first run the network to estimate the number of lesions. Then we remove the global pooling layer to compute localization maps of the size of the input image. We evaluate the proposed network on the detection of enlarged perivascular spaces in the basal ganglia in MRI. Our method achieves a sensitivity of 62% with on average 1.5 false positives per image. Compared with four other approaches based on intensity thresholding, saliency and class maps, our method has a 20% higher sensitivity.
Tasks
Published	2017-05-22
URL	http://arxiv.org/abs/1705.07999v2
PDF	http://arxiv.org/pdf/1705.07999v2.pdf
PWC	https://paperswithcode.com/paper/gp-unet-lesion-detection-from-weak-labels
Repo
Framework

A New Learning Paradigm for Random Vector Functional-Link Network: RVFL+


Title	A New Learning Paradigm for Random Vector Functional-Link Network: RVFL+
Authors	Peng-Bo Zhang, Zhi-Xin Yang
Abstract	In school, a teacher plays an important role in various classroom teaching patterns. Likewise to this human learning activity, the learning using privileged information (LUPI) paradigm provides additional information generated by the teacher to ‘teach’ learning models during the training stage. Therefore, this novel learning paradigm is a typical Teacher-Student Interaction mechanism. This paper is the first to present a random vector functional link network based on the LUPI paradigm, called RVFL+. Rather than simply combining two existing approaches, the newly-derived RVFL+ fills the gap between classical randomized neural networks and the newfashioned LUPI paradigm, which offers an alternative way to train RVFL networks. Moreover, the proposed RVFL+ can perform in conjunction with the kernel trick for highly complicated nonlinear feature learning, which is termed KRVFL+. Furthermore, the statistical property of the proposed RVFL+ is investigated, and we present a sharp and high-quality generalization error bound based on the Rademacher complexity. Competitive experimental results on 14 real-world datasets illustrate the great effectiveness and efficiency of the novel RVFL+ and KRVFL+, which can achieve better generalization performance than state-of-the-art methods.
Tasks
Published	2017-08-28
URL	http://arxiv.org/abs/1708.08282v4
PDF	http://arxiv.org/pdf/1708.08282v4.pdf
PWC	https://paperswithcode.com/paper/a-new-learning-paradigm-for-random-vector
Repo
Framework

Multifractal analysis of the time series of daily means of wind speed in complex regions


Title	Multifractal analysis of the time series of daily means of wind speed in complex regions
Authors	Mohamed Laib, Jean Golay, Luciano Telesca, Mikhail Kanevski
Abstract	In this paper, we applied the multifractal detrended fluctuation analysis to the daily means of wind speed measured by 119 weather stations distributed over the territory of Switzerland. The analysis was focused on the inner time fluctuations of wind speed, which could be more linked with the local conditions of the highly varying topography of Switzerland. Our findings point out to a persistent behaviour of all the measured wind speed series (indicated by a Hurst exponent significantly larger than 0.5), and to a high multifractality degree indicating a relative dominance of the large fluctuations in the dynamics of wind speed, especially in the Swiss plateau, which is comprised between the Jura and Alp mountain ranges. The study represents a contribution to the understanding of the dynamical mechanisms of wind speed variability in mountainous regions.
Tasks	Time Series
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01490v1
PDF	http://arxiv.org/pdf/1710.01490v1.pdf
PWC	https://paperswithcode.com/paper/multifractal-analysis-of-the-time-series-of
Repo
Framework

Efficient tracking of a growing number of experts


Title	Efficient tracking of a growing number of experts
Authors	Jaouad Mourtada, Odalric-Ambrym Maillard
Abstract	We consider a variation on the problem of prediction with expert advice, where new forecasters that were unknown until then may appear at each round. As often in prediction with expert advice, designing an algorithm that achieves near-optimal regret guarantees is straightforward, using aggregation of experts. However, when the comparison class is sufficiently rich, for instance when the best expert and the set of experts itself changes over time, such strategies naively require to maintain a prohibitive number of weights (typically exponential with the time horizon). By contrast, designing strategies that both achieve a near-optimal regret and maintain a reasonable number of weights is highly non-trivial. We consider three increasingly challenging objectives (simple regret, shifting regret and sparse shifting regret) that extend existing notions defined for a fixed expert ensemble; in each case, we design strategies that achieve tight regret bounds, adaptive to the parameters of the comparison class, while being computationally inexpensive. Moreover, our algorithms are anytime, agnostic to the number of incoming experts and completely parameter-free. Such remarkable results are made possible thanks to two simple but highly effective recipes: first the “abstention trick” that comes from the specialist framework and enables to handle the least challenging notions of regret, but is limited when addressing more sophisticated objectives. Second, the “muting trick” that we introduce to give more flexibility. We show how to combine these two tricks in order to handle the most challenging class of comparison strategies.
Tasks
Published	2017-08-31
URL	http://arxiv.org/abs/1708.09811v1
PDF	http://arxiv.org/pdf/1708.09811v1.pdf
PWC	https://paperswithcode.com/paper/efficient-tracking-of-a-growing-number-of
Repo
Framework

Seeded Laplaican: An Eigenfunction Solution for Scribble Based Interactive Image Segmentation


Title	Seeded Laplaican: An Eigenfunction Solution for Scribble Based Interactive Image Segmentation
Authors	Ahmed Taha, Marwan Torki
Abstract	In this paper, we cast the scribble-based interactive image segmentation as a semi-supervised learning problem. Our novel approach alleviates the need to solve an expensive generalized eigenvector problem by approximating the eigenvectors using efficiently computed eigenfunctions. The smoothness operator defined on feature densities at the limit n tends to infinity recovers the exact eigenvectors of the graph Laplacian, where n is the number of nodes in the graph. To further reduce the computational complexity without scarifying our accuracy, we select pivots pixels from user annotations. In our experiments, we evaluate our approach using both human scribble and “robot user” annotations to guide the foreground/background segmentation. We developed a new unbiased collection of five annotated images datasets to standardize the evaluation procedure for any scribble-based segmentation method. We experimented with several variations, including different feature vectors, pivot count and the number of eigenvectors. Experiments are carried out on datasets that contain a wide variety of natural images. We achieve better qualitative and quantitative results compared to state-of-the-art interactive segmentation algorithms.
Tasks	Interactive Segmentation, Semantic Segmentation
Published	2017-02-03
URL	http://arxiv.org/abs/1702.00882v2
PDF	http://arxiv.org/pdf/1702.00882v2.pdf
PWC	https://paperswithcode.com/paper/seeded-laplaican-an-eigenfunction-solution
Repo
Framework

Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines


Title	Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines
Authors	Maxinder S. Kanwal, Joshua A. Grochow, Nihat Ay
Abstract	In the past three decades, many theoretical measures of complexity have been proposed to help understand complex systems. In this work, for the first time, we place these measures on a level playing field, to explore the qualitative similarities and differences between them, and their shortcomings. Specifically, using the Boltzmann machine architecture (a fully connected recurrent neural network) with uniformly distributed weights as our model of study, we numerically measure how complexity changes as a function of network dynamics and network parameters. We apply an extension of one such information-theoretic measure of complexity to understand incremental Hebbian learning in Hopfield networks, a fully recurrent architecture model of autoassociative memory. In the course of Hebbian learning, the total information flow reflects a natural upward trend in complexity as the network attempts to learn more and more patterns.
Tasks
Published	2017-06-29
URL	http://arxiv.org/abs/1706.09667v2
PDF	http://arxiv.org/pdf/1706.09667v2.pdf
PWC	https://paperswithcode.com/paper/comparing-information-theoretic-measures-of
Repo
Framework

SegICP: Integrated Deep Semantic Segmentation and Pose Estimation


Title	SegICP: Integrated Deep Semantic Segmentation and Pose Estimation
Authors	Jay M. Wong, Vincent Kee, Tiffany Le, Syler Wagner, Gian-Luca Mariottini, Abraham Schneider, Lei Hamilton, Rahul Chipalkatty, Mitchell Hebert, David M. S. Johnson, Jimmy Wu, Bolei Zhou, Antonio Torralba
Abstract	Recent robotic manipulation competitions have highlighted that sophisticated robots still struggle to achieve fast and reliable perception of task-relevant objects in complex, realistic scenarios. To improve these systems’ perceptive speed and robustness, we present SegICP, a novel integrated solution to object recognition and pose estimation. SegICP couples convolutional neural networks and multi-hypothesis point cloud registration to achieve both robust pixel-wise semantic segmentation as well as accurate and real-time 6-DOF pose estimation for relevant objects. Our architecture achieves 1cm position error and <5^\circ$ angle error in real time without an initial seed. We evaluate and benchmark SegICP against an annotated dataset generated by motion capture.
Tasks	Motion Capture, Object Recognition, Point Cloud Registration, Pose Estimation, Semantic Segmentation
Published	2017-03-05
URL	http://arxiv.org/abs/1703.01661v2
PDF	http://arxiv.org/pdf/1703.01661v2.pdf
PWC	https://paperswithcode.com/paper/segicp-integrated-deep-semantic-segmentation
Repo
Framework

Language-Based Image Editing with Recurrent Attentive Models


Title	Language-Based Image Editing with Recurrent Attentive Models
Authors	Jianbo Chen, Yelong Shen, Jianfeng Gao, Jingjing Liu, Xiaodong Liu
Abstract	We investigate the problem of Language-Based Image Editing (LBIE). Given a source image and a natural language description, we want to generate a target image by editing the source image based on the description. We propose a generic modeling framework for two sub-tasks of LBIE: language-based image segmentation and image colorization. The framework uses recurrent attentive models to fuse image and language features. Instead of using a fixed step size, we introduce for each region of the image a termination gate to dynamically determine after each inference step whether to continue extrapolating additional information from the textual description. The effectiveness of the framework is validated on three datasets. First, we introduce a synthetic dataset, called CoSaL, to evaluate the end-to-end performance of our LBIE system. Second, we show that the framework leads to state-of-the-art performance on image segmentation on the ReferIt dataset. Third, we present the first language-based colorization result on the Oxford-102 Flowers dataset.
Tasks	Colorization, Semantic Segmentation
Published	2017-11-16
URL	http://arxiv.org/abs/1711.06288v2
PDF	http://arxiv.org/pdf/1711.06288v2.pdf
PWC	https://paperswithcode.com/paper/language-based-image-editing-with-recurrent
Repo
Framework