January 27, 2020

3074 words 15 mins read

Paper Group ANR 1192

Systematic Comparison of the Influence of Different Data Preprocessing Methods on the Classification of Gait Using Machine Learning. Saliency Detection With Fully Convolutional Neural Network. Modelling the Socialization of Creative Agents in a Master-Apprentice Setting: The Case of Movie Title Puns. Atlas-based automated detection of swim bladder …

Systematic Comparison of the Influence of Different Data Preprocessing Methods on the Classification of Gait Using Machine Learning


Title	Systematic Comparison of the Influence of Different Data Preprocessing Methods on the Classification of Gait Using Machine Learning
Authors	Johannes Burdack, Fabian Horst, Sven Giesselbach, Ibrahim Hassan, Sabrina Daffner, Wolfgang I. Schöllhorn
Abstract	Human movements are characterized by highly non-linear and multi-dimensional interactions within the motor system. Recently, an increasing emphasis on machine-learning applications has led to a significant contribution to the field of gait analysis e.g. in increasing the classification accuracy. In order to ensure the generalizability of the machine-learning models, different data preprocessing steps are usually carried out to process the measured raw data before the classifications. In the past, various methods have been used for each of these preprocessing steps. However, there are hardly any standard procedures or rather systematic comparisons of these different methods and their impact on the classification accuracy. Therefore, the aim of this analysis is to compare different combinations of commonly applied data preprocessing steps and test their effects on the classification accuracy of gait patterns. A publicly available dataset on intra-individual changes of gait patterns was used for this analysis. Forty-two healthy subjects performed 6 sessions of 15 gait trials for one day. For each trial, two force plates recorded the 3D ground reaction forces (GRF). The data was preprocessed with the following steps: GRF filtering, time derivative, time normalization, data reduction, weight normalization and data scaling. Subsequently, combinations of all methods from each individual preprocessing step were analyzed and compared with respect to their prediction accuracy in a six-session classification using Support Vector Machines, Random Forest Classifiers and Multi-Layer Perceptrons. In conclusion, the present results provide first domain-specific recommendations for commonly applied data preprocessing methods and might help to build more comparable and more robust classification models based on machine learning that are suitable for a practical application.
Tasks
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04335v1
PDF	https://arxiv.org/pdf/1911.04335v1.pdf
PWC	https://paperswithcode.com/paper/systematic-comparison-of-the-influence-of
Repo
Framework

Saliency Detection With Fully Convolutional Neural Network


Title	Saliency Detection With Fully Convolutional Neural Network
Authors	Hooman Misaghi, Reza Askari Moghadam, Ali Mahmoudi, Kurosh Madani
Abstract	Saliency detection is an important task in image processing as it can solve many problems and it usually is the first step in for other processes. Convolutional neural networks have been proved to be very effective on several image processing tasks such as classification, segmentation, semantic colorization and object manipulation. Besides, using the weights of a pretrained networks is a common practice for enhancing the accuracy of a network. In this paper a fully convolutional neural network which uses a part of VGG-16 is proposed for saliency detection in images.
Tasks	Colorization, Saliency Detection
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09806v1
PDF	https://arxiv.org/pdf/1906.09806v1.pdf
PWC	https://paperswithcode.com/paper/saliency-detection-with-fully-convolutional
Repo
Framework

Modelling the Socialization of Creative Agents in a Master-Apprentice Setting: The Case of Movie Title Puns


Title	Modelling the Socialization of Creative Agents in a Master-Apprentice Setting: The Case of Movie Title Puns
Authors	Mika Hämäläinen, Khalid Alnajjar
Abstract	This paper presents work on modelling the social psychological aspect of socialization in the case of a computationally creative master-apprentice system. In each master-apprentice pair, the master, a genetic algorithm, is seen as a parent for its apprentice, which is an NMT based sequence-to-sequence model. The effect of different parenting styles on the creative output of each pair is in the focus of this study. This approach brings a novel view point to computational social creativity, which has mainly focused in the past on computationally creative agents being on a socially equal level, whereas our approach studies the phenomenon in the context of a social hierarchy.
Tasks
Published	2019-07-10
URL	https://arxiv.org/abs/1907.04954v1
PDF	https://arxiv.org/pdf/1907.04954v1.pdf
PWC	https://paperswithcode.com/paper/modelling-the-socialization-of-creative
Repo
Framework

Atlas-based automated detection of swim bladder in Medaka embryo


Title	Atlas-based automated detection of swim bladder in Medaka embryo
Authors	Diane Genest, Marc Léonard, Jean Cousty, Noémie De Crozé, Hugues Talbot
Abstract	Fish embryo models are increasingly being used both for the assessment of chemicals efficacy and potential toxicity. This article proposes a methodology to automatically detect the swim bladder on 2D images of Medaka fish embryos seen either in dorsal view or in lateral view. After embryo segmentation and for each studied orientation, the method builds an atlas of a healthy embryo. This atlas is then used to define the region of interest and to guide the swim bladder segmentation with a discrete globally optimal active contour. Descriptors are subsequently designed from this segmentation. An automated random forest clas-sifier is built from these descriptors in order to classify embryos with and without a swim bladder. The proposed method is assessed on a dataset of 261 images, containing 202 embryos with a swim bladder (where 196 are in dorsal view and 6 are in lateral view) and 59 without (where 43 are in dorsal view and 16 are in lateral view). We obtain an average precision rate of 95% in the total dataset following 5-fold cross-validation.
Tasks
Published	2019-02-16
URL	http://arxiv.org/abs/1902.06130v1
PDF	http://arxiv.org/pdf/1902.06130v1.pdf
PWC	https://paperswithcode.com/paper/atlas-based-automated-detection-of-swim
Repo
Framework

Using colorization as a tool for automatic makeup suggestion


Title	Using colorization as a tool for automatic makeup suggestion
Authors	Shreyank Narayana Gowda
Abstract	Colorization is the method of converting an image in grayscale to a fully color image. There are multiple methods to do the same. Old school methods used machine learning algorithms and optimization techniques to suggest possible colors to use. With advances in the field of deep learning, colorization results have improved consistently with improvements in deep learning architectures. The latest development in the field of deep learning is the emergence of generative adversarial networks (GANs) which is used to generate information and not just predict or classify. As part of this report, 2 architectures of recent papers are reproduced along with a novel architecture being suggested for general colorization. Following this, we propose the use of colorization by generating makeup suggestions automatically on a face. To do this, a dataset consisting of 1000 images has been created. When an image of a person without makeup is sent to the model, the model first converts the image to grayscale and then passes it through the suggested GAN model. The output is a generated makeup suggestion. To develop this model, we need to tweak the general colorization model to deal only with faces of people.
Tasks	Colorization
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07421v1
PDF	https://arxiv.org/pdf/1906.07421v1.pdf
PWC	https://paperswithcode.com/paper/using-colorization-as-a-tool-for-automatic
Repo
Framework

Novel and Efficient Approximations for Zero-One Loss of Linear Classifiers


Title	Novel and Efficient Approximations for Zero-One Loss of Linear Classifiers
Authors	Hiva Ghanbari, Minhan Li, Katya Scheinberg
Abstract	The predictive quality of machine learning models is typically measured in terms of their (approximate) expected prediction accuracy or the so-called Area Under the Curve (AUC). Minimizing the reciprocals of these measures are the goals of supervised learning. However, when the models are constructed by the means of empirical risk minimization (ERM), surrogate functions such as the logistic loss or hinge loss are optimized instead. In this work, we show that in the case of linear predictors, the expected error and the expected ranking loss can be effectively approximated by smooth functions whose closed form expressions and those of their first (and second) order derivatives depend on the first and second moments of the data distribution, which can be precomputed. Hence, the complexity of an optimization algorithm applied to these functions does not depend on the size of the training data. These approximation functions are derived under the assumption that the output of the linear classifier for a given data set has an approximately normal distribution. We argue that this assumption is significantly weaker than the Gaussian assumption on the data itself and we support this claim by demonstrating that our new approximation is quite accurate on data sets that are not necessarily Gaussian. We present computational results that show that our proposed approximations and related optimization algorithms can produce linear classifiers with similar or better test accuracy or AUC, than those obtained using state-of-the-art approaches, in a fraction of the time.
Tasks
Published	2019-02-28
URL	http://arxiv.org/abs/1903.00359v1
PDF	http://arxiv.org/pdf/1903.00359v1.pdf
PWC	https://paperswithcode.com/paper/novel-and-efficient-approximations-for-zero
Repo
Framework

Federated Hierarchical Hybrid Networks for Clickbait Detection


Title	Federated Hierarchical Hybrid Networks for Clickbait Detection
Authors	Feng Liao, Hankz Hankui Zhuo, Xiaoling Huang, Yu Zhang
Abstract	Online media outlets adopt clickbait techniques to lure readers to click on articles in a bid to expand their reach and subsequently increase revenue through ad monetization. As the adverse effects of clickbait attract more and more attention, researchers have started to explore machine learning techniques to automatically detect clickbaits. Previous work on clickbait detection assumes that all the training data is available locally during training. In many real-world applications, however, training data is generally distributedly stored by different parties (e.g., different parties maintain data with different feature spaces), and the parties cannot share their data with each other due to data privacy issues. It is challenging to build models of high-quality federally for detecting clickbaits effectively without data sharing. In this paper, we propose a federated training framework, which is called federated hierarchical hybrid networks, to build clickbait detection models, where the titles and contents are stored by different parties, whose relationships must be exploited for clickbait detection. We empirically demonstrate that our approach is effective by comparing our approach to the state-of-the-art approaches using datasets from social media.
Tasks	Clickbait Detection
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00638v1
PDF	https://arxiv.org/pdf/1906.00638v1.pdf
PWC	https://paperswithcode.com/paper/190600638
Repo
Framework

Shape Constrained Network for Eye Segmentation in the Wild


Title	Shape Constrained Network for Eye Segmentation in the Wild
Authors	Bingnan Luo, Jie Shen, Shiyang Cheng, Yujiang Wang, Maja Pantic
Abstract	Semantic segmentation of eyes has long been a vital pre-processing step in many biometric applications. Majority of the works focus only on high resolution eye images, while little has been done to segment the eyes from low quality images in the wild. However, this is a particularly interesting and meaningful topic, as eyes play a crucial role in conveying the emotional state and mental well-being of a person. In this work, we take two steps toward solving this problem: (1) We collect and annotate a challenging eye segmentation dataset containing 8882 eye patches from 4461 facial images of different resolutions, illumination conditions and head poses; (2) We develop a novel eye segmentation method, Shape Constrained Network (SCN), that incorporates shape prior into the segmentation network training procedure. Specifically, we learn the shape prior from our dataset using VAE-GAN, and leverage the pre-trained encoder and discriminator to regularise the training of SegNet. To improve the accuracy and quality of predicted masks, we replace the loss of SegNet with three new losses: Intersection-over-Union (IoU) loss, shape discriminator loss and shape embedding loss. Extensive experiments shows that our method outperforms state-of-the-art segmentation and landmark detection methods in terms of mean IoU (mIoU) accuracy and the quality of segmentation masks. The eye segmentation database is available at https://www.dropbox.com/s/yvveouvxsvti08x/Eye_Segmentation_Database.zip?dl=0.
Tasks	Semantic Segmentation
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05283v1
PDF	https://arxiv.org/pdf/1910.05283v1.pdf
PWC	https://paperswithcode.com/paper/shape-constrained-network-for-eye
Repo
Framework

Solving Service Robot Tasks: UT Austin Villa@Home 2019 Team Report


Title	Solving Service Robot Tasks: UT Austin Villa@Home 2019 Team Report
Authors	Rishi Shah, Yuqian Jiang, Haresh Karnan, Gilberto Briscoe-Martinez, Dominick Mulder, Ryan Gupta, Rachel Schlossman, Marika Murphy, Justin W. Hart, Luis Sentis, Peter Stone
Abstract	RoboCup@Home is an international robotics competition based on domestic tasks requiring autonomous capabilities pertaining to a large variety of AI technologies. Research challenges are motivated by these tasks both at the level of individual technologies and the integration of subsystems into a fully functional, robustly autonomous system. We describe the progress made by the UT Austin Villa 2019 RoboCup@Home team which represents a significant step forward in AI-based HRI due to the breadth of tasks accomplished within a unified system. Presented are the competition tasks, component technologies they rely on, our initial approaches both to the components and their integration, and directions for future research.
Tasks
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06529v1
PDF	https://arxiv.org/pdf/1909.06529v1.pdf
PWC	https://paperswithcode.com/paper/solving-service-robot-tasks-ut-austin
Repo
Framework

Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow


Title	Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow
Authors	Mingyu Ding, Zhe Wang, Bolei Zhou, Jianping Shi, Zhiwu Lu, Ping Luo
Abstract	A major challenge for video semantic segmentation is the lack of labeled data. In most benchmark datasets, only one frame of a video clip is annotated, which makes most supervised methods fail to utilize information from the rest of the frames. To exploit the spatio-temporal information in videos, many previous works use pre-computed optical flows, which encode the temporal consistency to improve the video segmentation. However, the video segmentation and optical flow estimation are still considered as two separate tasks. In this paper, we propose a novel framework for joint video semantic segmentation and optical flow estimation. Semantic segmentation brings semantic information to handle occlusion for more robust optical flow estimation, while the non-occluded optical flow provides accurate pixel-level temporal correspondences to guarantee the temporal consistency of the segmentation. Moreover, our framework is able to utilize both labeled and unlabeled frames in the video through joint training, while no additional calculation is required in inference. Extensive experiments show that the proposed model makes the video semantic segmentation and optical flow estimation benefit from each other and outperforms existing methods under the same settings in both tasks.
Tasks	Optical Flow Estimation, Semantic Segmentation, Video Semantic Segmentation
Published	2019-11-28
URL	https://arxiv.org/abs/1911.12739v1
PDF	https://arxiv.org/pdf/1911.12739v1.pdf
PWC	https://paperswithcode.com/paper/every-frame-counts-joint-learning-of-video
Repo
Framework

Learning from Noisy Anchors for One-stage Object Detection


Title	Learning from Noisy Anchors for One-stage Object Detection
Authors	Hengduo Li, Zuxuan Wu, Chen Zhu, Caiming Xiong, Richard Socher, Larry S. Davis
Abstract	State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding groundtruth objects. Such a harsh split conditioned on IoU results in binary labels that are potentially noisy and challenging for training. In this paper, we propose to mitigate noise incurred by imperfect label assignment such that the contributions of anchors are dynamically determined by a carefully constructed cleanliness score associated with each anchor. Exploring outputs from both regression and classification branches, the cleanliness scores, estimated without incurring any additional computational overhead, are used not only as soft labels to supervise the training of the classification branch but also sample re-weighting factors for improved localization and classification accuracy. We conduct extensive experiments on COCO, and demonstrate, among other things, the proposed approach steadily improves RetinaNet by ~2% with various backbones.
Tasks	Object Detection
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05086v1
PDF	https://arxiv.org/pdf/1912.05086v1.pdf
PWC	https://paperswithcode.com/paper/learning-from-noisy-anchors-for-one-stage
Repo
Framework

HSCJN: A Holistic Semantic Constraint Joint Network for Diverse Response Generation


Title	HSCJN: A Holistic Semantic Constraint Joint Network for Diverse Response Generation
Authors	Yiru Wang, Pengda Si, Zeyang Lei, Guangxu Xun, Yujiu Yang
Abstract	The sequence-to-sequence (Seq2Seq) model generates target words iteratively given the previously observed words during decoding process, which results in the loss of the holistic semantics in the target response and the complete semantic relationship between responses and dialogue histories. In this paper, we propose a generic diversity-promoting joint network, called Holistic Semantic Constraint Joint Network (HSCJN), enhancing the global sentence information, and then regularizing the objective function with penalizing the low entropy output. Our network introduces more target information to improve diversity, and captures direct semantic information to better constrain the relevance simultaneously. Moreover, the proposed method can be easily applied to any Seq2Seq structure. Extensive experiments on several dialogue corpuses show that our method effectively improves both semantic consistency and diversity of generated responses, and achieves better performance than other competitive methods.
Tasks
Published	2019-12-01
URL	https://arxiv.org/abs/1912.00380v2
PDF	https://arxiv.org/pdf/1912.00380v2.pdf
PWC	https://paperswithcode.com/paper/hscjn-a-holistic-semantic-constraint-joint
Repo
Framework

Classification and Detection in Mammograms with Weak Supervision via Dual Branch Deep Neural Net


Title	Classification and Detection in Mammograms with Weak Supervision via Dual Branch Deep Neural Net
Authors	Ran Bakalo, Rami Ben-Ari, Jacob Goldberger
Abstract	The high cost of generating expert annotations, poses a strong limitation for supervised machine learning methods in medical imaging. Weakly supervised methods may provide a solution to this tangle. In this study, we propose a novel deep learning architecture for multi-class classification of mammograms according to the severity of their containing anomalies, having only a global tag over the image. The suggested scheme further allows localization of the different types of findings in full resolution. The new scheme contains a dual branch network that combines region-level classification with region ranking. We evaluate our method on a large multi-center mammography dataset including $\sim$3,000 mammograms with various anomalies and demonstrate the advantages of the proposed method over a previous weakly-supervised strategy.
Tasks
Published	2019-04-28
URL	http://arxiv.org/abs/1904.12319v1
PDF	http://arxiv.org/pdf/1904.12319v1.pdf
PWC	https://paperswithcode.com/paper/190412319
Repo
Framework

Batch Normalization is a Cause of Adversarial Vulnerability


Title	Batch Normalization is a Cause of Adversarial Vulnerability
Authors	Angus Galloway, Anna Golubeva, Thomas Tanay, Medhat Moussa, Graham W. Taylor
Abstract	Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter updates required to achieve low training error. However, it also reduces robustness to small adversarial input perturbations and noise by double-digit percentages, as we show on five standard datasets. Furthermore, substituting weight decay for batch norm is sufficient to nullify the relationship between adversarial vulnerability and the input dimension. Our work is consistent with a mean-field analysis that found that batch norm causes exploding gradients.
Tasks
Published	2019-05-06
URL	https://arxiv.org/abs/1905.02161v2
PDF	https://arxiv.org/pdf/1905.02161v2.pdf
PWC	https://paperswithcode.com/paper/batch-normalization-is-a-cause-of-adversarial
Repo
Framework

Algorithms for Verifying Deep Neural Networks


Title	Algorithms for Verifying Deep Neural Networks
Authors	Changliu Liu, Tomer Arnon, Christopher Lazarus, Clark Barrett, Mykel J. Kochenderfer
Abstract	Deep neural networks are widely used for nonlinear function approximation with applications ranging from computer vision to control. Although these networks involve the composition of simple arithmetic operations, it can be very challenging to verify whether a particular network satisfies certain input-output properties. This article surveys methods that have emerged recently for soundly verifying such properties. These methods borrow insights from reachability analysis, optimization, and search. We discuss fundamental differences and connections between existing algorithms. In addition, we provide pedagogical implementations of existing methods and compare them on a set of benchmark problems.
Tasks
Published	2019-03-15
URL	http://arxiv.org/abs/1903.06758v1
PDF	http://arxiv.org/pdf/1903.06758v1.pdf
PWC	https://paperswithcode.com/paper/algorithms-for-verifying-deep-neural-networks
Repo
Framework