January 28, 2020

2795 words 14 mins read

Paper Group ANR 964

On approximating dropout noise injection. MTRNet: A Generic Scene Text Eraser. Robust Feature-Based Point Registration Using Directional Mixture Model. Neural-networks for geophysicists and their application to seismic data interpretation. Multiple Kernel Learning from $U$-Statistics of Empirical Measures in the Feature Space. Improving sample dive …

On approximating dropout noise injection


Title	On approximating dropout noise injection
Authors	Natalie Schluter
Abstract	This paper examines the assumptions of the derived equivalence between dropout noise injection and $L_2$ regularisation for logistic regression with negative log loss. We show that the approximation method is based on a divergent Taylor expansion, making, subsequent work using this approximation to compare the dropout trained logistic regression model with standard regularisers unfortunately ill-founded to date. Moreover, the approximation approach is shown to be invalid using any robust constraints. We show how this finding extends to general neural network topologies that use a cross-entropy prediction layer.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11320v2
PDF	https://arxiv.org/pdf/1905.11320v2.pdf
PWC	https://paperswithcode.com/paper/on-approximating-dropout-noise-injection
Repo
Framework

MTRNet: A Generic Scene Text Eraser


Title	MTRNet: A Generic Scene Text Eraser
Authors	Osman Tursun, Rui Zeng, Simon Denman, Sabesan Sivapalan, Sridha Sridharan, Clinton Fookes
Abstract	Text removal algorithms have been proposed for uni-lingual scripts with regular shapes and layouts. However, to the best of our knowledge, a generic text removal method which is able to remove all or user-specified text regions regardless of font, script, language or shape is not available. Developing such a generic text eraser for real scenes is a challenging task, since it inherits all the challenges of multi-lingual and curved text detection and inpainting. To fill this gap, we propose a mask-based text removal network (MTRNet). MTRNet is a conditional adversarial generative network (cGAN) with an auxiliary mask. The introduced auxiliary mask not only makes the cGAN a generic text eraser, but also enables stable training and early convergence on a challenging large-scale synthetic dataset, initially proposed for text detection in real scenes. What’s more, MTRNet achieves state-of-the-art results on several real-world datasets including ICDAR 2013, ICDAR 2017 MLT, and CTW1500, without being explicitly trained on this data, outperforming previous state-of-the-art methods trained directly on these datasets.
Tasks	Curved Text Detection
Published	2019-03-11
URL	https://arxiv.org/abs/1903.04092v3
PDF	https://arxiv.org/pdf/1903.04092v3.pdf
PWC	https://paperswithcode.com/paper/mtrnet-a-generic-scene-text-eraser
Repo
Framework

Robust Feature-Based Point Registration Using Directional Mixture Model


Title	Robust Feature-Based Point Registration Using Directional Mixture Model
Authors	Saman Fahandezh-Saadi, Di Wang, Masayoshi Tomizuka
Abstract	This paper presents a robust probabilistic point registration method for estimating the rigid transformation (i.e. rotation matrix and translation vector) between two pointcloud dataset. The method improves the robustness of point registration and consequently the robot localization in the presence of outliers in the pointclouds which always occurs due to occlusion, dynamic objects, and sensor errors. The framework models the point registration task based on directional statistics on a unit sphere. In particular, a Kent distribution mixture model is adopted and the process of point registration has been carried out in the two phases of Expectation-Maximization algorithm. The proposed method has been evaluated on the pointcloud dataset from LiDAR sensors in an indoor environment.
Tasks
Published	2019-11-25
URL	https://arxiv.org/abs/1912.05016v1
PDF	https://arxiv.org/pdf/1912.05016v1.pdf
PWC	https://paperswithcode.com/paper/robust-feature-based-point-registration-using
Repo
Framework

Neural-networks for geophysicists and their application to seismic data interpretation


Title	Neural-networks for geophysicists and their application to seismic data interpretation
Authors	Bas Peters, Eldad Haber, Justin Granek
Abstract	Neural-networks have seen a surge of interest for the interpretation of seismic images during the last few years. Network-based learning methods can provide fast and accurate automatic interpretation, provided there are sufficiently many training labels. We provide an introduction to the field aimed at geophysicists that are familiar with the framework of forward modeling and inversion. We explain the similarities and differences between deep networks to other geophysical inverse problems and show their utility in solving problems such as lithology interpolation between wells, horizon tracking and segmentation of seismic images. The benefits of our approach are demonstrated on field data from the Sea of Ireland and the North Sea.
Tasks
Published	2019-03-27
URL	http://arxiv.org/abs/1903.11215v1
PDF	http://arxiv.org/pdf/1903.11215v1.pdf
PWC	https://paperswithcode.com/paper/neural-networks-for-geophysicists-and-their
Repo
Framework

Multiple Kernel Learning from $U$-Statistics of Empirical Measures in the Feature Space


Title	Multiple Kernel Learning from $U$-Statistics of Empirical Measures in the Feature Space
Authors	Masoud Badiei Khuzani, Hongyi Ren, Varun Vasudevan, Lei Xing
Abstract	We propose a novel data-driven method to learn multiple kernels in kernel methods of statistical machine learning from training samples. The proposed kernel learning algorithm is based on a $U$-statistics of the empirical marginal distributions of features in the feature space given their class labels. We prove the consistency of the $U$-statistic estimate using the empirical distributions for kernel learning. In particular, we show that the empirical estimate of $U$-statistic converges to its population value with respect to all admissible distributions as the number of the training samples increase. We also prove the sample optimality of the estimate by establishing a minimax lower bound via Fano’s method. In addition, we establish the generalization bounds of the proposed kernel learning approach by computing novel upper bounds on the Rademacher and Gaussian complexities using the concentration of measures for the quadratic matrix forms.We apply the proposed kernel learning approach to classification of the real-world data-sets using the kernel SVM and compare the results with $5$-fold cross-validation for the kernel model selection problem. We also apply the proposed kernel learning approach to devise novel architectures for the semantic segmentation of biomedical images. The proposed segmentation networks are suited for training on small data-sets and employ new mechanisms to generate representations from input images.
Tasks	Model Selection, Semantic Segmentation
Published	2019-02-27
URL	http://arxiv.org/abs/1902.10365v1
PDF	http://arxiv.org/pdf/1902.10365v1.pdf
PWC	https://paperswithcode.com/paper/multiple-kernel-learning-from-u-statistics-of
Repo
Framework

Improving sample diversity of a pre-trained, class-conditional GAN by changing its class embeddings


Title	Improving sample diversity of a pre-trained, class-conditional GAN by changing its class embeddings
Authors	Qi Li, Long Mai, Michael A. Alcorn, Anh Nguyen
Abstract	Mode collapse is a well-known issue in Generative Adversarial Networks (GANs) posing a big challenge to the research community. We propose a simple solution to mode collapse i.e. improving the sample diversity of a pre-trained class-conditional GAN by modifying only its class embeddings. We search for a class embedding that increases sample diversity over a batch of latent vectors. To keep the samples in correct classes while the embeddings change in the direction of maximizing sample diversity, we also move the embeddings in the direction of maximizing the log probability outputs of an auxiliary classifier pre-trained on the same dataset. Our method improves the sample diversity of state-of-the-art ImageNet BigGANs at both 128x128 and 256x256 resolutions. By replacing only the embeddings, we can also synthesize plausible images for Places365 using a BigGAN generator pre-trained on ImageNet, revealing the surprising expressivity of the BigGAN class embedding space.
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04760v3
PDF	https://arxiv.org/pdf/1910.04760v3.pdf
PWC	https://paperswithcode.com/paper/improving-sample-diversity-of-a-pre-trained
Repo
Framework

Android Malicious Application Classification Using Clustering


Title	Android Malicious Application Classification Using Clustering
Authors	Hemant Rathore, Sanjay K. Sahay, Palash Chaturvedi, Mohit Sewak
Abstract	Android malware have been growing at an exponential pace and becomes a serious threat to mobile users. It appears that most of the anti-malware still relies on the signature-based detection system which is generally slow and often not able to detect advanced obfuscated malware. Hence time-to-time various authors have proposed different machine learning solutions to identify sophisticated malware. However, it appears that detection accuracy can be improved by using the clustering method. Therefore in this paper, we propose a novel scalable and effective clustering method to improve the detection accuracy of the malicious android application and obtained a better overall accuracy (98.34%) by random forest classifier compared to regular method, i.e., taking the data altogether to detect the malware. However, as far as true positive and true negative are concerned, by clustering method, true positive is best obtained by decision tree (97.59%) and true negative by support vector machine (99.96%) which is the almost same result obtained by the random forest true positive (97.30%) and true negative (99.38%) respectively. The reason that overall accuracy of random forest is high because the true positive of support vector machine and true negative of the decision tree is significantly less than the random forest.
Tasks
Published	2019-04-21
URL	http://arxiv.org/abs/1904.10142v1
PDF	http://arxiv.org/pdf/1904.10142v1.pdf
PWC	https://paperswithcode.com/paper/android-malicious-application-classification
Repo
Framework

Knowledge of Uncertain Worlds: Programming with Logical Constraints


Title	Knowledge of Uncertain Worlds: Programming with Logical Constraints
Authors	Yanhong A. Liu, Scott D. Stoller
Abstract	Programming with logic for sophisticated applications must deal with recursion and negation, which have created significant challenges in logic, leading to many different, conflicting semantics of rules. This paper describes a unified language, DA logic, for design and analysis logic, based on the unifying founded semantics and constraint semantics, that support the power and ease of programming with different intended semantics. The key idea is to provide meta constraints, support the use of uncertain information in the form of either undefined values or possible combinations of values, and promote the use of knowledge units that can be instantiated by any new predicates, including predicates with additional arguments.
Tasks
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10346v1
PDF	https://arxiv.org/pdf/1910.10346v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-of-uncertain-worlds-programming
Repo
Framework

Relational Mimic for Visual Adversarial Imitation Learning


Title	Relational Mimic for Visual Adversarial Imitation Learning
Authors	Lionel Blondé, Yichuan Charlie Tang, Jian Zhang, Russ Webb
Abstract	In this work, we introduce a new method for imitation learning from video demonstrations. Our method, Relational Mimic (RM), improves on previous visual imitation learning methods by combining generative adversarial networks and relational learning. RM is flexible and can be used in conjunction with other recent advances in generative adversarial imitation learning to better address the need for more robust and sample-efficient approaches. In addition, we introduce a new neural network architecture that improves upon the previous state-of-the-art in reinforcement learning and illustrate how increasing the relational reasoning capabilities of the agent enables the latter to achieve increasingly higher performance in a challenging locomotion task with pixel inputs. Finally, we study the effects and contributions of relational learning in policy evaluation, policy improvement and reward learning through ablation studies.
Tasks	Imitation Learning, Relational Reasoning
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08444v1
PDF	https://arxiv.org/pdf/1912.08444v1.pdf
PWC	https://paperswithcode.com/paper/relational-mimic-for-visual-adversarial
Repo
Framework

Improving Robustness of Machine Translation with Synthetic Noise


Title	Improving Robustness of Machine Translation with Synthetic Noise
Authors	Vaibhav Vaibhav, Sumeet Singh, Craig Stewart, Graham Neubig
Abstract	Modern Machine Translation (MT) systems perform consistently well on clean, in-domain text. However most human generated text, particularly in the realm of social media, is full of typos, slang, dialect, idiolect and other noise which can have a disastrous impact on the accuracy of output translation. In this paper we leverage the Machine Translation of Noisy Text (MTNT) dataset to enhance the robustness of MT systems by emulating naturally occurring noise in otherwise clean data. Synthesizing noise in this manner we are ultimately able to make a vanilla MT system resilient to naturally occurring noise and partially mitigate loss in accuracy resulting therefrom.
Tasks	Machine Translation
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09508v2
PDF	http://arxiv.org/pdf/1902.09508v2.pdf
PWC	https://paperswithcode.com/paper/improving-robustness-of-machine-translation
Repo
Framework

EvoMan: Game-playing Competition


Title	EvoMan: Game-playing Competition
Authors	Fabricio Olivetti de Franca, Denis Fantinato, Karine Miras, A. E. Eiben, Patricia A. Vargas
Abstract	This paper describes a competition proposal for evolving Intelligent Agents for the game-playing framework called EvoMan. The framework is based on the boss fights of the game called Mega Man II developed by Capcom. For this particular competition, the main goal is to beat all of the eight bosses using a generalist strategy. In other words, the competitors should train the agent to beat a set of the bosses and then the agent will be evaluated by its performance against all eight bosses. At the end of this paper, the competitors are provided with baseline results so that they can have an intuition on how good their results are.
Tasks
Published	2019-12-22
URL	https://arxiv.org/abs/1912.10445v3
PDF	https://arxiv.org/pdf/1912.10445v3.pdf
PWC	https://paperswithcode.com/paper/evoman-game-playing-competition
Repo
Framework

Exploring Domain Shift in Extractive Text Summarization


Title	Exploring Domain Shift in Extractive Text Summarization
Authors	Danqing Wang, Pengfei Liu, Ming Zhong, Jie Fu, Xipeng Qiu, Xuanjing Huang
Abstract	Although domain shift has been well explored in many NLP applications, it still has received little attention in the domain of extractive text summarization. As a result, the model is under-utilizing the nature of the training data due to ignoring the difference in the distribution of training sets and shows poor generalization on the unseen domain. With the above limitation in mind, in this paper, we first extend the conventional definition of the domain from categories into data sources for the text summarization task. Then we re-purpose a multi-domain summarization dataset and verify how the gap between different domains influences the performance of neural summarization models. Furthermore, we investigate four learning strategies and examine their abilities to deal with the domain shift problem. Experimental results on three different settings show their different characteristics in our new testbed. Our source code including \textit{BERT-based}, \textit{meta-learning} methods for multi-domain summarization learning and the re-purposed dataset \textsc{Multi-SUM} will be available on our project: \url{http://pfliu.com/TransferSum/}.
Tasks	Meta-Learning, Text Summarization
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11664v1
PDF	https://arxiv.org/pdf/1908.11664v1.pdf
PWC	https://paperswithcode.com/paper/exploring-domain-shift-in-extractive-text
Repo
Framework

On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of Constructions


Title	On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of Constructions
Authors	Rongrong Lin, Haizhang Zhang, Jun Zhang
Abstract	Recently, there has been emerging interest in constructing reproducing kernel Banach spaces (RKBS) for applied and theoretical purposes such as machine learning, sampling reconstruction, sparse approximation and functional analysis. Existing constructions include the reflexive RKBS via a bilinear form, the semi-inner-product RKBS, the RKBS with $\ell^1$ norm, the $p$-norm RKBS via generalized Mercer kernels, etc. The definitions of RKBS and the associated reproducing kernel in those references are dependent on the construction. Moreover, relations among those constructions are unclear. We explore a generic definition of RKBS and the reproducing kernel for RKBS that is independent of construction. Furthermore, we propose a framework of constructing RKBSs that unifies existing constructions mentioned above via a continuous bilinear form and a pair of feature maps. A new class of Orlicz RKBSs is proposed. Finally, we develop representer theorems for machine learning in RKBSs constructed in our framework, which also unifies representer theorems in existing RKBSs.
Tasks
Published	2019-01-04
URL	http://arxiv.org/abs/1901.01002v1
PDF	http://arxiv.org/pdf/1901.01002v1.pdf
PWC	https://paperswithcode.com/paper/on-reproducing-kernel-banach-spaces-generic
Repo
Framework

SimulCap : Single-View Human Performance Capture with Cloth Simulation


Title	SimulCap : Single-View Human Performance Capture with Cloth Simulation
Authors	Tao Yu, Zerong Zheng, Yuan Zhong, Jianhui Zhao, Qionghai Dai, Gerard Pons-Moll, Yebin Liu
Abstract	This paper proposes a new method for live free-viewpoint human performance capture with dynamic details (e.g., cloth wrinkles) using a single RGBD camera. Our main contributions are: (i) a multi-layer representation of garments and body, and (ii) a physics-based performance capture procedure. We first digitize the performer using multi-layer surface representation, which includes the undressed body surface and separate clothing meshes. For performance capture, we perform skeleton tracking, cloth simulation, and iterative depth fitting sequentially for the incoming frame. By incorporating cloth simulation into the performance capture pipeline, we can simulate plausible cloth dynamics and cloth-body interactions even in the occluded regions, which was not possible in previous capture methods. Moreover, by formulating depth fitting as a physical process, our system produces cloth tracking results consistent with the depth observation while still maintaining physical constraints. Results and evaluations show the effectiveness of our method. Our method also enables new types of applications such as cloth retargeting, free-viewpoint video rendering and animations.
Tasks
Published	2019-03-15
URL	http://arxiv.org/abs/1903.06323v2
PDF	http://arxiv.org/pdf/1903.06323v2.pdf
PWC	https://paperswithcode.com/paper/simulcap-single-view-human-performance
Repo
Framework

Search Based Repair of Deep Neural Networks


Title	Search Based Repair of Deep Neural Networks
Authors	Jeongju Sohn, Sungmin Kang, Shin Yoo
Abstract	Deep Neural Networks (DNNs) are being adopted in various domains, including safety critical ones. The wide-spread adoption also calls for ways to guide the testing of their accuracy and robustness, for which various test adequacy criteria and input generation methods have been recently introduced. In this paper, we explore the natural subsequent step: given an input that reveals unexpected behaviour in a trained DNN, we propose to repair the DNN using input-output pairs as a specification. This paper introduces Arachne, a novel program repair technique for DNNs. Arachne first performs sensitivity based fault localisation to limit the number of neural weights it has to modify. Subsequently, Arachne uses Particle Swarm Optimisation (PSO) to directly optimise the localised neural weights until the behaviour is corrected. An empirical study using three different benchmark datasets shows that Arachne can reduce the instances of the most frequent misclassification type committed by a pre-trained CIFAR-10 classifier by 27.5%, without any need for additional training data. Patches generated by Arachne tend to be more focused on the targeted misbehaviour than DNN retraining, which is more disruptive to non-targeted behaviour. The overall results suggest the feasibility of patching DNNs using Arachne until they can be retrained properly.
Tasks
Published	2019-12-28
URL	https://arxiv.org/abs/1912.12463v1
PDF	https://arxiv.org/pdf/1912.12463v1.pdf
PWC	https://paperswithcode.com/paper/search-based-repair-of-deep-neural-networks
Repo
Framework