January 30, 2020

2898 words 14 mins read

Paper Group ANR 239

Robust Classification with Sparse Representation Fusion on Diverse Data Subsets. Open DNN Box by Power Side-Channel Attack. User Curated Shaping of Expressive Performances. Improving Prediction Accuracy in Building Performance Models Using Generative Adversarial Networks (GANs). Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Sce …

Robust Classification with Sparse Representation Fusion on Diverse Data Subsets


Title	Robust Classification with Sparse Representation Fusion on Diverse Data Subsets
Authors	Chun-Mei Feng, Yong Xu, Zuoyong Li, Jian Yang
Abstract	Sparse Representation (SR) techniques encode the test samples into a sparse linear combination of all training samples and then classify the test samples into the class with the minimum residual. The classification of SR techniques depends on the representation capability on the test samples. However, most of these models view the representation problem of the test samples as a deterministic problem, ignoring the uncertainty of the representation. The uncertainty is caused by two factors, random noise in the samples and the intrinsic randomness of the sample set, which means that if we capture a group of samples, the obtained set of samples will be different in different conditions. In this paper, we propose a novel method based upon Collaborative Representation that is a special instance of SR and has closed-form solution. It performs Sparse Representation Fusion based on the Diverse Subset of training samples (SRFDS), which reduces the impact of randomness of the sample set and enhances the robustness of classification results. The proposed method is suitable for multiple types of data and has no requirement on the pattern type of the tasks. In addition, SRFDS not only preserves a closed-form solution but also greatly improves the classification performance. Promising results on various datasets serve as the evidence of better performance of SRFDS than other SR-based methods. The Matlab code of SRFDS will be accessible at http://www.yongxu.org/lunwen.html.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.11885v1
PDF	https://arxiv.org/pdf/1906.11885v1.pdf
PWC	https://paperswithcode.com/paper/robust-classification-with-sparse
Repo
Framework

Open DNN Box by Power Side-Channel Attack


Title	Open DNN Box by Power Side-Channel Attack
Authors	Yun Xiang, Zhuangzhi Chen, Zuohui Chen, Zebin Fang, Haiyang Hao, Jinyin Chen, Yi Liu, Zhefu Wu, Qi Xuan, Xiaoniu Yang
Abstract	Deep neural networks are becoming popular and important assets of many AI companies. However, recent studies indicate that they are also vulnerable to adversarial attacks. Adversarial attacks can be either white-box or black-box. The white-box attacks assume full knowledge of the models while the black-box ones assume none. In general, revealing more internal information can enable much more powerful and efficient attacks. However, in most real-world applications, the internal information of embedded AI devices is unavailable, i.e., they are black-box. Therefore, in this work, we propose a side-channel information based technique to reveal the internal information of black-box models. Specifically, we have made the following contributions: (1) we are the first to use side-channel information to reveal internal network architecture in embedded devices; (2) we are the first to construct models for internal parameter estimation; and (3) we validate our methods on real-world devices and applications. The experimental results show that our method can achieve 96.50% accuracy on average. Such results suggest that we should pay strong attention to the security problem of many AI applications, and further propose corresponding defensive strategies in the future.
Tasks
Published	2019-07-21
URL	https://arxiv.org/abs/1907.10406v1
PDF	https://arxiv.org/pdf/1907.10406v1.pdf
PWC	https://paperswithcode.com/paper/open-dnn-box-by-power-side-channel-attack
Repo
Framework

User Curated Shaping of Expressive Performances


Title	User Curated Shaping of Expressive Performances
Authors	Zhengshan Shi, Carlos Cancino-Chacón, Gerhard Widmer
Abstract	Musicians produce individualized, expressive performances by manipulating parameters such as dynamics, tempo and articulation. This manipulation of expressive parameters is informed by elements of score information such as pitch, meter, and tempo and dynamics markings (among others). In this paper we present an interactive interface that gives users the opportunity to explore the relationship between structural elements of a score and expressive parameters. This interface draws on the basis function models, a data-driven framework for expressive performance. In this framework, expressive parameters are modeled as a function of score features, i.e., numerical encodings of specific aspects of a musical score, using neural networks. With the proposed interface, users are able to weight the contribution of individual score features and understand how an expressive performance is constructed.
Tasks
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06428v1
PDF	https://arxiv.org/pdf/1906.06428v1.pdf
PWC	https://paperswithcode.com/paper/user-curated-shaping-of-expressive
Repo
Framework

Improving Prediction Accuracy in Building Performance Models Using Generative Adversarial Networks (GANs)


Title	Improving Prediction Accuracy in Building Performance Models Using Generative Adversarial Networks (GANs)
Authors	Chanachok Chokwitthaya, Edward Collier, Yimin Zhu, Supratik Mukhopadhyay
Abstract	Building performance discrepancies between building design and operation are one of the causes that lead many new designs fail to achieve their goals and objectives. One of main factors contributing to the discrepancy is occupant behaviors. Occupants responding to a new design are influenced by several factors. Existing building performance models (BPMs) ignore or partially address those factors (called contextual factors) while developing BPMs. To potentially reduce the discrepancies and improve the prediction accuracy of BPMs, this paper proposes a computational framework for learning mixture models by using Generative Adversarial Networks (GANs) that appropriately combining existing BPMs with knowledge on occupant behaviors to contextual factors in new designs. Immersive virtual environments (IVEs) experiments are used to acquire data on such behaviors. Performance targets are used to guide appropriate combination of existing BPMs with knowledge on occupant behaviors. The resulting model obtained is called an augmented BPM. Two different experiments related to occupant lighting behaviors are shown as case study. The results reveal that augmented BPMs significantly outperformed existing BPMs with respect to achieving specified performance targets. The case study confirms the potential of the computational framework for improving prediction accuracy of BPMs during design.
Tasks
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05767v2
PDF	https://arxiv.org/pdf/1906.05767v2.pdf
PWC	https://paperswithcode.com/paper/improving-prediction-accuracy-in-building
Repo
Framework

Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes


Title	Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes
Authors	Fabian Brickwedde, Steffen Abraham, Rudolf Mester
Abstract	Existing 3D scene flow estimation methods provide the 3D geometry and 3D motion of a scene and gain a lot of interest, for example in the context of autonomous driving. These methods are traditionally based on a temporal series of stereo images. In this paper, we propose a novel monocular 3D scene flow estimation method, called Mono-SF. Mono-SF jointly estimates the 3D structure and motion of the scene by combining multi-view geometry and single-view depth information. Mono-SF considers that the scene flow should be consistent in terms of warping the reference image in the consecutive image based on the principles of multi-view geometry. For integrating single-view depth in a statistical manner, a convolutional neural network, called ProbDepthNet, is proposed. ProbDepthNet estimates pixel-wise depth distributions from a single image rather than single depth values. Additionally, as part of ProbDepthNet, a novel recalibration technique for regression problems is proposed to ensure well-calibrated distributions. Our experiments show that Mono-SF outperforms state-of-the-art monocular baselines and ablation studies support the Mono-SF approach and ProbDepthNet design.
Tasks	Autonomous Driving, Scene Flow Estimation
Published	2019-08-17
URL	https://arxiv.org/abs/1908.06316v1
PDF	https://arxiv.org/pdf/1908.06316v1.pdf
PWC	https://paperswithcode.com/paper/mono-sf-multi-view-geometry-meets-single-view
Repo
Framework

Rescan: Inductive Instance Segmentation for Indoor RGBD Scans


Title	Rescan: Inductive Instance Segmentation for Indoor RGBD Scans
Authors	Maciej Halber, Yifei Shi, Kai Xu, Thomas Funkhouser
Abstract	In depth-sensing applications ranging from home robotics to AR/VR, it will be common to acquire 3D scans of interior spaces repeatedly at sparse time intervals (e.g., as part of regular daily use). We propose an algorithm that analyzes these “rescans” to infer a temporal model of a scene with semantic instance information. Our algorithm operates inductively by using the temporal model resulting from past observations to infer an instance segmentation of a new scan, which is then used to update the temporal model. The model contains object instance associations across time and thus can be used to track individual objects, even though there are only sparse observations. During experiments with a new benchmark for the new task, our algorithm outperforms alternate approaches based on state-of-the-art networks for semantic instance segmentation.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11268v1
PDF	https://arxiv.org/pdf/1909.11268v1.pdf
PWC	https://paperswithcode.com/paper/rescan-inductive-instance-segmentation-for
Repo
Framework

Aggregation in Value-Based Argumentation Frameworks


Title	Aggregation in Value-Based Argumentation Frameworks
Authors	Grzegorz Lisowski, Sylvie Doutre, Umberto Grandi
Abstract	Value-based argumentation enhances a classical abstract argumentation graph - in which arguments are modelled as nodes connected by directed arrows called attacks - with labels on arguments, called values, and an ordering on values, called audience, to provide a more fine-grained justification of the attack relation. With more than one agent facing such an argumentation problem, agents may differ in their ranking of values. When needing to reach a collective view, such agents face a dilemma between two equally justifiable approaches: aggregating their views at the level of values, or aggregating their attack relations, remaining therefore at the level of the graphs. We explore the strenghts and limitations of both approaches, employing techniques from preference aggregation and graph aggregation, and propose a third possibility aggregating rankings extracted from given attack relations.
Tasks	Abstract Argumentation
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09113v1
PDF	https://arxiv.org/pdf/1907.09113v1.pdf
PWC	https://paperswithcode.com/paper/aggregation-in-value-based-argumentation
Repo
Framework

Locally Constant Networks


Title	Locally Constant Networks
Authors	Guang-He Lee, Tommi S. Jaakkola
Abstract	We show how neural models can be used to realize piece-wise constant functions such as decision trees. Our approach builds on ReLU networks that are piece-wise linear and hence their associated gradients with respect to the inputs are locally constant. We formally establish the equivalence between the classes of locally constant networks and decision trees. Moreover, we highlight several advantageous properties of locally constant networks, including how they realize decision trees with parameter sharing across branching / leaves. Indeed, only $M$ neurons suffice to implicitly model an oblique decision tree with $2^M$ leaf nodes. The neural representation also enables us to adopt many tools developed for deep networks (e.g., DropConnect (Wan et al. 2013)) while implicitly training decision trees. We demonstrate that our method outperforms alternative techniques for training oblique decision trees in the context of molecular property classification and regression tasks.
Tasks
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13488v1
PDF	https://arxiv.org/pdf/1909.13488v1.pdf
PWC	https://paperswithcode.com/paper/locally-constant-networks
Repo
Framework

Foundations of Digital Archæoludology


Title	Foundations of Digital Archæoludology
Authors	Cameron Browne, Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Michael Conrad, Walter Crist, Thierry Depaulis, Eddie Duggan, Fred Horn, Steven Kelk, Simon M. Lucas, João Pedro Neto, David Parlett, Abdallah Saffidine, Ulrich Schädler, Jorge Nuno Silva, Alex de Voogt, Mark H. M. Winands
Abstract	Digital Archaeoludology (DAL) is a new field of study involving the analysis and reconstruction of ancient games from incomplete descriptions and archaeological evidence using modern computational techniques. The aim is to provide digital tools and methods to help game historians and other researchers better understand traditional games, their development throughout recorded human history, and their relationship to the development of human culture and mathematical knowledge. This work is being explored in the ERC-funded Digital Ludeme Project. The aim of this inaugural international research meeting on DAL is to gather together leading experts in relevant disciplines - computer science, artificial intelligence, machine learning, computational phylogenetics, mathematics, history, archaeology, anthropology, etc. - to discuss the key themes and establish the foundations for this new field of research, so that it may continue beyond the lifetime of its initiating project.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1905.13516v1
PDF	https://arxiv.org/pdf/1905.13516v1.pdf
PWC	https://paperswithcode.com/paper/foundations-of-digital-archoludology
Repo
Framework

Unsupervised Image-to-Image Translation with Self-Attention Networks


Title	Unsupervised Image-to-Image Translation with Self-Attention Networks
Authors	Taewon Kang, Kwang Hee Lee
Abstract	Unsupervised image translation aims to learn the transformation from a source domain to another target domain given unpaired training data. Several state-of-the-art works have yielded impressive results in the GANs-based unsupervised image-to-image translation. It fails to capture strong geometric or structural changes between domains, or it produces unsatisfactory result for complex scenes, compared to local texture mapping tasks such as style transfer. Recently, SAGAN (Han Zhang, 2018) showed that the self-attention network produces better results than the convolution-based GAN. However, the effectiveness of the self-attention network in unsupervised image-to-image translation tasks have not been verified. In this paper, we propose an unsupervised image-to-image translation with self-attention networks, in which long range dependency helps to not only capture strong geometric change but also generate details using cues from all feature locations. In experiments, we qualitatively and quantitatively show superiority of the proposed method compared to existing state-of-the-art unsupervised image-to-image translation task.
Tasks	Image-to-Image Translation, Style Transfer, Unsupervised Image-To-Image Translation
Published	2019-01-24
URL	https://arxiv.org/abs/1901.08242v3
PDF	https://arxiv.org/pdf/1901.08242v3.pdf
PWC	https://paperswithcode.com/paper/unsupervised-image-to-image-translation-with-1
Repo
Framework

Safe Approximate Dynamic Programming Via Kernelized Lipschitz Estimation


Title	Safe Approximate Dynamic Programming Via Kernelized Lipschitz Estimation
Authors	Ankush Chakrabarty, Devesh K. Jha, Gregery T. Buzzard, Yebin Wang, Kyriakos Vamvoudakis
Abstract	We develop a method for obtaining safe initial policies for reinforcement learning via approximate dynamic programming (ADP) techniques for uncertain systems evolving with discrete-time dynamics. We employ kernelized Lipschitz estimation and semidefinite programming for computing admissible initial control policies with provably high probability. Such admissible controllers enable safe initialization and constraint enforcement while providing exponential stability of the equilibrium of the closed-loop system.
Tasks
Published	2019-07-03
URL	https://arxiv.org/abs/1907.02151v1
PDF	https://arxiv.org/pdf/1907.02151v1.pdf
PWC	https://paperswithcode.com/paper/safe-approximate-dynamic-programming-via
Repo
Framework

American Sign Language Alphabet Recognition using Deep Learning


Title	American Sign Language Alphabet Recognition using Deep Learning
Authors	Nikhil Kasukurthi, Brij Rokad, Shiv Bidani, Dr. Aju Dennisan
Abstract	Tremendous headway has been made in the field of 3D hand pose estimation but the 3D depth cameras are usually inaccessible. We propose a model to recognize American Sign Language alphabet from RGB images. Images for the training were resized and pre-processed before training the Deep Neural Network. The model was trained on a squeezenet architecture to make it capable of running on mobile devices with an accuracy of 83.29%.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05487v1
PDF	https://arxiv.org/pdf/1905.05487v1.pdf
PWC	https://paperswithcode.com/paper/american-sign-language-alphabet-recognition
Repo
Framework

The Domain Shift Problem of Medical Image Segmentation and Vendor-Adaptation by Unet-GAN


Title	The Domain Shift Problem of Medical Image Segmentation and Vendor-Adaptation by Unet-GAN
Authors	Wenjun Yan, Yuanyuan Wang, Shengjia Gu, Lu Huang, Fuhua Yan, Liming Xia, Qian Tao
Abstract	Convolutional neural network (CNN), in particular the Unet, is a powerful method for medical image segmentation. To date Unet has demonstrated state-of-art performance in many complex medical image segmentation tasks, especially under the condition when the training and testing data share the same distribution (i.e. come from the same source domain). However, in clinical practice, medical images are acquired from different vendors and centers. The performance of a U-Net trained from a particular source domain, when transferred to a different target domain (e.g. different vendor, acquisition parameter), can drop unexpectedly. Collecting a large amount of annotation from each new domain to retrain the U-Net is expensive, tedious, and practically impossible. In this work, we proposed a generic framework to address this problem, consisting of (1) an unpaired generative adversarial network (GAN) for vendor-adaptation, and (2) a Unet for object segmentation. In the proposed Unet-GAN architecture, GAN learns from Unet at the feature level that is segmentation-specific. We used cardiac cine MRI as the example, with three major vendors (Philips, Siemens, and GE) as three domains, while the methodology can be extended to medical images segmentation in general. The proposed method showed significant improvement of the segmentation results across vendors. The proposed Unet-GAN provides an annotation-free solution to the cross-vendor medical image segmentation problem, potentially extending a trained deep learning model to multi-center and multi-vendor use in real clinical scenario.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2019-10-30
URL	https://arxiv.org/abs/1910.13681v1
PDF	https://arxiv.org/pdf/1910.13681v1.pdf
PWC	https://paperswithcode.com/paper/the-domain-shift-problem-of-medical-image
Repo
Framework

The Label Complexity of Active Learning from Observational Data


Title	The Label Complexity of Active Learning from Observational Data
Authors	Songbai Yan, Kamalika Chaudhuri, Tara Javidi
Abstract	Counterfactual learning from observational data involves learning a classifier on an entire population based on data that is observed conditioned on a selection policy. This work considers this problem in an active setting, where the learner additionally has access to unlabeled examples and can choose to get a subset of these labeled by an oracle. Prior work on this problem uses disagreement-based active learning, along with an importance weighted loss estimator to account for counterfactuals, which leads to a high label complexity. We show how to instead incorporate a more efficient counterfactual risk minimizer into the active learning algorithm. This requires us to modify both the counterfactual risk to make it amenable to active learning, as well as the active learning process to make it amenable to the risk. We provably demonstrate that the result of this is an algorithm which is statistically consistent as well as more label-efficient than prior work.
Tasks	Active Learning
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12791v2
PDF	https://arxiv.org/pdf/1905.12791v2.pdf
PWC	https://paperswithcode.com/paper/the-label-complexity-of-active-learning-from
Repo
Framework

Exploring Feature Representation and Training strategies in Temporal Action Localization


Title	Exploring Feature Representation and Training strategies in Temporal Action Localization
Authors	Tingting Xie, Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu, Ioannis Patras
Abstract	Temporal action localization has recently attracted significant interest in the Computer Vision community. However, despite the great progress, it is hard to identify which aspects of the proposed methods contribute most to the increase in localization performance. To address this issue, we conduct ablative experiments on feature extraction methods, fixed-size feature representation methods and training strategies, and report how each influences the overall performance. Based on our findings, we propose a two-stage detector that outperforms the state of the art in THUMOS14, achieving a mAP@tIoU=0.5 equal to 44.2%.
Tasks	Action Localization, Temporal Action Localization
Published	2019-05-25
URL	https://arxiv.org/abs/1905.10608v2
PDF	https://arxiv.org/pdf/1905.10608v2.pdf
PWC	https://paperswithcode.com/paper/exploring-feature-representation-and-training
Repo
Framework