January 27, 2020

3388 words 16 mins read

Paper Group ANR 1129

ER-AE: Differentially-private Text Generation for Authorship Anonymization. Completing and Debugging Ontologies: state of the art and challenges. Fully Automatic Brain Tumor Segmentation using a Normalized Gaussian Bayesian Classifier and 3D Fluid Vector Flow. Guiding Variational Response Generator to Exploit Persona. Post-mortem Iris Decomposition …

ER-AE: Differentially-private Text Generation for Authorship Anonymization


Title	ER-AE: Differentially-private Text Generation for Authorship Anonymization
Authors	Haohan Bo, Steven H. H. Ding, Benjamin C. M. Fung, Farkhund Iqbal
Abstract	Most of privacy protection studies for textual data focus on removing explicit sensitive identifiers. However, personal writing style, as a strong indicator of the authorship, is often neglected. Recent studies on writing style anonymization can only output numeric vectors which are difficult for the recipients to interpret. We propose a novel text generation model with the exponential mechanism for authorship anonymization. By augmenting the semantic information through a REINFORCE training reward function, the model can generate differentially-private text that has a close semantic and similar grammatical structure to the original text while removing personal traits of the writing style. It does not assume any conditioned labels or paralleled text data for training. We evaluate the performance of the proposed model on the real-life peer reviews dataset and the Yelp review dataset. The result suggests that our model outperforms the state-of-the-art on semantic preservation, authorship obfuscation, and stylometric transformation.
Tasks	Text Generation
Published	2019-07-20
URL	https://arxiv.org/abs/1907.08736v3
PDF	https://arxiv.org/pdf/1907.08736v3.pdf
PWC	https://paperswithcode.com/paper/er-ae-differentially-private-text-generation
Repo
Framework

Completing and Debugging Ontologies: state of the art and challenges


Title	Completing and Debugging Ontologies: state of the art and challenges
Authors	Patrick Lambrix
Abstract	As semantically-enabled applications require high-quality ontologies, developing and maintaining as correct and complete as possible ontologies is an important, although difficult task in ontology engineering. A key step is ontology debugging and completion. In general, there are two steps: detecting defects and repairing defects. In this paper we formalize the repairing step as an abduction problem and situate the state of the art with respect to this framework. We show that there still are many open research problems and show opportunities for further work and advancing the field.
Tasks
Published	2019-08-08
URL	https://arxiv.org/abs/1908.03171v1
PDF	https://arxiv.org/pdf/1908.03171v1.pdf
PWC	https://paperswithcode.com/paper/completing-and-debugging-ontologies-state-of
Repo
Framework

Fully Automatic Brain Tumor Segmentation using a Normalized Gaussian Bayesian Classifier and 3D Fluid Vector Flow


Title	Fully Automatic Brain Tumor Segmentation using a Normalized Gaussian Bayesian Classifier and 3D Fluid Vector Flow
Authors	Tao Wang, Irene Cheng, Anup Basu
Abstract	Brain tumor segmentation from Magnetic Resonance Images (MRIs) is an important task to measure tumor responses to treatments. However, automatic segmentation is very challenging. This paper presents an automatic brain tumor segmentation method based on a Normalized Gaussian Bayesian classification and a new 3D Fluid Vector Flow (FVF) algorithm. In our method, a Normalized Gaussian Mixture Model (NGMM) is proposed and used to model the healthy brain tissues. Gaussian Bayesian Classifier is exploited to acquire a Gaussian Bayesian Brain Map (GBBM) from the test brain MR images. GBBM is further processed to initialize the 3D FVF algorithm, which segments the brain tumor. This algorithm has two major contributions. First, we present a NGMM to model healthy brains. Second, we extend our 2D FVF algorithm to 3D space and use it for brain tumor segmentation. The proposed method is validated on a publicly available dataset.
Tasks	Brain Tumor Segmentation
Published	2019-05-01
URL	http://arxiv.org/abs/1905.00469v1
PDF	http://arxiv.org/pdf/1905.00469v1.pdf
PWC	https://paperswithcode.com/paper/fully-automatic-brain-tumor-segmentation
Repo
Framework

Guiding Variational Response Generator to Exploit Persona


Title	Guiding Variational Response Generator to Exploit Persona
Authors	Bowen Wu, Mengyuan Li, Zongsheng Wang, Yifu Chen, Derek Wong, Qihang Feng, Junhong Huang, Baoxun Wang
Abstract	Leveraging persona information of users in Neural Response Generators (NRG) to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over the past few years. Despite of the promising progresses achieved by recent studies in this field, persona information tends to be incorporated into neural networks in the form of user embeddings, with the expectation that the persona can be involved via the End-to-End learning. This paper proposes to adopt the personality-related characteristics of human conversations into variational response generators, by designing a specific conditional variational autoencoder based deep model with two new regularization terms employed to the loss function, so as to guide the optimization towards the direction of generating both persona-aware and relevant responses. Besides, to reasonably evaluate the performances of various persona modeling approaches, this paper further presents three direct persona-oriented metrics from different perspectives. The experimental results have shown that our proposed methodology can notably improve the performance of persona-aware response generation, and the metrics are reasonable to evaluate the results.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02390v1
PDF	https://arxiv.org/pdf/1911.02390v1.pdf
PWC	https://paperswithcode.com/paper/guiding-variational-response-generator-to
Repo
Framework

Post-mortem Iris Decomposition and its Dynamics in Morgue Conditions


Title	Post-mortem Iris Decomposition and its Dynamics in Morgue Conditions
Authors	Mateusz Trokielewicz, Adam Czajka, Piotr Maciejewicz
Abstract	With increasing interest in employing iris biometrics as a forensic tool for identification by investigation authorities, there is a need for a thorough examination and understanding of post-mortem decomposition processes that take place within the human eyeball, especially the iris. This can prove useful for fast and accurate matching of ante-mortem with post-mortem data acquired at crime scenes or mass casualties, as well as for ensuring correct dispatching of bodies from the incident scene to a mortuary or funeral homes. Following these needs of forensic community, this paper offers an analysis of the coarse effects of eyeball decay done from a perspective of automatic iris recognition point of view. Therefore, we analyze post-mortem iris images acquired in both visible light as well as in near-infrared light (860 nm), as the latter wavelength is used in commercial iris recognition systems. Conclusions and suggestions are provided that may aid forensic examiners in successfully utilizing iris patterns in post-mortem identification of deceased subjects. Initial guidelines regarding the imaging process, types of illumination, resolution are also given, together with expectations with respect to the iris features decomposition rates.
Tasks	Iris Recognition
Published	2019-11-07
URL	https://arxiv.org/abs/1911.02837v1
PDF	https://arxiv.org/pdf/1911.02837v1.pdf
PWC	https://paperswithcode.com/paper/post-mortem-iris-decomposition-and-its
Repo
Framework

Micro-expression Action Unit Detection withSpatio-temporal Adaptive Pooling


Title	Micro-expression Action Unit Detection withSpatio-temporal Adaptive Pooling
Authors	Yante Li, Xiaohua Huang, Guoying Zhao
Abstract	Action Unit (AU) detection plays an important role for facial expression recognition. To the best of our knowledge, there is little research about AU analysis for micro-expressions. In this paper, we focus on AU detection in micro-expressions. Microexpression AU detection is challenging due to the small quantity of micro-expression databases, low intensity, short duration of facial muscle change, and class imbalance. In order to alleviate the problems, we propose a novel Spatio-Temporal Adaptive Pooling (STAP) network for AU detection in micro-expressions. Firstly, STAP is aggregated by a series of convolutional filters of different sizes. In this way, STAP can obtain multi-scale information on spatial and temporal domains. On the other hand, STAP contains less parameters, thus it has less computational cost and is suitable for micro-expression AU detection on very small databases. Furthermore, STAP module is designed to pool discriminative information for micro-expression AUs on spatial and temporal domains.Finally, Focal loss is employed to prevent the vast number of negatives from overwhelming the microexpression AU detector. In experiments, we firstly polish the AU annotations on three commonly used databases. We conduct intensive experiments on three micro-expression databases, and provide several baseline results on micro-expression AU detection. The results show that our proposed approach outperforms the basic Inflated inception-v1 (I3D) in terms of an average of F1- score. We also evaluate the performance of our proposed method on cross-database protocol. It demonstrates that our proposed approach is feasible for cross-database micro-expression AU detection. Importantly, the results on three micro-expression databases and cross-database protocol provide extensive baseline results for future research on micro-expression AU detection.
Tasks	Action Unit Detection, Facial Expression Recognition
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05023v1
PDF	https://arxiv.org/pdf/1907.05023v1.pdf
PWC	https://paperswithcode.com/paper/micro-expression-action-unit-detection
Repo
Framework

Towards semi-supervised segmentation via image-to-image translation


Title	Towards semi-supervised segmentation via image-to-image translation
Authors	Eugene Vorontsov, Pavlo Molchanov, Christopher Beckham, Wonmin Byeon, Shalini De Mello, Varun Jampani, Ming-Yu Liu, Samuel Kadoury, Jan Kautz
Abstract	In many cases, especially with medical images, it is prohibitively challenging to produce a sufficiently large training sample of pixel-level annotations to train deep neural networks for semantic image segmentation. On the other hand, some information is often known about the contents of images. We leverage information on whether an image presents the segmentation target or whether it is absent from the image to improve segmentation performance by augmenting the amount of data usable for model training. Specifically, we propose a semi-supervised framework that employs image-to-image translation between weak labels (e.g., presence vs. absence of cancer), in addition to fully supervised segmentation on some examples. We conjecture that this translation objective is well aligned with the segmentation objective as both require the same disentangling of image variations. Building on prior image-to-image translation work, we re-use the encoder and decoders for translating in either direction between two domains, employing a strategy of selectively decoding domain-specific variations. For presence vs. absence domains, the encoder produces variations that are common to both and those unique to the presence domain. Furthermore, we successfully re-use one of the decoders used in translation for segmentation. We validate the proposed method on synthetic tasks of varying difficulty as well as on the real task of brain tumor segmentation in magnetic resonance images, where we show significant improvements over standard semi-supervised training with autoencoding.
Tasks	Brain Tumor Segmentation, Image-to-Image Translation, Semantic Segmentation
Published	2019-04-02
URL	https://arxiv.org/abs/1904.01636v3
PDF	https://arxiv.org/pdf/1904.01636v3.pdf
PWC	https://paperswithcode.com/paper/boosting-segmentation-with-weak-supervision
Repo
Framework

Modeling Teacher-Student Techniques in Deep Neural Networks for Knowledge Distillation


Title	Modeling Teacher-Student Techniques in Deep Neural Networks for Knowledge Distillation
Authors	Sajjad Abbasi, Mohsen Hajabdollahi, Nader Karimi, Shadrokh Samavi
Abstract	Knowledge distillation (KD) is a new method for transferring knowledge of a structure under training to another one. The typical application of KD is in the form of learning a small model (named as a student) by soft labels produced by a complex model (named as a teacher). Due to the novel idea introduced in KD, recently, its notion is used in different methods such as compression and processes that are going to enhance the model accuracy. Although different techniques are proposed in the area of KD, there is a lack of a model to generalize KD techniques. In this paper, various studies in the scope of KD are investigated and analyzed to build a general model for KD. All the methods and techniques in KD can be summarized through the proposed model. By utilizing the proposed model, different methods in KD are better investigated and explored. The advantages and disadvantages of different approaches in KD can be better understood and develop a new strategy for KD can be possible. Using the proposed model, different KD methods are represented in an abstract view.
Tasks
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13179v1
PDF	https://arxiv.org/pdf/1912.13179v1.pdf
PWC	https://paperswithcode.com/paper/modeling-teacher-student-techniques-in-deep
Repo
Framework

Visual SLAM: Why Bundle Adjust?


Title	Visual SLAM: Why Bundle Adjust?
Authors	Álvaro Parra, Tat-Jun Chin, Anders Eriksson, Ian Reid
Abstract	Bundle adjustment plays a vital role in feature-based monocular SLAM. In many modern SLAM pipelines, bundle adjustment is performed to estimate the 6DOF camera trajectory and 3D map (3D point cloud) from the input feature tracks. However, two fundamental weaknesses plague SLAM systems based on bundle adjustment. First, the need to carefully initialise bundle adjustment means that all variables, in particular the map, must be estimated as accurately as possible and maintained over time, which makes the overall algorithm cumbersome. Second, since estimating the 3D structure (which requires sufficient baseline) is inherent in bundle adjustment, the SLAM algorithm will encounter difficulties during periods of slow motion or pure rotational motion. We propose a different SLAM optimisation core: instead of bundle adjustment, we conduct rotation averaging to incrementally optimise only camera orientations. Given the orientations, we estimate the camera positions and 3D points via a quasi-convex formulation that can be solved efficiently and globally optimally. Our approach not only obviates the need to estimate and maintain the positions and 3D map at keyframe rate (which enables simpler SLAM systems), it is also more capable of handling slow motions or pure rotational motions.
Tasks
Published	2019-02-11
URL	https://arxiv.org/abs/1902.03747v2
PDF	https://arxiv.org/pdf/1902.03747v2.pdf
PWC	https://paperswithcode.com/paper/visual-slam-why-bundle-adjust
Repo
Framework

Low Shot Learning with Untrained Neural Networks for Imaging Inverse Problems


Title	Low Shot Learning with Untrained Neural Networks for Imaging Inverse Problems
Authors	Oscar Leong, Wesam Sakla
Abstract	Employing deep neural networks as natural image priors to solve inverse problems either requires large amounts of data to sufficiently train expressive generative models or can succeed with no data via untrained neural networks. However, very few works have considered how to interpolate between these no- to high-data regimes. In particular, how can one use the availability of a small amount of data (even $5-25$ examples) to one’s advantage in solving these inverse problems and can a system’s performance increase as the amount of data increases as well? In this work, we consider solving linear inverse problems when given a small number of examples of images that are drawn from the same distribution as the image of interest. Comparing to untrained neural networks that use no data, we show how one can pre-train a neural network with a few given examples to improve reconstruction results in compressed sensing and semantic image recovery problems such as colorization. Our approach leads to improved reconstruction as the amount of available data increases and is on par with fully trained generative models, while requiring less than $1 %$ of the data needed to train a generative model.
Tasks	Colorization
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10797v1
PDF	https://arxiv.org/pdf/1910.10797v1.pdf
PWC	https://paperswithcode.com/paper/low-shot-learning-with-untrained-neural
Repo
Framework

Clustering with Similarity Preserving


Title	Clustering with Similarity Preserving
Authors	Zhao Kang, Honghui Xu, Boyu Wang, Hongyuan Zhu, Zenglin Xu
Abstract	Graph-based clustering has shown promising performance in many tasks. A key step of graph-based approach is the similarity graph construction. In general, learning graph in kernel space can enhance clustering accuracy due to the incorporation of nonlinearity. However, most existing kernel-based graph learning mechanisms is not similarity-preserving, hence leads to sub-optimal performance. To overcome this drawback, we propose a more discriminative graph learning method which can preserve the pairwise similarities between samples in an adaptive manner for the first time. Specifically, we require the learned graph be close to a kernel matrix, which serves as a measure of similarity in raw data. Moreover, the structure is adaptively tuned so that the number of connected components of the graph is exactly equal to the number of clusters. Finally, our method unifies clustering and graph learning which can directly obtain cluster indicators from the graph itself without performing further clustering step. The effectiveness of this approach is examined on both single and multiple kernel learning scenarios in several datasets.
Tasks	graph construction
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08419v1
PDF	https://arxiv.org/pdf/1905.08419v1.pdf
PWC	https://paperswithcode.com/paper/clustering-with-similarity-preserving
Repo
Framework

Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar


Title	Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar
Authors	Nicolas Scheiner, Florian Kraus, Fangyin Wei, Buu Phan, Fahim Mannan, Nils Appenrodt, Werner Ritter, Jürgen Dickmann, Klaus Dietmayer, Bernhard Sick, Felix Heide
Abstract	Conventional sensor systems record information about directly visible objects, whereas occluded scene components are considered lost in the measurement process. Non-line-of-sight (NLOS) methods try to recover such hidden objects from their indirect reflections - faint signal components, traditionally treated as measurement noise. Existing NLOS approaches struggle to record these low-signal components outside the lab, and do not scale to large-scale outdoor scenes and high-speed motion, typical in automotive scenarios. In particular, optical NLOS capture is fundamentally limited by the quartic intensity falloff of diffuse indirect reflections. In this work, we depart from visible-wavelength approaches and demonstrate detection, classification, and tracking of hidden objects in large-scale dynamic environments using Doppler radars that can be manufactured at low-cost in series production. To untangle noisy indirect and direct reflections, we learn from temporal sequences of Doppler velocity and position measurements, which we fuse in a joint NLOS detection and tracking network over time. We validate the approach on in-the-wild automotive scenes, including sequences of parked cars or house facades as relay surfaces, and demonstrate low-cost, real-time NLOS in dynamic automotive environments.
Tasks
Published	2019-12-13
URL	https://arxiv.org/abs/1912.06613v2
PDF	https://arxiv.org/pdf/1912.06613v2.pdf
PWC	https://paperswithcode.com/paper/seeing-around-street-corners-non-line-of
Repo
Framework

First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise


Title	First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise
Authors	Thanh Huy Nguyen, Umut Şimşekli, Mert Gürbüzbalaban, Gaël Richard
Abstract	Stochastic gradient descent (SGD) has been widely used in machine learning due to its computational efficiency and favorable generalization properties. Recently, it has been empirically demonstrated that the gradient noise in several deep learning settings admits a non-Gaussian, heavy-tailed behavior. This suggests that the gradient noise can be modeled by using $\alpha$-stable distributions, a family of heavy-tailed distributions that appear in the generalized central limit theorem. In this context, SGD can be viewed as a discretization of a stochastic differential equation (SDE) driven by a L'{e}vy motion, and the metastability results for this SDE can then be used for illuminating the behavior of SGD, especially in terms of `preferring wide minima’. While this approach brings a new perspective for analyzing SGD, it is limited in the sense that, due to the time discretization, SGD might admit a significantly different behavior than its continuous-time limit. Intuitively, the behaviors of these two systems are expected to be similar to each other only when the discretization step is sufficiently small; however, to the best of our knowledge, there is no theoretical understanding on how small the step-size should be chosen in order to guarantee that the discretized system inherits the properties of the continuous-time system. In this study, we provide formal theoretical analysis where we derive explicit conditions for the step-size such that the metastability behavior of the discrete-time system is similar to its continuous-time limit. We show that the behaviors of the two systems are indeed similar for small step-sizes and we identify how the error depends on the algorithm and problem parameters. We illustrate our results with simulations on a synthetic model and neural networks. \|
Tasks
Published	2019-06-21
URL	https://arxiv.org/abs/1906.09069v1
PDF	https://arxiv.org/pdf/1906.09069v1.pdf
PWC	https://paperswithcode.com/paper/first-exit-time-analysis-of-stochastic
Repo
Framework

Signal Instructed Coordination in Cooperative Multi-agent Reinforcement Learning


Title	Signal Instructed Coordination in Cooperative Multi-agent Reinforcement Learning
Authors	Liheng Chen, Hongyi Guo, Yali Du, Fei Fang, Haifeng Zhang, Yaoming Zhu, Ming Zhou, Weinan Zhang, Qing Wang, Yong Yu
Abstract	In many real-world problems, a team of agents need to collaborate to maximize the common reward. Although existing works formulate this problem into a centralized learning with decentralized execution framework, which avoids the non-stationary problem in training, their decentralized execution paradigm limits the agents’ capability to coordinate. Inspired by the concept of correlated equilibrium, we propose to introduce a coordination signal to address this limitation, and theoretically show that following mild conditions, decentralized agents with the coordination signal can coordinate their individual policies as manipulated by a centralized controller. The idea of introducing coordination signal is to encapsulate coordinated strategies into the signals, and use the signals to instruct the collaboration in decentralized execution. To encourage agents to learn to exploit the coordination signal, we propose Signal Instructed Coordination (SIC), a novel coordination module that can be integrated with most existing MARL frameworks. SIC casts a common signal sampled from a pre-defined distribution to all agents, and introduces an information-theoretic regularization to facilitate the consistency between the observed signal and agents’ policies. Our experiments show that SIC consistently improves performance over well-recognized MARL models in both matrix games and a predator-prey game with high-dimensional strategy space.
Tasks	Multi-agent Reinforcement Learning
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04224v2
PDF	https://arxiv.org/pdf/1909.04224v2.pdf
PWC	https://paperswithcode.com/paper/signal-instructed-coordination-in-team
Repo
Framework

Orthogonal variance decomposition based feature selection


Title	Orthogonal variance decomposition based feature selection
Authors	Firuz Kamalov
Abstract	Existing feature selection methods fail to properly account for interactions between features when evaluating feature subsets. In this paper, we attempt to remedy this issue by using orthogonal variance decomposition to evaluate features. The orthogonality of the decomposition allows us to directly calculate the total contribution of a feature to the output variance. Thus we obtain an efficient algorithm for feature evaluation which takes into account interactions among features. Numerical experiments demonstrate that our method accurately identifies relevant features and improves the accuracy of numerical models.
Tasks	Feature Selection
Published	2019-10-22
URL	https://arxiv.org/abs/1910.09851v1
PDF	https://arxiv.org/pdf/1910.09851v1.pdf
PWC	https://paperswithcode.com/paper/orthogonal-variance-decomposition-based
Repo
Framework