January 30, 2020

3019 words 15 mins read

Paper Group ANR 322

Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations. OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization. Sparse inversion for derivative of log determinant. BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts. Robust learning with implicit residual networks. Moti …

Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations


Title	Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations
Authors	Yuezun Li, Xin Yang, Baoyuan Wu, Siwei Lyu
Abstract	Recent years have seen fast development in synthesizing realistic human faces using AI technologies. Such fake faces can be weaponized to cause negative personal and social impact. In this work, we develop technologies to defend individuals from becoming victims of recent AI synthesized fake videos by sabotaging would-be training data. This is achieved by disrupting deep neural network (DNN) based face detection method with specially designed imperceptible adversarial perturbations to reduce the quality of the detected faces. We describe attacking schemes under white-box, gray-box and black-box settings, each with decreasing information about the DNN based face detectors. We empirically show the effectiveness of our methods in disrupting state-of-the-art DNN based face detectors on several datasets.
Tasks	Face Detection, Face Generation
Published	2019-06-21
URL	https://arxiv.org/abs/1906.09288v1
PDF	https://arxiv.org/pdf/1906.09288v1.pdf
PWC	https://paperswithcode.com/paper/hiding-faces-in-plain-sight-disrupting-ai
Repo
Framework

OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization


Title	OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization
Authors	Bingchen Liu, Yizhe Zhu, Zuohui Fu, Gerard de Melo, Ahmed Elgammal
Abstract	Exploring the potential of GANs for unsupervised disentanglement learning, this paper proposes a novel GAN-based disentanglement framework with One-Hot Sampling and Orthogonal Regularization (OOGAN). While previous works mostly attempt to tackle disentanglement learning through VAE and seek to implicitly minimize the Total Correlation (TC) objective with various sorts of approximation methods, we show that GANs have a natural advantage in disentangling with an alternating latent variable (noise) sampling method that is straightforward and robust. Furthermore, we provide a brand-new perspective on designing the structure of the generator and discriminator, demonstrating that a minor structural change and an orthogonal regularization on model weights entails an improved disentanglement. Instead of experimenting on simple toy datasets, we conduct experiments on higher-resolution images and show that OOGAN greatly pushes the boundary of unsupervised disentanglement.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10836v5
PDF	https://arxiv.org/pdf/1905.10836v5.pdf
PWC	https://paperswithcode.com/paper/oogan-disentangling-gan-with-one-hot-sampling
Repo
Framework

Sparse inversion for derivative of log determinant


Title	Sparse inversion for derivative of log determinant
Authors	Shengxin Zhu, Andrew J Wathen
Abstract	Algorithms for Gaussian process, marginal likelihood methods or restricted maximum likelihood methods often require derivatives of log determinant terms. These log determinants are usually parametric with variance parameters of the underlying statistical models. This paper demonstrates that, when the underlying matrix is sparse, how to take the advantage of sparse inversion—selected inversion which share the same sparsity as the original matrix—to accelerate evaluating the derivative of log determinant.
Tasks
Published	2019-11-02
URL	https://arxiv.org/abs/1911.00685v1
PDF	https://arxiv.org/pdf/1911.00685v1.pdf
PWC	https://paperswithcode.com/paper/sparse-inversion-for-derivative-of-log
Repo
Framework

BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts


Title	BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts
Authors	Benjamin Kiessling, Daniel Stökl Ben Ezra, Matthew Thomas Miller
Abstract	The application of handwritten text recognition to historical works is highly dependant on accurate text line retrieval. A number of systems utilizing a robust baseline detection paradigm have emerged recently but the advancement of layout analysis methods for challenging scripts is held back by the lack of well-established datasets including works in non-Latin scripts. We present a dataset of 400 annotated document images from different domains and time periods. A short elaboration on the particular challenges posed by handwriting in Arabic script for layout analysis and subsequent processing steps is given. Lastly, we propose a method based on a fully convolutional encoder-decoder network to extract arbitrarily shaped text line images from manuscripts.
Tasks
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04041v1
PDF	https://arxiv.org/pdf/1907.04041v1.pdf
PWC	https://paperswithcode.com/paper/badam-a-public-dataset-for-baseline-detection
Repo
Framework

Robust learning with implicit residual networks


Title	Robust learning with implicit residual networks
Authors	Viktor Reshniak, Clayton Webster
Abstract	In this effort, we propose a new deep architecture utilizing residual blocks inspired by implicit discretization schemes. As opposed to the standard feed-forward networks, the outputs of the proposed implicit residual blocks are defined as the fixed points of the appropriately chosen nonlinear transformations. We show that this choice leads to the improved stability of both forward and backward propagations, has a favorable impact on the generalization power and allows to control the robustness of the network with only a few hyperparameters. In addition, the proposed reformulation of ResNet does not introduce new parameters and can potentially lead to a reduction in the number of required layers due to improved forward stability. Finally, we derive the memory-efficient training algorithm, propose a stochastic regularization technique and provide numerical results in support of our findings.
Tasks
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10479v2
PDF	https://arxiv.org/pdf/1905.10479v2.pdf
PWC	https://paperswithcode.com/paper/robust-learning-with-implicit-residual
Repo
Framework

Motion Equivariant Networks for Event Cameras with the Temporal Normalization Transform


Title	Motion Equivariant Networks for Event Cameras with the Temporal Normalization Transform
Authors	Alex Zihao Zhu, Ziyun Wang, Kostas Daniilidis
Abstract	In this work, we propose a novel transformation for events from an event camera that is equivariant to optical flow under convolutions in the 3-D spatiotemporal domain. Events are generated by changes in the image, which are typically due to motion, either of the camera or the scene. As a result, different motions result in a different set of events. For learning based tasks based on a static scene such as classification which directly use the events, we must either rely on the learning method to learn the underlying object distinct from the motion, or to memorize all possible motions for each object with extensive data augmentation. Instead, we propose a novel transformation of the input event data which normalizes the $x$ and $y$ positions by the timestamp of each event. We show that this transformation generates a representation of the events that is equivariant to this motion when the optical flow is constant, allowing a deep neural network to learn the classification task without the need for expensive data augmentation. We test our method on the event based N-MNIST dataset, as well as a novel dataset N-MOVING-MNIST, with significantly more variety in motion compared to the standard N-MNIST dataset. In all sequences, we demonstrate that our transformed network is able to achieve similar or better performance compared to a network with a standard volumetric event input, and performs significantly better when the test set has a larger set of motions than seen at training.
Tasks	Data Augmentation, Optical Flow Estimation
Published	2019-02-18
URL	http://arxiv.org/abs/1902.06820v1
PDF	http://arxiv.org/pdf/1902.06820v1.pdf
PWC	https://paperswithcode.com/paper/motion-equivariant-networks-for-event-cameras
Repo
Framework

Robust Structured Group Local Sparse Tracker Using Deep Features


Title	Robust Structured Group Local Sparse Tracker Using Deep Features
Authors	Mohammadreza Javanmardi, Amir Hossein Farzaneh, Xiaojun Qi
Abstract	Sparse representation has recently been successfully applied in visual tracking. It utilizes a set of templates to represent target candidates and find the best one with the minimum reconstruction error as the tracking result. In this paper, we propose a robust deep features-based structured group local sparse tracker (DF-SGLST), which exploits the deep features of local patches inside target candidates and represents them by a set of templates in the particle filter framework. Unlike the conventional local sparse trackers, the proposed optimization model in DF-SGLST employs a group-sparsity regularization term to seamlessly adopt local and spatial information of the target candidates and attain the spatial layout structure among them. To solve the optimization model, we propose an efficient and fast numerical algorithm that consists of two subproblems with the closed-form solutions. Different evaluations in terms of success and precision on the benchmarks of challenging image sequences (e.g., OTB50 and OTB100) demonstrate the superior performance of the proposed tracker against several state-of-the-art trackers.
Tasks	Visual Tracking
Published	2019-02-18
URL	https://arxiv.org/abs/1902.07668v2
PDF	https://arxiv.org/pdf/1902.07668v2.pdf
PWC	https://paperswithcode.com/paper/robust-structured-group-local-sparse-tracker
Repo
Framework

Inertial Block Mirror Descent Method for Non-Convex Non-Smooth Optimization


Title	Inertial Block Mirror Descent Method for Non-Convex Non-Smooth Optimization
Authors	Le Thi Khanh Hien, Nicolas Gillis, Panagiotis Patrinos
Abstract	In this paper, we propose inertial versions of block coordinate descent methods for solving non-convex non-smooth composite optimization problems. We use the general framework of Bregman distance functions to compute the proximal maps. Our methods not only allow using two different extrapolation points to evaluate gradients and adding the inertial force, but also take advantage of randomly picking the block of variables to update. Moreover, our methods do not require a restarting step, and as such, it is not a monotonically decreasing method. To prove the convergence of the whole generated sequence to a critical point, we modify the convergence proof recipe of Bolte, Sabach and Teboulle (Proximal alternating linearized minimization for non-convex and non-smooth problems, Math.@ Prog. 146(1):459–494, 2014), and combine it with auxiliary functions. We deploy the proposed methods to solve non-negative matrix factorization (NMF) and show that they compete favourably with the state-of-the-art NMF algorithms.
Tasks
Published	2019-03-05
URL	https://arxiv.org/abs/1903.01818v2
PDF	https://arxiv.org/pdf/1903.01818v2.pdf
PWC	https://paperswithcode.com/paper/inertial-block-mirror-descent-method-for-non
Repo
Framework

Deep Reasoning Networks: Thinking Fast and Slow


Title	Deep Reasoning Networks: Thinking Fast and Slow
Authors	Di Chen, Yiwei Bai, Wenting Zhao, Sebastian Ament, John M. Gregoire, Carla P. Gomes
Abstract	We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving complex tasks, typically in an unsupervised or weakly-supervised setting. DRNets exploit problem structure and prior knowledge by tightly combining logic and constraint reasoning with stochastic-gradient-based neural network optimization. We illustrate the power of DRNets on de-mixing overlapping hand-written Sudokus (Multi-MNIST-Sudoku) and on a substantially more complex task in scientific discovery that concerns inferring crystal structures of materials from X-ray diffraction data under thermodynamic rules (Crystal-Structure-Phase-Mapping). At a high level, DRNets encode a structured latent space of the input data, which is constrained to adhere to prior knowledge by a reasoning module. The structured latent encoding is used by a generative decoder to generate the targeted output. Finally, an overall objective combines responses from the generative decoder (thinking fast) and the reasoning module (thinking slow), which is optimized using constraint-aware stochastic gradient descent. We show how to encode different tasks as DRNets and demonstrate DRNets’ effectiveness with detailed experiments: DRNets significantly outperform the state of the art and experts’ capabilities on Crystal-Structure-Phase-Mapping, recovering more precise and physically meaningful crystal structures. On Multi-MNIST-Sudoku, DRNets perfectly recovered the mixed Sudokus’ digits, with 100% digit accuracy, outperforming the supervised state-of-the-art MNIST de-mixing models. Finally, as a proof of concept, we also show how DRNets can solve standard combinatorial problems – 9-by-9 Sudoku puzzles and Boolean satisfiability problems (SAT), outperforming other specialized deep learning models. DRNets are general and can be adapted and expanded to tackle other tasks.
Tasks
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00855v2
PDF	https://arxiv.org/pdf/1906.00855v2.pdf
PWC	https://paperswithcode.com/paper/190600855
Repo
Framework

Passing Tests without Memorizing: Two Models for Fooling Discriminators


Title	Passing Tests without Memorizing: Two Models for Fooling Discriminators
Authors	Olivier Bousquet, Roi Livni, Shay Moran
Abstract	We introduce two mathematical frameworks for foolability in the context of generative distribution learning. In a nuthsell, fooling is an algorithmic task in which the input sample is drawn from some target distribution and the goal is to output a synthetic distribution that is indistinguishable from the target w.r.t to some fixed class of tests. This framework received considerable attention in the context of Generative Adversarial Networks (GANs), a recently proposed approach which achieves impressive empirical results. From a theoretical viewpoint this problem seems difficult to model. This is due to the fact that in its basic form, the notion of foolability is susceptible to a type of overfitting called memorizing. This raises a challenge of devising notions and definitions that separate between fooling algorithms that generate new synthetic data vs. algorithms that merely memorize or copy the training set. The first model we consider is called GAM–Foolability and is inspired by GANs. Here the learner has only an indirect access to the target distribution via a discriminator. The second model, called DP–Foolability, exploits the notion of differential privacy as a candidate criterion for non-memorization. We proceed to characterize foolability within these two models and study their interrelations. We show that DP–Foolability implies GAM–Foolability and prove partial results with respect to the converse. It remains, though, an open question whether GAM–Foolability implies DP–Foolability. We also present an application in the context of differentially private PAC learning. We show that from a statistical perspective, for any class H, learnability by a private proper learner is equivalent to the existence of a private sanitizer for H. This can be seen as an analogue of the equivalence between uniform convergence and learnability in classical PAC learning.
Tasks
Published	2019-02-09
URL	http://arxiv.org/abs/1902.03468v1
PDF	http://arxiv.org/pdf/1902.03468v1.pdf
PWC	https://paperswithcode.com/paper/passing-tests-without-memorizing-two-models
Repo
Framework

A Simple Haploid-Diploid Evolutionary Algorithm


Title	A Simple Haploid-Diploid Evolutionary Algorithm
Authors	Larry Bull
Abstract	It has recently been suggested that evolution exploits a form of fitness landscape smoothing within eukaryotic sex due to the haploid-diploid cycle. This short paper presents a simple modification to the standard evolutionary computing algorithm to similarly benefit from the process. Using the well-known NK model of fitness landscapes it is shown that the benefit emerges as ruggedness is increased.
Tasks
Published	2019-03-27
URL	http://arxiv.org/abs/1903.11598v1
PDF	http://arxiv.org/pdf/1903.11598v1.pdf
PWC	https://paperswithcode.com/paper/a-simple-haploid-diploid-evolutionary
Repo
Framework

Learning Taxonomies of Concepts and not Words using Contextualized Word Representations: A Position Paper


Title	Learning Taxonomies of Concepts and not Words using Contextualized Word Representations: A Position Paper
Authors	Lukas Schmelzeisen, Steffen Staab
Abstract	Taxonomies are semantic hierarchies of concepts. One limitation of current taxonomy learning systems is that they define concepts as single words. This position paper argues that contextualized word representations, which recently achieved state-of-the-art results on many competitive NLP tasks, are a promising method to address this limitation. We outline a novel approach for taxonomy learning that (1) defines concepts as synsets, (2) learns density-based approximations of contextualized word representations, and (3) can measure similarity and hypernymy among them.
Tasks
Published	2019-01-31
URL	http://arxiv.org/abs/1902.02169v1
PDF	http://arxiv.org/pdf/1902.02169v1.pdf
PWC	https://paperswithcode.com/paper/learning-taxonomies-of-concepts-and-not-words
Repo
Framework

An approach to Decision Making based on Dynamic Argumentation Systems


Title	An approach to Decision Making based on Dynamic Argumentation Systems
Authors	Edgardo Ferretti, Luciano H. Tamargo, Alejandro J. Garcia, Marcelo L. Errecalde, Guillermo R. Simari
Abstract	In this paper, we introduce a formalism for single-agent decision making that is based on Dynamic Argumentation Frameworks. The formalism can be used to justify a choice, which is based on the current situation the agent is involved. Taking advantage of the inference mechanism of the argumentation formalism, it is possible to consider preference relations and conflicts among the available alternatives for that reasoning. With this formalization, given a particular set of evidence, the justified conclusions supported by warranted arguments will be used by the agent’s decision rules to determine which alternatives will be selected. We also present an algorithm that implements a choice function based on our formalization. Finally, we complete our presentation by introducing formal results that relate the proposed framework with approaches of classical decision theory.
Tasks	Decision Making
Published	2019-03-05
URL	http://arxiv.org/abs/1903.01920v1
PDF	http://arxiv.org/pdf/1903.01920v1.pdf
PWC	https://paperswithcode.com/paper/an-approach-to-decision-making-based-on
Repo
Framework

Compositional Network Embedding


Title	Compositional Network Embedding
Authors	Tianshu Lyu, Fei Sun, Peng Jiang, Wenwu Ou, Yan Zhang
Abstract	Network embedding has proved extremely useful in a variety of network analysis tasks such as node classification, link prediction, and network visualization. Almost all the existing network embedding methods learn to map the node IDs to their corresponding node embeddings. This design principle, however, hinders the existing methods from being applied in real cases. Node ID is not generalizable and, thus, the existing methods have to pay great effort in cold-start problem. The heterogeneous network usually requires extra work to encode node types, as node type is not able to be identified by node ID. Node ID carries rare information, resulting in the criticism that the existing methods are not robust to noise. To address this issue, we introduce Compositional Network Embedding, a general inductive network representation learning framework that generates node embeddings by combining node features based on the principle of compositionally. Instead of directly optimizing an embedding lookup based on arbitrary node IDs, we learn a composition function that infers node embeddings by combining the corresponding node attribute embeddings through a graph-based loss. For evaluation, we conduct the experiments on link prediction under four different settings. The results verified the effectiveness and generalization ability of compositional network embeddings, especially on unseen nodes.
Tasks	Link Prediction, Network Embedding, Node Classification, Representation Learning
Published	2019-04-17
URL	https://arxiv.org/abs/1904.08157v3
PDF	https://arxiv.org/pdf/1904.08157v3.pdf
PWC	https://paperswithcode.com/paper/compositional-network-embedding
Repo
Framework

Ontology alignment: A Content-Based Bayesian Approach


Title	Ontology alignment: A Content-Based Bayesian Approach
Authors	Vladimir Menkov, Paul Kantor
Abstract	There are many legacy databases, and related stores of information that are maintained by distinct organizations, and there are other organizations that would like to be able to access and use those disparate sources. Among the examples of current interest are such things as emergency room records, of interest in tracking and interdicting illicit drugs, or social media public posts that indicate preparation and intention for a mass shooting incident. In most cases, this information is discovered too late to be useful. While agencies responsible for coordination are aware of the potential value of contemporaneous access to new data, the costs of establishing a connection are prohibitive. The problem grown even worse with the proliferation of hash-tagging,'' which permits new labels and ontological relations to spring up overnight. While research interest has waned, the need for powerful and inexpensive tools enabling prompt access to multiple sources has grown ever more pressing. This paper describes techniques for computing alignment matrix coefficients, which relate the fields or content of one database to those of another, using the Bayesian Ontology Alignment tool (BOA). Particular attention is given to formulas that have an easy-to-understand meaning when all cells of the data sources containing values from some small set. These formulas can be expressed in terms of probability estimates. The estimates themselves are given by a black box’’ polytomous logistic regression model (PLRM), and thus can be easily generalized to the case of any arbitrary probability-generating model. The specific PLRM model used in this example is the BOXER Bayesian Extensible Online Regression model.
Tasks
Published	2019-08-24
URL	https://arxiv.org/abs/1908.09205v1
PDF	https://arxiv.org/pdf/1908.09205v1.pdf
PWC	https://paperswithcode.com/paper/ontology-alignment-a-content-based-bayesian
Repo
Framework