October 16, 2019

2888 words 14 mins read

Paper Group ANR 1122

Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference. Spectral feature scaling method for supervised dimensionality reduction. Log-Scale Shrinkage Priors and Adaptive Bayesian Global-Local Shrinkage Estimation. Multi-range Reasoning for Machine Comprehension. Sparse 3D Point-cloud Map Upsampling and Noise R …

Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference


Title	Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference
Authors	Ruying Bao, Sihang Liang, Qingcan Wang
Abstract	Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations intentionally added to the original inputs can fool the classifier. In this paper, we propose a defense method, Featurized Bidirectional Generative Adversarial Networks (FBGAN), to extract the semantic features of the input and filter the non-semantic perturbation. FBGAN is pre-trained on the clean dataset in an unsupervised manner, adversarially learning a bidirectional mapping between the high-dimensional data space and the low-dimensional semantic space; also mutual information is applied to disentangle the semantically meaningful features. After the bidirectional mapping, the adversarial data can be reconstructed to denoised data, which could be fed into any pre-trained classifier. We empirically show the quality of reconstruction images and the effectiveness of defense.
Tasks	Adversarial Defense
Published	2018-05-21
URL	http://arxiv.org/abs/1805.07862v2
PDF	http://arxiv.org/pdf/1805.07862v2.pdf
PWC	https://paperswithcode.com/paper/featurized-bidirectional-gan-adversarial
Repo
Framework

Spectral feature scaling method for supervised dimensionality reduction


Title	Spectral feature scaling method for supervised dimensionality reduction
Authors	Momo Matsuda, Keiichi Morikuni, Tetsuya Sakurai
Abstract	Spectral dimensionality reduction methods enable linear separations of complex data with high-dimensional features in a reduced space. However, these methods do not always give the desired results due to irregularities or uncertainties of the data. Thus, we consider aggressively modifying the scales of the features to obtain the desired classification. Using prior knowledge on the labels of partial samples to specify the Fiedler vector, we formulate an eigenvalue problem of a linear matrix pencil whose eigenvector has the feature scaling factors. The resulting factors can modify the features of entire samples to form clusters in the reduced space, according to the known labels. In this study, we propose new dimensionality reduction methods supervised using the feature scaling associated with the spectral clustering. Numerical experiments show that the proposed methods outperform well-established supervised methods for toy problems with more samples than features, and are more robust regarding clustering than existing methods. Also, the proposed methods outperform existing methods regarding classification for real-world problems with more features than samples of gene expression profiles of cancer diseases. Furthermore, the feature scaling tends to improve the clustering and classification accuracies of existing unsupervised methods, as the proportion of training data increases.
Tasks	Dimensionality Reduction
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07006v1
PDF	http://arxiv.org/pdf/1805.07006v1.pdf
PWC	https://paperswithcode.com/paper/spectral-feature-scaling-method-for
Repo
Framework

Log-Scale Shrinkage Priors and Adaptive Bayesian Global-Local Shrinkage Estimation


Title	Log-Scale Shrinkage Priors and Adaptive Bayesian Global-Local Shrinkage Estimation
Authors	Daniel F. Schmidt, Enes Makalic
Abstract	Global-local shrinkage hierarchies are an important innovation in Bayesian estimation. We propose the use of log-scale distributions as a novel basis for generating familes of prior distributions for local shrinkage hyperparameters. By varying the scale parameter one may vary the degree to which the prior distribution promotes sparsity in the coefficient estimates. By examining the class of distributions over the logarithm of the local shrinkage parameter that have log-linear, or sub-log-linear tails, we show that many standard prior distributions for local shrinkage parameters can be unified in terms of the tail behaviour and concentration properties of their corresponding marginal distributions over the coefficients $\beta_j$. We derive upper bounds on the rate of concentration around $\beta_j=0$, and the tail decay as $\beta_j \to \infty$, achievable by this wide class of prior distributions. We then propose a new type of ultra-heavy tailed prior, called the log-$t$ prior with the property that, irrespective of the choice of associated scale parameter, the marginal distribution always diverges at $\beta_j = 0$, and always possesses super-Cauchy tails. We develop results demonstrating when prior distributions with (sub)-log-linear tails attain Kullback–Leibler super-efficiency and prove that the log-$t$ prior distribution is always super-efficient. We show that the log-$t$ prior is less sensitive to misspecification of the global shrinkage parameter than the horseshoe or lasso priors. By incorporating the scale parameter of the log-scale prior distributions into the Bayesian hierarchy we derive novel adaptive shrinkage procedures. Simulations show that the adaptive log-$t$ procedure appears to always perform well, irrespective of the level of sparsity or signal-to-noise ratio of the underlying model.
Tasks
Published	2018-01-08
URL	https://arxiv.org/abs/1801.02321v2
PDF	https://arxiv.org/pdf/1801.02321v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-bayesian-shrinkage-estimation-using
Repo
Framework

Multi-range Reasoning for Machine Comprehension


Title	Multi-range Reasoning for Machine Comprehension
Authors	Yi Tay, Luu Anh Tuan, Siu Cheung Hui
Abstract	We propose MRU (Multi-Range Reasoning Units), a new fast compositional encoder for machine comprehension (MC). Our proposed MRU encoders are characterized by multi-ranged gating, executing a series of parameterized contract-and-expand layers for learning gating vectors that benefit from long and short-term dependencies. The aims of our approach are as follows: (1) learning representations that are concurrently aware of long and short-term context, (2) modeling relationships between intra-document blocks and (3) fast and efficient sequence encoding. We show that our proposed encoder demonstrates promising results both as a standalone encoder and as well as a complementary building block. We conduct extensive experiments on three challenging MC datasets, namely RACE, SearchQA and NarrativeQA, achieving highly competitive performance on all. On the RACE benchmark, our model outperforms DFN (Dynamic Fusion Networks) by 1.5%-6% without using any recurrent or convolution layers. Similarly, we achieve competitive performance relative to AMANDA on the SearchQA benchmark and BiDAF on the NarrativeQA benchmark without using any LSTM/GRU layers. Finally, incorporating MRU encoders with standard BiLSTM architectures further improves performance, achieving state-of-the-art results.
Tasks	Reading Comprehension
Published	2018-03-24
URL	http://arxiv.org/abs/1803.09074v1
PDF	http://arxiv.org/pdf/1803.09074v1.pdf
PWC	https://paperswithcode.com/paper/multi-range-reasoning-for-machine
Repo
Framework

Sparse 3D Point-cloud Map Upsampling and Noise Removal as a vSLAM Post-processing Step: Experimental Evaluation


Title	Sparse 3D Point-cloud Map Upsampling and Noise Removal as a vSLAM Post-processing Step: Experimental Evaluation
Authors	Andrey Bokovoy, Konstantin Yakovlev
Abstract	The monocular vision-based simultaneous localization and mapping (vSLAM) is one of the most challenging problem in mobile robotics and computer vision. In this work we study the post-processing techniques applied to sparse 3D point-cloud maps, obtained by feature-based vSLAM algorithms. Map post-processing is split into 2 major steps: 1) noise and outlier removal and 2) upsampling. We evaluate different combinations of known algorithms for outlier removing and upsampling on datasets of real indoor and outdoor environments and identify the most promising combination. We further use it to convert a point-cloud map, obtained by the real UAV performing indoor flight to 3D voxel grid (octo-map) potentially suitable for path planning.
Tasks	Simultaneous Localization and Mapping
Published	2018-06-25
URL	http://arxiv.org/abs/1806.09346v1
PDF	http://arxiv.org/pdf/1806.09346v1.pdf
PWC	https://paperswithcode.com/paper/sparse-3d-point-cloud-map-upsampling-and
Repo
Framework

Recent Research Advances on Interactive Machine Learning


Title	Recent Research Advances on Interactive Machine Learning
Authors	Liu Jiang, Shixia Liu, Changjian Chen
Abstract	Interactive Machine Learning (IML) is an iterative learning process that tightly couples a human with a machine learner, which is widely used by researchers and practitioners to effectively solve a wide variety of real-world application problems. Although recent years have witnessed the proliferation of IML in the field of visual analytics, most recent surveys either focus on a specific area of IML or aim to summarize a visualization field that is too generic for IML. In this paper, we systematically review the recent literature on IML and classify them into a task-oriented taxonomy built by us. We conclude the survey with a discussion of open challenges and research opportunities that we believe are inspiring for future work in IML.
Tasks
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04548v1
PDF	http://arxiv.org/pdf/1811.04548v1.pdf
PWC	https://paperswithcode.com/paper/recent-research-advances-on-interactive
Repo
Framework

The EuroCity Persons Dataset: A Novel Benchmark for Object Detection


Title	The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
Authors	Markus Braun, Sebastian Krebs, Fabian Flohr, Dariu M. Gavrila
Abstract	Big data has had a great share in the success of deep learning in computer vision. Recent works suggest that there is significant further potential to increase object detection performance by utilizing even bigger datasets. In this paper, we introduce the EuroCity Persons dataset, which provides a large number of highly diverse, accurate and detailed annotations of pedestrians, cyclists and other riders in urban traffic scenes. The images for this dataset were collected on-board a moving vehicle in 31 cities of 12 European countries. With over 238200 person instances manually labeled in over 47300 images, EuroCity Persons is nearly one order of magnitude larger than person datasets used previously for benchmarking. The dataset furthermore contains a large number of person orientation annotations (over 211200). We optimize four state-of-the-art deep learning approaches (Faster R-CNN, R-FCN, SSD and YOLOv3) to serve as baselines for the new object detection benchmark. In experiments with previous datasets we analyze the generalization capabilities of these detectors when trained with the new dataset. We furthermore study the effect of the training set size, the dataset diversity (day- vs. night-time, geographical region), the dataset detail (i.e. availability of object orientation information) and the annotation quality on the detector performance. Finally, we analyze error sources and discuss the road ahead.
Tasks	Object Detection
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07193v2
PDF	http://arxiv.org/pdf/1805.07193v2.pdf
PWC	https://paperswithcode.com/paper/the-eurocity-persons-dataset-a-novel
Repo
Framework

Adversarial Defense based on Structure-to-Signal Autoencoders


Title	Adversarial Defense based on Structure-to-Signal Autoencoders
Authors	Joachim Folz, Sebastian Palacio, Joern Hees, Damian Borth, Andreas Dengel
Abstract	Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerous misclassifications. We propose a novel way to interpret adversarial perturbations in terms of the effective input signal that classifiers actually use. Based on this, we apply specially trained autoencoders, referred to as S2SNets, as defense mechanism. They follow a two-stage training scheme: first unsupervised, followed by a fine-tuning of the decoder, using gradients from an existing classifier. S2SNets induce a shift in the distribution of gradients propagated through them, stripping them from class-dependent signal. We analyze their robustness against several white-box and gray-box scenarios on the large ImageNet dataset. Our approach reaches comparable resilience in white-box attack scenarios as other state-of-the-art defenses in gray-box scenarios. We further analyze the relationships of AlexNet, VGG 16, ResNet 50 and Inception v3 in adversarial space, and found that VGG 16 is the easiest to fool, while perturbations from ResNet 50 are the most transferable.
Tasks	Adversarial Attack, Adversarial Defense
Published	2018-03-21
URL	http://arxiv.org/abs/1803.07994v1
PDF	http://arxiv.org/pdf/1803.07994v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-defense-based-on-structure-to
Repo
Framework

Building Ethics into Artificial Intelligence


Title	Building Ethics into Artificial Intelligence
Authors	Han Yu, Zhiqi Shen, Chunyan Miao, Cyril Leung, Victor R. Lesser, Qiang Yang
Abstract	As artificial intelligence (AI) systems become increasingly ubiquitous, the topic of AI governance for ethical decision-making by AI has captured public imagination. Within the AI research community, this topic remains less familiar to many researchers. In this paper, we complement existing surveys, which largely focused on the psychological, social and legal discussions of the topic, with an analysis of recent advances in technical solutions for AI governance. By reviewing publications in leading AI conferences including AAAI, AAMAS, ECAI and IJCAI, we propose a taxonomy which divides the field into four areas: 1) exploring ethical dilemmas; 2) individual ethical decision frameworks; 3) collective ethical decision frameworks; and 4) ethics in human-AI interactions. We highlight the intuitions and key techniques used in each approach, and discuss promising future research directions towards successful integration of ethical AI systems into human societies.
Tasks	Decision Making
Published	2018-12-07
URL	http://arxiv.org/abs/1812.02953v1
PDF	http://arxiv.org/pdf/1812.02953v1.pdf
PWC	https://paperswithcode.com/paper/building-ethics-into-artificial-intelligence
Repo
Framework

Bandit Learning with Positive Externalities


Title	Bandit Learning with Positive Externalities
Authors	Virag Shah, Jose Blanchet, Ramesh Johari
Abstract	In many platforms, user arrivals exhibit a self-reinforcing behavior: future user arrivals are likely to have preferences similar to users who were satisfied in the past. In other words, arrivals exhibit positive externalities. We study multiarmed bandit (MAB) problems with positive externalities. We show that the self-reinforcing preferences may lead standard benchmark algorithms such as UCB to exhibit linear regret. We develop a new algorithm, Balanced Exploration (BE), which explores arms carefully to avoid suboptimal convergence of arrivals before sufficient evidence is gathered. We also introduce an adaptive variant of BE which successively eliminates suboptimal arms. We analyze their asymptotic regret, and establish optimality by showing that no algorithm can perform better.
Tasks
Published	2018-02-15
URL	http://arxiv.org/abs/1802.05693v5
PDF	http://arxiv.org/pdf/1802.05693v5.pdf
PWC	https://paperswithcode.com/paper/bandit-learning-with-positive-externalities
Repo
Framework

Deep Reinforcement Learning: An Overview


Title	Deep Reinforcement Learning: An Overview
Authors	Seyed Sajad Mousavi, Michael Schukat, Enda Howley
Abstract	In recent years, a specific machine learning method called deep learning has gained huge attraction, as it has obtained astonishing results in broad applications such as pattern recognition, speech recognition, computer vision, and natural language processing. Recent research has also been shown that deep learning techniques can be combined with reinforcement learning methods to learn useful representations for the problems with high dimensional raw data input. This chapter reviews the recent advances in deep reinforcement learning with a focus on the most used deep architectures such as autoencoders, convolutional neural networks and recurrent neural networks which have successfully been come together with the reinforcement learning framework.
Tasks	Speech Recognition
Published	2018-06-23
URL	http://arxiv.org/abs/1806.08894v1
PDF	http://arxiv.org/pdf/1806.08894v1.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-an-overview-1
Repo
Framework

Multilingual Scene Character Recognition System using Sparse Auto-Encoder for Efficient Local Features Representation in Bag of Features


Title	Multilingual Scene Character Recognition System using Sparse Auto-Encoder for Efficient Local Features Representation in Bag of Features
Authors	Maroua Tounsi, Ikram Moalla, Frank Lebourgeois, Adel M. Alimi
Abstract	The recognition of texts existing in camera-captured images has become an important issue for a great deal of research during the past few decades. This give birth to Scene Character Recognition (SCR) which is an important step in scene text recognition pipeline. In this paper, we extended the Bag of Features (BoF)-based model using deep learning for representing features for accurate SCR of different languages. In the features coding step, a deep Sparse Auto-encoder (SAE)-based strategy was applied to enhance the representative and discriminative abilities of image features. This deep learning architecture provides more efficient features representation and therefore a better recognition accuracy. Our system was evaluated extensively on all the scene character datasets of five different languages. The experimental results proved the efficiency of our system for a multilingual SCR.
Tasks	Scene Text Recognition
Published	2018-06-11
URL	http://arxiv.org/abs/1806.07374v4
PDF	http://arxiv.org/pdf/1806.07374v4.pdf
PWC	https://paperswithcode.com/paper/multilingual-scene-character-recognition
Repo
Framework

Adaptive Co-weighting Deep Convolutional Features For Object Retrieval


Title	Adaptive Co-weighting Deep Convolutional Features For Object Retrieval
Authors	Jiaxing Wang, Jihua Zhu, Shanmin Pang, Zhongyu Li, Yaochen Li, Xueming Qian
Abstract	Aggregating deep convolutional features into a global image vector has attracted sustained attention in image retrieval. In this paper, we propose an efficient unsupervised aggregation method that uses an adaptive Gaussian filter and an elementvalue sensitive vector to co-weight deep features. Specifically, the Gaussian filter assigns large weights to features of region-of-interests (RoI) by adaptively determining the RoI’s center, while the element-value sensitive channel vector suppresses burstiness phenomenon by assigning small weights to feature maps with large sum values of all locations. Experimental results on benchmark datasets validate the proposed two weighting schemes both effectively improve the discrimination power of image vectors. Furthermore, with the same experimental setting, our method outperforms other very recent aggregation approaches by a considerable margin.
Tasks	Image Retrieval
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07360v1
PDF	http://arxiv.org/pdf/1803.07360v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-co-weighting-deep-convolutional
Repo
Framework

MeshAdv: Adversarial Meshes for Visual Recognition


Title	MeshAdv: Adversarial Meshes for Visual Recognition
Authors	Chaowei Xiao, Dawei Yang, Bo Li, Jia Deng, Mingyan Liu
Abstract	Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications. However, recent studies show that DNNs are vulnerable to adversarial examples, which are carefully crafted inputs aiming to mislead the predictions. Currently, the majority of these studies have focused on perturbation added to image pixels, while such manipulation is not physically realistic. Some works have tried to overcome this limitation by attaching printable 2D patches or painting patterns onto surfaces, but can be potentially defended because 3D shape features are intact. In this paper, we propose meshAdv to generate “adversarial 3D meshes” from objects that have rich shape features but minimal textural variation. To manipulate the shape or texture of the objects, we make use of a differentiable renderer to compute accurate shading on the shape and propagate the gradient. Extensive experiments show that the generated 3D meshes are effective in attacking both classifiers and object detectors. We evaluate the attack under different viewpoints. In addition, we design a pipeline to perform black-box attack on a photorealistic renderer with unknown rendering parameters.
Tasks
Published	2018-10-11
URL	https://arxiv.org/abs/1810.05206v2
PDF	https://arxiv.org/pdf/1810.05206v2.pdf
PWC	https://paperswithcode.com/paper/realistic-adversarial-examples-in-3d-meshes
Repo
Framework

A Very Brief and Critical Discussion on AutoML


Title	A Very Brief and Critical Discussion on AutoML
Authors	Bin Liu
Abstract	This contribution presents a very brief and critical discussion on automated machine learning (AutoML), which is categorized here into two classes, referred to as narrow AutoML and generalized AutoML, respectively. The conclusions yielded from this discussion can be summarized as follows: (1) most existent research on AutoML belongs to the class of narrow AutoML; (2) advances in narrow AutoML are mainly motivated by commercial needs, while any possible benefit obtained is definitely at a cost of increase in computing burdens; (3)the concept of generalized AutoML has a strong tie in spirit with artificial general intelligence (AGI), also called “strong AI”, for which obstacles abound for obtaining pivotal progresses.
Tasks	AutoML
Published	2018-11-09
URL	http://arxiv.org/abs/1811.03822v1
PDF	http://arxiv.org/pdf/1811.03822v1.pdf
PWC	https://paperswithcode.com/paper/a-very-brief-and-critical-discussion-on
Repo
Framework