January 31, 2020

3266 words 16 mins read

Paper Group ANR 165

Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation. Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning. NLP Driven Ensemble Based Automatic Subtitle Generation and Semantic Video Summarization Technique. Simple iterative method for generating targeted universal advers …

Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation


Title	Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation
Authors	Yuh-Shyang Wang, Tsui-Wei Weng, Luca Daniel
Abstract	Deep neural networks are known to be fragile to small adversarial perturbations. This issue becomes more critical when a neural network is interconnected with a physical system in a closed loop. In this paper, we show how to combine recent works on neural network certification tools (which are mainly used in static settings such as image classification) with robust control theory to certify a neural network policy in a control loop. Specifically, we give a sufficient condition and an algorithm to ensure that the closed loop state and control constraints are satisfied when the persistent adversarial perturbation is l-infinity norm bounded. Our method is based on finding a positively invariant set of the closed loop dynamical system, and thus we do not require the differentiability or the continuity of the neural network policy. Along with the verification result, we also develop an effective attack strategy for neural network control systems that outperforms exhaustive Monte-Carlo search significantly. We show that our certification algorithm works well on learned models and achieves 5 times better result than the traditional Lipschitz-based method to certify the robustness of a neural network policy on a cart pole control problem.
Tasks	Image Classification
Published	2019-08-18
URL	https://arxiv.org/abs/1908.06353v1
PDF	https://arxiv.org/pdf/1908.06353v1.pdf
PWC	https://paperswithcode.com/paper/verification-of-neural-network-control-policy
Repo
Framework

Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning


Title	Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning
Authors	Julien Roy, Paul Barde, Félix G. Harvey, Derek Nowrouzezahrai, Christopher Pal
Abstract	In multi-agent reinforcement learning, discovering successful collective behaviors is challenging as it requires exploring a joint action space that grows exponentially with the number of agents. While the tractability of independent agent-wise exploration is appealing, this approach fails on tasks that require elaborate group strategies. We argue that coordinating the agents’ policies can guide their exploration and we investigate techniques to promote such an inductive bias. We propose two policy regularization methods: TeamReg, which is based on inter-agent action predictability and CoachReg that relies on synchronized behavior selection. We evaluate each approach on four challenging continuous control tasks with sparse rewards that require varying levels of coordination. Our methodology allocates the same hyper-parameter search budget across our algorithms and baselines and we find that our approaches are more robust to hyper-parameter variations. Our experiments show that our methods significantly improve performance on cooperative multi-agent problems and scale well when the number of agents is increased. Finally, we quantitatively analyze the effects of our proposed methods on the policies that our agents learn and we show that our methods successfully enforce the qualities that we propose as proxies for coordinated behaviors.
Tasks	Continuous Control, Multi-agent Reinforcement Learning
Published	2019-08-06
URL	https://arxiv.org/abs/1908.02269v3
PDF	https://arxiv.org/pdf/1908.02269v3.pdf
PWC	https://paperswithcode.com/paper/promoting-coordination-through-policy
Repo
Framework

NLP Driven Ensemble Based Automatic Subtitle Generation and Semantic Video Summarization Technique


Title	NLP Driven Ensemble Based Automatic Subtitle Generation and Semantic Video Summarization Technique
Authors	VB Aswin, Mohammed Javed, Parag Parihar, K Aswanth, CR Druval, Anpam Dagar, CV Aravinda
Abstract	This paper proposes an automatic subtitle generation and semantic video summarization technique. The importance of automatic video summarization is vast in the present era of big data. Video summarization helps in efficient storage and also quick surfing of large collection of videos without losing the important ones. The summarization of the videos is done with the help of subtitles which is obtained using several text summarization algorithms. The proposed technique generates the subtitle for videos with/without subtitles using speech recognition and then applies NLP based Text summarization algorithms on the subtitles. The performance of subtitle generation and video summarization is boosted through Ensemble method with two approaches such as Intersection method and Weight based learning method Experimental results reported show the satisfactory performance of the proposed method
Tasks	Speech Recognition, Text Summarization, Video Summarization
Published	2019-04-22
URL	http://arxiv.org/abs/1904.09740v1
PDF	http://arxiv.org/pdf/1904.09740v1.pdf
PWC	https://paperswithcode.com/paper/nlp-driven-ensemble-based-automatic-subtitle
Repo
Framework

Simple iterative method for generating targeted universal adversarial perturbations


Title	Simple iterative method for generating targeted universal adversarial perturbations
Authors	Hokuto Hirano, Kazuhiro Takemoto
Abstract	Deep neural networks (DNNs) are vulnerable to adversarial attacks. In particular, a single perturbation known as the universal adversarial perturbation (UAP) can foil most classification tasks conducted by DNNs. Thus, different methods for generating UAPs are required to fully evaluate the vulnerability of DNNs. A realistic evaluation would be with cases that consider targeted attacks; wherein the generated UAP causes DNN to classify an input into a specific class. However, the development of UAPs for targeted attacks has largely fallen behind that of UAPs for non-targeted attacks. Therefore, we propose a simple iterative method to generate UAPs for targeted attacks. Our method combines the simple iterative method for generating non-targeted UAPs and the fast gradient sign method for generating a targeted adversarial perturbation for an input. We applied the proposed method to state-of-the-art DNN models for image classification and proved the existence of almost imperceptible UAPs for targeted attacks; further, we demonstrated that such UAPs are easily generatable.
Tasks	Image Classification
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06502v2
PDF	https://arxiv.org/pdf/1911.06502v2.pdf
PWC	https://paperswithcode.com/paper/simple-iterative-method-for-generating
Repo
Framework

Morphing and Sampling Network for Dense Point Cloud Completion


Title	Morphing and Sampling Network for Dense Point Cloud Completion
Authors	Minghua Liu, Lu Sheng, Sheng Yang, Jing Shao, Shi-Min Hu
Abstract	3D point cloud completion, the task of inferring the complete geometric shape from a partial point cloud, has been attracting attention in the community. For acquiring high-fidelity dense point clouds and avoiding uneven distribution, blurred details, or structural loss of existing methods’ results, we propose a novel approach to complete the partial point cloud in two stages. Specifically, in the first stage, the approach predicts a complete but coarse-grained point cloud with a collection of parametric surface elements. Then, in the second stage, it merges the coarse-grained prediction with the input point cloud by a novel sampling algorithm. Our method utilizes a joint loss function to guide the distribution of the points. Extensive experiments verify the effectiveness of our method and demonstrate that it outperforms the existing methods in both the Earth Mover’s Distance (EMD) and the Chamfer Distance (CD).
Tasks
Published	2019-11-30
URL	https://arxiv.org/abs/1912.00280v1
PDF	https://arxiv.org/pdf/1912.00280v1.pdf
PWC	https://paperswithcode.com/paper/morphing-and-sampling-network-for-dense-point
Repo
Framework

Deep Temporal Analysis for Non-Acted Body Affect Recognition


Title	Deep Temporal Analysis for Non-Acted Body Affect Recognition
Authors	Danilo Avola, Luigi Cinque, Alessio Fagioli, Gian Luca Foresti, Cristiano Massaroni
Abstract	Affective computing is a field of great interest in many computer vision applications, including video surveillance, behaviour analysis, and human-robot interaction. Most of the existing literature has addressed this field by analysing different sets of face features. However, in the last decade, several studies have shown how body movements can play a key role even in emotion recognition. The majority of these experiments on the body are performed by trained actors whose aim is to simulate emotional reactions. These unnatural expressions differ from the more challenging genuine emotions, thus invalidating the obtained results. In this paper, a solution for basic non-acted emotion recognition based on 3D skeleton and Deep Neural Networks (DNNs) is provided. The proposed work introduces three majors contributions. First, unlike the current state-of-the-art in non-acted body affect recognition, where only static or global body features are considered, in this work also temporal local movements performed by subjects in each frame are examined. Second, an original set of global and time-dependent features for body movement description is provided. Third, to the best of out knowledge, this is the first attempt to use deep learning methods for non-acted body affect recognition. Due to the novelty of the topic, only the UCLIC dataset is currently considered the benchmark for comparative tests. On the latter, the proposed method outperforms all the competitors.
Tasks	Emotion Recognition
Published	2019-07-23
URL	https://arxiv.org/abs/1907.09945v1
PDF	https://arxiv.org/pdf/1907.09945v1.pdf
PWC	https://paperswithcode.com/paper/deep-temporal-analysis-for-non-acted-body
Repo
Framework

Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets


Title	Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets
Authors	Naima Otberdout, Mohamed Daoudi, Anis Kacem, Lahoucine Ballihi, Stefano Berretti
Abstract	In this work, we propose a novel approach for generating videos of the six basic facial expressions given a neutral face image. We propose to exploit the face geometry by modeling the facial landmarks motion as curves encoded as points on a hypersphere. By proposing a conditional version of manifold-valued Wasserstein generative adversarial network (GAN) for motion generation on the hypersphere, we learn the distribution of facial expression dynamics of different classes, from which we synthesize new facial expression motions. The resulting motions can be transformed to sequences of landmarks and then to images sequences by editing the texture information using another conditional Generative Adversarial Network. To the best of our knowledge, this is the first work that explores manifold-valued representations with GAN to address the problem of dynamic facial expression generation. We evaluate our proposed approach both quantitatively and qualitatively on two public datasets; Oulu-CASIA and MUG Facial Expression. Our experimental results demonstrate the effectiveness of our approach in generating realistic videos with continuous motion, realistic appearance and identity preservation. We also show the efficiency of our framework for dynamic facial expressions generation, dynamic facial expression transfer and data augmentation for training improved emotion recognition models.
Tasks	Data Augmentation, Emotion Recognition
Published	2019-07-23
URL	https://arxiv.org/abs/1907.10087v1
PDF	https://arxiv.org/pdf/1907.10087v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-facial-expression-generation-on
Repo
Framework

Machine Learning for a Low-cost Air Pollution Network


Title	Machine Learning for a Low-cost Air Pollution Network
Authors	Michael T. Smith, Joel Ssematimba, Mauricio A. Alvarez, Engineer Bainomugisha
Abstract	Data collection in economically constrained countries often necessitates using approximate and biased measurements due to the low-cost of the sensors used. This leads to potentially invalid predictions and poor policies or decision making. This is especially an issue if methods from resource-rich regions are applied without handling these additional constraints. In this paper we show, through the use of an air pollution network example, how using probabilistic machine learning can mitigate some of the technical constraints. Specifically we experiment with modelling the calibration for individual sensors as either distributions or Gaussian processes over time, and discuss the wider issues around the decision process.
Tasks	Calibration, Decision Making, Gaussian Processes
Published	2019-11-28
URL	https://arxiv.org/abs/1911.12868v1
PDF	https://arxiv.org/pdf/1911.12868v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-a-low-cost-air-pollution
Repo
Framework

Machine Learning Automation Toolbox (MLaut)


Title	Machine Learning Automation Toolbox (MLaut)
Authors	Viktor Kazakov, Franz J. Király
Abstract	In this paper we present MLaut (Machine Learning AUtomation Toolbox) for the python data science ecosystem. MLaut automates large-scale evaluation and benchmarking of machine learning algorithms on a large number of datasets. MLaut provides a high-level workflow interface to machine algorithm algorithms, implements a local back-end to a database of dataset collections, trained algorithms, and experimental results, and provides easy-to-use interfaces to the scikit-learn and keras modelling libraries. Experiments are easy to set up with default settings in a few lines of code, while remaining fully customizable to the level of hyper-parameter tuning, pipeline composition, or deep learning architecture. As a principal test case for MLaut, we conducted a large-scale supervised classification study in order to benchmark the performance of a number of machine learning algorithms - to our knowledge also the first larger-scale study on standard supervised learning data sets to include deep learning algorithms. While corroborating a number of previous findings in literature, we found (within the limitations of our study) that deep neural networks do not perform well on basic supervised learning, i.e., outside the more specialized, image-, audio-, or text-based tasks.
Tasks
Published	2019-01-11
URL	http://arxiv.org/abs/1901.03678v1
PDF	http://arxiv.org/pdf/1901.03678v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-automation-toolbox-mlaut
Repo
Framework

Photorealistic Image Synthesis for Object Instance Detection


Title	Photorealistic Image Synthesis for Object Instance Detection
Authors	Tomas Hodan, Vibhav Vineet, Ran Gal, Emanuel Shalev, Jon Hanzelka, Treb Connell, Pedro Urbina, Sudipta N. Sinha, Brian Guenter
Abstract	We present an approach to synthesize highly photorealistic images of 3D object models, which we use to train a convolutional neural network for detecting the objects in real images. The proposed approach has three key ingredients: (1) 3D object models are rendered in 3D models of complete scenes with realistic materials and lighting, (2) plausible geometric configuration of objects and cameras in a scene is generated using physics simulations, and (3) high photorealism of the synthesized images achieved by physically based rendering. When trained on images synthesized by the proposed approach, the Faster R-CNN object detector achieves a 24% absolute improvement of mAP@.75IoU on Rutgers APC and 11% on LineMod-Occluded datasets, compared to a baseline where the training images are synthesized by rendering object models on top of random photographs. This work is a step towards being able to effectively train object detectors without capturing or annotating any real images. A dataset of 600K synthetic images with ground truth annotations for various computer vision tasks will be released on the project website: thodan.github.io/objectsynth.
Tasks	Image Generation
Published	2019-02-09
URL	http://arxiv.org/abs/1902.03334v1
PDF	http://arxiv.org/pdf/1902.03334v1.pdf
PWC	https://paperswithcode.com/paper/photorealistic-image-synthesis-for-object
Repo
Framework

AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds


Title	AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
Authors	Abdullah Hamdi, Sara Rojas, Ali Thabet, Bernard Ghanem
Abstract	Deep neural networks are vulnerable to adversarial attacks, in which imperceptible perturbations to their input lead to erroneous network predictions. This phenomenon has been extensively studied in the image domain, and only recently extended to 3D point clouds. In this work, we present novel data-driven adversarial attacks against 3D point cloud networks. We aim to address the following problems in current 3D point cloud adversarial attacks: they do not transfer well between different networks, and they are easy to defend against simple statistical methods. To this extent, we develop new point cloud attacks (we dub AdvPC) that exploit input data distributions. These attacks lead to perturbations that are resilient against current defenses while remaining highly transferable compared to state-of-the-art attacks. We test our attacks using four popular point cloud networks: PointNet, PointNet++ (MSG and SSG), and DGCNN. Our proposed attack enables an increase in the transferability of up to 20 points for some networks. It also increases the ability to break defenses of up to 23 points on ModelNet40 data.
Tasks
Published	2019-12-01
URL	https://arxiv.org/abs/1912.00461v1
PDF	https://arxiv.org/pdf/1912.00461v1.pdf
PWC	https://paperswithcode.com/paper/advpc-transferable-adversarial-perturbations
Repo
Framework

On the geometry of learning neural quantum states


Title	On the geometry of learning neural quantum states
Authors	Chae-Yeun Park, Michael J. Kastoryano
Abstract	Combining insights from machine learning and quantum Monte Carlo, the stochastic reconfiguration method with neural network Ansatz states is a promising new direction for high precision ground state estimation of quantum many body problems. At present, the method is heuristic, lacking a proper theoretical foundation. We initiate a thorough analysis of the learning landscape, and show that it reveals universal behavior reflecting a combination of the underlying physics and of the learning dynamics. In particular, the spectrum of the quantum Fisher matrix of complex restricted Boltzmann machine states can dramatically change across a phase transition. In contrast to the spectral properties of the quantum Fisher matrix, the actual weights of the network at convergence do not reveal much information about the system or the dynamics. Furthermore, we identify a new measure of correlation in the state by analyzing entanglement the eigenvectors. We show that, generically, the learning landscape modes with least entanglement have largest eigenvalue, suggesting that correlations are encoded in large flat valleys of the learning landscape, favoring stable representations of the ground state.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11163v1
PDF	https://arxiv.org/pdf/1910.11163v1.pdf
PWC	https://paperswithcode.com/paper/on-the-geometry-of-learning-neural-quantum
Repo
Framework

AOP: An Anti-overfitting Pretreatment for Practical Image-based Plant Diagnosis


Title	AOP: An Anti-overfitting Pretreatment for Practical Image-based Plant Diagnosis
Authors	Takumi Saikawa, Quan Huu Cap, Satoshi Kagiwada, Hiroyuki Uga, Hitoshi Iyatomi
Abstract	In image-based plant diagnosis, clues related to diagnosis are often unclear, and the other factors such as image backgrounds often have a significant impact on the final decision. As a result, overfitting due to latent similarities in the dataset often occurs, and the diagnostic performance on real unseen data (e,g. images from other farms) is usually dropped significantly. However, this problem has not been sufficiently explored, since many systems have shown excellent diagnostic performance due to the bias caused by the similarities in the dataset. In this study, we investigate this problem with experiments using more than 50,000 images of cucumber leaves, and propose an anti-overfitting pretreatment (AOP) for realizing practical image-based plant diagnosis systems. The AOP detects the area of interest (leaf, fruit etc.) and performs brightness calibration as a preprocessing step. The experimental results demonstrate that our AOP can improve the accuracy of diagnosis for unknown test images from different farms by 12.2% in a practical setting.
Tasks	Calibration
Published	2019-11-25
URL	https://arxiv.org/abs/1911.10727v1
PDF	https://arxiv.org/pdf/1911.10727v1.pdf
PWC	https://paperswithcode.com/paper/aop-an-anti-overfitting-pretreatment-for
Repo
Framework

Extending Relational Query Processing with ML Inference


Title	Extending Relational Query Processing with ML Inference
Authors	Konstantinos Karanasos, Matteo Interlandi, Doris Xin, Fotis Psallidas, Rathijit Sen, Kwanghyun Park, Ivan Popivanov, Supun Nakandal, Subru Krishnan, Markus Weimer, Yuan Yu, Raghu Ramakrishnan, Carlo Curino
Abstract	The broadening adoption of machine learning in the enterprise is increasing the pressure for strict governance and cost-effective performance, in particular for the common and consequential steps of model storage and inference. The RDBMS provides a natural starting point, given its mature infrastructure for fast data access and processing, along with support for enterprise features (e.g., encryption, auditing, high-availability). To take advantage of all of the above, we need to address a key concern: Can in-RDBMS scoring of ML models match (outperform?) the performance of dedicated frameworks? We answer the above positively by building Raven, a system that leverages native integration of ML runtimes (i.e., ONNX Runtime) deep within SQL Server, and a unified intermediate representation (IR) to enable advanced cross-optimizations between ML and DB operators. In this optimization space, we discover the most exciting research opportunities that combine DB/Compiler/ML thinking. Our initial evaluation on real data demonstrates performance gains of up to 5.5x from the native integration of ML in SQL Server, and up to 24x from cross-optimizations–we will demonstrate Raven live during the conference talk.
Tasks
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00231v1
PDF	https://arxiv.org/pdf/1911.00231v1.pdf
PWC	https://paperswithcode.com/paper/extending-relational-query-processing-with-ml
Repo
Framework

DuDoNet: Dual Domain Network for CT Metal Artifact Reduction


Title	DuDoNet: Dual Domain Network for CT Metal Artifact Reduction
Authors	Wei-An Lin, Haofu Liao, Cheng Peng, Xiaohang Sun, Jingdan Zhang, Jiebo Luo, Rama Chellappa, Shaohua Kevin Zhou
Abstract	Computed tomography (CT) is an imaging modality widely used for medical diagnosis and treatment. CT images are often corrupted by undesirable artifacts when metallic implants are carried by patients, which creates the problem of metal artifact reduction (MAR). Existing methods for reducing the artifacts due to metallic implants are inadequate for two main reasons. First, metal artifacts are structured and non-local so that simple image domain enhancement approaches would not suffice. Second, the MAR approaches which attempt to reduce metal artifacts in the X-ray projection (sinogram) domain inevitably lead to severe secondary artifact due to sinogram inconsistency. To overcome these difficulties, we propose an end-to-end trainable Dual Domain Network (DuDoNet) to simultaneously restore sinogram consistency and enhance CT images. The linkage between the sigogram and image domains is a novel Radon inversion layer that allows the gradients to back-propagate from the image domain to the sinogram domain during training. Extensive experiments show that our method achieves significant improvements over other single domain MAR approaches. To the best of our knowledge, it is the first end-to-end dual-domain network for MAR.
Tasks	Computed Tomography (CT), Medical Diagnosis, Metal Artifact Reduction
Published	2019-06-29
URL	https://arxiv.org/abs/1907.00273v1
PDF	https://arxiv.org/pdf/1907.00273v1.pdf
PWC	https://paperswithcode.com/paper/dudonet-dual-domain-network-for-ct-metal-1
Repo
Framework