January 30, 2020

3252 words 16 mins read

Paper Group ANR 316

Thwarting finite difference adversarial attacks with output randomization. Real-time Video Summarization on Commodity Hardware. Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation. An Abstraction Model for Semantic Segmentation Algorithms. PProCRC: Probabilistic Collaboration of Image Patches. Comp …

Thwarting finite difference adversarial attacks with output randomization


Title	Thwarting finite difference adversarial attacks with output randomization
Authors	Haidar Khan, Daniel Park, Azer Khan, Bülent Yener
Abstract	Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model and to the opposite “black box” setting. Black box attacks are particularly threatening as the adversary only needs access to the input and output of the model. Defending against black box adversarial example generation attacks is paramount as currently proposed defenses are not effective. Since these types of attacks rely on repeated queries to the model to estimate gradients over input dimensions, we investigate the use of randomization to thwart such adversaries from successfully creating adversarial examples. Randomization applied to the output of the deep neural network model has the potential to confuse potential attackers, however this introduces a tradeoff between accuracy and robustness. We show that for certain types of randomization, we can bound the probability of introducing errors by carefully setting distributional parameters. For the particular case of finite difference black box attacks, we quantify the error introduced by the defense in the finite difference estimate of the gradient. Lastly, we show empirically that the defense can thwart two adaptive black box adversarial attack algorithms.
Tasks	Adversarial Attack
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09871v1
PDF	https://arxiv.org/pdf/1905.09871v1.pdf
PWC	https://paperswithcode.com/paper/thwarting-finite-difference-adversarial
Repo
Framework

Real-time Video Summarization on Commodity Hardware


Title	Real-time Video Summarization on Commodity Hardware
Authors	Wesley Taylor, Faisal Z. Qureshi
Abstract	We present a method for creating video summaries in real-time on commodity hardware. Real-time here refers to the fact that the time required for video summarization is less than the duration of the input video. First, low-level features are use to discard undesirable frames. Next, video is divided into segments, and segment-level features are extracted for each segment. Tree-based models trained on widely available video summarization and computational aesthetics datasets are then used to rank individual segments, and top-ranked segments are selected to generate the final video summary. We evaluate the proposed method on SUMME dataset and show that our method is able to achieve summarization accuracy that is comparable to that of a current state-of-the-art deep learning method, while posting significantly faster run-times. Our method on average is able to generate a video summary in time that is shorter than the duration of the video.
Tasks	Video Summarization
Published	2019-01-26
URL	http://arxiv.org/abs/1901.09287v1
PDF	http://arxiv.org/pdf/1901.09287v1.pdf
PWC	https://paperswithcode.com/paper/real-time-video-summarization-on-commodity
Repo
Framework

Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation


Title	Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
Authors	Antreas Antoniou, Amos Storkey
Abstract	The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning setting, where no labels of any kind are required, has seen little investigation. We propose a method, named Assume, Augment and Learn or AAL, for generating few-shot tasks using unlabeled data. We randomly label a random subset of images from an unlabeled dataset to generate a support set. Then by applying data augmentation on the support set’s images, and reusing the support set’s labels, we obtain a target set. The resulting few-shot tasks can be used to train any standard meta-learning framework. Once trained, such a model, can be directly applied on small real-labeled datasets without any changes or fine-tuning required. In our experiments, the learned models achieve good generalization performance in a variety of established few-shot learning tasks on Omniglot and Mini-Imagenet.
Tasks	Data Augmentation, Few-Shot Learning, Meta-Learning, Omniglot
Published	2019-02-26
URL	http://arxiv.org/abs/1902.09884v3
PDF	http://arxiv.org/pdf/1902.09884v3.pdf
PWC	https://paperswithcode.com/paper/assume-augment-and-learn-unsupervised-few
Repo
Framework

An Abstraction Model for Semantic Segmentation Algorithms


Title	An Abstraction Model for Semantic Segmentation Algorithms
Authors	Reihaneh Teymoori, Zahra Nabizadeh, Nader Karimi, Shadrokh Samavi
Abstract	Semantic segmentation is a process of classifying each pixel in the image. Due to its advantages, sematic segmentation is used in many tasks such as cancer detection, robot-assisted surgery, satellite image analysis, self-driving car control, etc. In this process, accuracy and efficiency are the two crucial goals for this purpose, and there are several state of the art neural networks. In each method, by employing different techniques, new solutions have been presented for increasing efficiency, accuracy, and reducing the costs. The diversity of the implemented approaches for semantic segmentation makes it difficult for researches to achieve a comprehensive view of the field. To offer a comprehensive view, in this paper, an abstraction model for the task of semantic segmentation is offered. The proposed framework consists of four general blocks that cover the majority of majority of methods that have been proposed for semantic segmentation. We also compare different approaches and consider the importance of each part in the overall performance of a method.
Tasks	Semantic Segmentation
Published	2019-12-27
URL	https://arxiv.org/abs/1912.11995v1
PDF	https://arxiv.org/pdf/1912.11995v1.pdf
PWC	https://paperswithcode.com/paper/an-abstraction-model-for-semantic
Repo
Framework

PProCRC: Probabilistic Collaboration of Image Patches


Title	PProCRC: Probabilistic Collaboration of Image Patches
Authors	Tapabrata Chakraborti, Brendan McCane, Steven Mills, Umapada Pal
Abstract	We present a conditional probabilistic framework for collaborative representation of image patches. It in-corporates background compensation and outlier patch suppression into the main formulation itself, thus doingaway with the need for pre-processing steps to handle the same. A closed form non-iterative solution of the costfunction is derived. The proposed method (PProCRC) outperforms earlier related patch based (PCRC, GP-CRC)as well as the state-of-the-art probabilistic (ProCRC and EProCRC) models on several fine-grained benchmarkimage datasets for face recognition (AR and LFW) and species recognition (Oxford Flowers and Pets) tasks.We also expand our recent endemic Indian birds (IndBirds) dataset and report results on it. The demo code andIndBirds dataset are available through lead author.
Tasks	Face Recognition
Published	2019-03-21
URL	https://arxiv.org/abs/1903.09123v2
PDF	https://arxiv.org/pdf/1903.09123v2.pdf
PWC	https://paperswithcode.com/paper/pprocrc-probabilistic-collaboration-of-image
Repo
Framework

Comparison-Based Framework for Psychophysics: Lab versus Crowdsourcing


Title	Comparison-Based Framework for Psychophysics: Lab versus Crowdsourcing
Authors	Siavash Haghiri, Patricia Rubisch, Robert Geirhos, Felix Wichmann, Ulrike von Luxburg
Abstract	Traditionally, psychophysical experiments are conducted by repeated measurements on a few well-trained participants under well-controlled conditions, often resulting in, if done properly, high quality data. In recent years, however, crowdsourcing platforms are becoming increasingly popular means of data collection, measuring many participants at the potential cost of obtaining data of worse quality. In this paper we study whether the use of comparison-based (ordinal) data, combined with machine learning algorithms, can boost the reliability of crowdsourcing studies for psychophysics, such that they can achieve performance close to a lab experiment. To this end, we compare three setups: simulations, a psychophysics lab experiment, and the same experiment on Amazon Mechanical Turk. All these experiments are conducted in a comparison-based setting where participants have to answer triplet questions of the form “is object x closer to y or to z?". We then use machine learning to solve the triplet prediction problem: given a subset of triplet questions with corresponding answers, we predict the answer to the remaining questions. Considering the limitations and noise on MTurk, we find that the accuracy of triplet prediction is surprisingly close—but not equal—to our lab study.
Tasks
Published	2019-05-17
URL	https://arxiv.org/abs/1905.07234v2
PDF	https://arxiv.org/pdf/1905.07234v2.pdf
PWC	https://paperswithcode.com/paper/comparison-based-framework-for-psychophysics
Repo
Framework

Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks


Title	Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks
Authors	Roberto Martín-Martín, Michelle A. Lee, Rachel Gardner, Silvio Savarese, Jeannette Bohg, Animesh Garg
Abstract	Reinforcement Learning (RL) of contact-rich manipulation tasks has yielded impressive results in recent years. While many studies in RL focus on varying the observation space or reward model, few efforts focused on the choice of action space (e.g. joint or end-effector space, position, velocity, etc.). However, studies in robot motion control indicate that choosing an action space that conforms to the characteristics of the task can simplify exploration and improve robustness to disturbances. This paper studies the effect of different action spaces in deep RL and advocates for Variable Impedance Control in End-effector Space (VICES) as an advantageous action space for constrained and contact-rich tasks. We evaluate multiple action spaces on three prototypical manipulation tasks: Path Following (task with no contact), Door Opening (task with kinematic constraints), and Surface Wiping (task with continuous contact). We show that VICES improves sample efficiency, maintains low energy consumption, and ensures safety across all three experimental setups. Further, RL policies learned with VICES can transfer across different robot models in simulation, and from simulation to real for the same robot. Further information is available at https://stanfordvl.github.io/vices.
Tasks
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08880v2
PDF	https://arxiv.org/pdf/1906.08880v2.pdf
PWC	https://paperswithcode.com/paper/variable-impedance-control-in-end-effector
Repo
Framework

Joint Manifold Diffusion for Combining Predictions on Decoupled Observations


Title	Joint Manifold Diffusion for Combining Predictions on Decoupled Observations
Authors	Kwang In Kim, Hyung Jin Chang
Abstract	We present a new predictor combination algorithm that improves a given task predictor based on potentially relevant reference predictors. Existing approaches are limited in that, to discover the underlying task dependence, they either require known parametric forms of all predictors or access to a single fixed dataset on which all predictors are jointly evaluated. To overcome these limitations, we design a new non-parametric task dependence estimation procedure that automatically aligns evaluations of heterogeneous predictors across disjoint feature sets. Our algorithm is instantiated as a robust manifold diffusion process that jointly refines the estimated predictor alignments and the corresponding task dependence. We apply this algorithm to the relative attributes ranking problem and demonstrate that it not only broadens the application range of predictor combination approaches but also outperforms existing methods even when applied to classical predictor combination settings.
Tasks
Published	2019-04-10
URL	http://arxiv.org/abs/1904.05159v1
PDF	http://arxiv.org/pdf/1904.05159v1.pdf
PWC	https://paperswithcode.com/paper/joint-manifold-diffusion-for-combining
Repo
Framework

Efficient Machine Learning for Large-Scale Urban Land-Use Forecasting in Sub-Saharan Africa


Title	Efficient Machine Learning for Large-Scale Urban Land-Use Forecasting in Sub-Saharan Africa
Authors	Daniel Omeiza
Abstract	Urbanization is a common phenomenon in developing countries and it poses serious challenges when not managed effectively. Lack of proper planning and management may cause the encroachment of urban fabrics into reserved or special regions which in turn can lead to an unsustainable increase in population. Ineffective management and planning generally leads to depreciated standard of living, where physical hazards like traffic accidents and disease vector breeding become prevalent. In order to support urban planners and policy makers in effective planning and accurate decision making, we investigate urban land-use in sub-Saharan Africa. Land-use dynamics serves as a crucial parameter in current strategies and policies for natural resource management and monitoring. Focusing on Nairobi, we use an efficient deep learning approach with patch-based prediction to classify regions based on land-use from 2004 to 2018 on a quarterly basis. We estimate changes in land-use within this period, and using the Autoregressive Integrated Moving Average (ARIMA) model, our results forecast land-use for a given future date. Furthermore, we provide labelled land-use maps which will be helpful to urban planners.
Tasks	Decision Making
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00340v1
PDF	https://arxiv.org/pdf/1908.00340v1.pdf
PWC	https://paperswithcode.com/paper/efficient-machine-learning-for-large-scale
Repo
Framework

D-SPIDER-SFO: A Decentralized Optimization Algorithm with Faster Convergence Rate for Nonconvex Problems


Title	D-SPIDER-SFO: A Decentralized Optimization Algorithm with Faster Convergence Rate for Nonconvex Problems
Authors	Taoxing Pan, Jun Liu, Jie Wang
Abstract	Decentralized optimization algorithms have attracted intensive interests recently, as it has a balanced communication pattern, especially when solving large-scale machine learning problems. Stochastic Path Integrated Differential Estimator Stochastic First-Order method (SPIDER-SFO) nearly achieves the algorithmic lower bound in certain regimes for nonconvex problems. However, whether we can find a decentralized algorithm which achieves a similar convergence rate to SPIDER-SFO is still unclear. To tackle this problem, we propose a decentralized variant of SPIDER-SFO, called decentralized SPIDER-SFO (D-SPIDER-SFO). We show that D-SPIDER-SFO achieves a similar gradient computation cost—that is, $\mathcal{O}(\epsilon^{-3})$ for finding an $\epsilon$-approximate first-order stationary point—to its centralized counterpart. To the best of our knowledge, D-SPIDER-SFO achieves the state-of-the-art performance for solving nonconvex optimization problems on decentralized networks in terms of the computational cost. Experiments on different network configurations demonstrate the efficiency of the proposed method.
Tasks
Published	2019-11-28
URL	https://arxiv.org/abs/1911.12665v1
PDF	https://arxiv.org/pdf/1911.12665v1.pdf
PWC	https://paperswithcode.com/paper/d-spider-sfo-a-decentralized-optimization
Repo
Framework

DeepWiFi: Cognitive WiFi with Deep Learning


Title	DeepWiFi: Cognitive WiFi with Deep Learning
Authors	Kemal Davaslioglu, Sohraab Soltani, Tugba Erpek, Yalin E. Sagduyu
Abstract	We present the DeepWiFi protocol, which hardens the baseline WiFi (IEEE 802.11ac) with deep learning and sustains high throughput by mitigating out-of-network interference. DeepWiFi is interoperable with baseline WiFi and builds upon the existing WiFi’s PHY transceiver chain without changing the MAC frame format. Users run DeepWiFi for i) RF front end processing; ii) spectrum sensing and signal classification; iii) signal authentication; iv) channel selection and access; v) power control; vi) modulation and coding scheme (MCS) adaptation; and vii) routing. DeepWiFi mitigates the effects of probabilistic, sensing-based, and adaptive jammers. RF front end processing applies a deep learning-based autoencoder to extract spectrum-representative features. Then a deep neural network is trained to classify waveforms reliably as idle, WiFi, or jammer. Utilizing channel labels, users effectively access idle or jammed channels, while avoiding interference with legitimate WiFi transmissions (authenticated by machine learning-based RF fingerprinting) resulting in higher throughput. Users optimize their transmit power for low probability of intercept/detection and their MCS to maximize link rates used by backpressure algorithm for routing. Supported by embedded platform implementation, DeepWiFi provides major throughput gains compared to baseline WiFi and another jamming-resistant protocol, especially when channels are likely to be jammed and the signal-to-interference-plus-noise-ratio is low.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13315v1
PDF	https://arxiv.org/pdf/1910.13315v1.pdf
PWC	https://paperswithcode.com/paper/191013315
Repo
Framework

Semi-Supervised Learning by Label Gradient Alignment


Title	Semi-Supervised Learning by Label Gradient Alignment
Authors	Jacob Jackson, John Schulman
Abstract	We present label gradient alignment, a novel algorithm for semi-supervised learning which imputes labels for the unlabeled data and trains on the imputed labels. We define a semantically meaningful distance metric on the input space by mapping a point (x, y) to the gradient of the model at (x, y). We then formulate an optimization problem whose objective is to minimize the distance between the labeled and the unlabeled data in this space, and we solve it by gradient descent on the imputed labels. We evaluate label gradient alignment using the standardized architecture introduced by Oliver et al. (2018) and demonstrate state-of-the-art accuracy in semi-supervised CIFAR-10 classification.
Tasks
Published	2019-02-06
URL	http://arxiv.org/abs/1902.02336v1
PDF	http://arxiv.org/pdf/1902.02336v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-by-label-gradient
Repo
Framework

Experimental performance of graph neural networks on random instances of max-cut


Title	Experimental performance of graph neural networks on random instances of max-cut
Authors	Weichi Yao, Afonso S. Bandeira, Soledad Villar
Abstract	This note explores the applicability of unsupervised machine learning techniques towards hard optimization problems on random inputs. In particular we consider Graph Neural Networks (GNNs) – a class of neural networks designed to learn functions on graphs – and we apply them to the max-cut problem on random regular graphs. We focus on the max-cut problem on random regular graphs because it is a fundamental problem that has been widely studied. In particular, even though there is no known explicit solution to compare the output of our algorithm to, we can leverage the known asymptotics of the optimal max-cut value in order to evaluate the performance of the GNNs. In order to put the performance of the GNNs in context, we compare it with the classical semidefinite relaxation approach by Goemans and Williamson~(SDP), and with extremal optimization, which is a local optimization heuristic from the statistical physics literature. The numerical results we obtain indicate that, surprisingly, Graph Neural Networks attain comparable performance to the Goemans and Williamson SDP. We also observe that extremal optimization consistently outperforms the other two methods. Furthermore, the performances of the three methods present similar patterns, that is, for sparser, and for larger graphs, the size of the found cuts are closer to the asymptotic optimal max-cut value.
Tasks
Published	2019-08-15
URL	https://arxiv.org/abs/1908.05767v1
PDF	https://arxiv.org/pdf/1908.05767v1.pdf
PWC	https://paperswithcode.com/paper/experimental-performance-of-graph-neural
Repo
Framework

Detection and Correction of Cardiac MR Motion Artefacts during Reconstruction from K-space


Title	Detection and Correction of Cardiac MR Motion Artefacts during Reconstruction from K-space
Authors	lkay Oksuz, James Clough, Bram Ruijsink, Esther Puyol-Anton, Aurelien Bustin, Gastao Cruz, Claudia Prieto, Daniel Rueckert, Andrew P. King, Julia A. Schnabel
Abstract	In fully sampled cardiac MR (CMR) acquisitions, motion can lead to corruption of k-space lines, which can result in artefacts in the reconstructed images. In this paper, we propose a method to automatically detect and correct motion-related artefacts in CMR acquisitions during reconstruction from k-space data. Our correction method is inspired by work on undersampled CMR reconstruction, and uses deep learning to optimize a data-consistency term for under-sampled k-space reconstruction. Our main methodological contribution is the addition of a detection network to classify motion-corrupted k-space lines to convert the problem of artefact correction to a problem of reconstruction using the data consistency term. We train our network to automatically correct for motion-related artefacts using synthetically corrupted cine CMR k-space data as well as uncorrupted CMR images. Using a test set of 50 2D+time cine CMR datasets from the UK Biobank, we achieve good image quality in the presence of synthetic motion artefacts. We quantitatively compare our method with a variety of techniques for recovering good image quality and showcase better performance compared to state of the art denoising techniques with a PSNR of 37.1. Moreover, we show that our method preserves the quality of uncorrupted images and therefore can be also utilized as a general image reconstruction algorithm.
Tasks	Denoising, Image Reconstruction
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05695v1
PDF	https://arxiv.org/pdf/1906.05695v1.pdf
PWC	https://paperswithcode.com/paper/detection-and-correction-of-cardiac-mr-motion
Repo
Framework

Towards FAIR protocols and workflows: The OpenPREDICT case study


Title	Towards FAIR protocols and workflows: The OpenPREDICT case study
Authors	Remzi Celebi, Joao Rebelo Moreira, Ahmed A. Hassan, Sandeep Ayyar, Lars Ridder, Tobias Kuhn, Michel Dumontier
Abstract	It is essential for the advancement of science that scientists and researchers share, reuse and reproduce workflows and protocols used by others. The FAIR principles are a set of guidelines that aim to maximize the value and usefulness of research data, and emphasize a number of important points regarding the means by which digital objects are found and reused by others. The question of how to apply these principles not just to the static input and output data but also to the dynamic workflows and protocols that consume and produce them is still under debate and poses a number of challenges. In this paper we describe our inclusive and overarching approach to apply the FAIR principles to workflows and protocols and demonstrate its benefits. We apply and evaluate our approach on a case study that consists of making the PREDICT workflow, a highly cited drug repurposing workflow, open and FAIR. This includes FAIRification of the involved datasets, as well as applying semantic technologies to represent and store data about the detailed versions of the general protocol, of the concrete workflow instructions, and of their execution traces. A semantic model was proposed to better address these specific requirements and were evaluated by answering competency questions. This semantic model consists of classes and relations from a number of existing ontologies, including Workflow4ever, PROV, EDAM, and BPMN. This allowed us then to formulate and answer new kinds of competency questions. Our evaluation shows the high degree to which our FAIRified OpenPREDICT workflow now adheres to the FAIR principles and the practicality and usefulness of being able to answer our new competency questions.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.09531v1
PDF	https://arxiv.org/pdf/1911.09531v1.pdf
PWC	https://paperswithcode.com/paper/towards-fair-protocols-and-workflows-the
Repo
Framework