October 20, 2019

3055 words 15 mins read

Paper Group ANR 55

Efficient Graph Cut Optimization for Full CRFs with Quantized Edges. LEARN Codes: Inventing Low-latency Codes via Recurrent Neural Networks. Online Learning in Kernelized Markov Decision Processes. Counterfactuals uncover the modular structure of deep generative models. Mining Threat Intelligence about Open-Source Projects and Libraries from Code R …

Efficient Graph Cut Optimization for Full CRFs with Quantized Edges


Title	Efficient Graph Cut Optimization for Full CRFs with Quantized Edges
Authors	Olga Veksler
Abstract	Fully connected pairwise Conditional Random Fields (Full-CRF) with Gaussian edge weights can achieve superior results compared to sparsely connected CRFs. However, traditional methods for Full-CRFs are too expensive. Previous work develops efficient approximate optimization based on mean field inference, which is a local optimization method and can be far from the optimum. We propose efficient and effective optimization based on graph cuts for Full-CRFs with quantized edge weights. To quantize edge weights, we partition the image into superpixels and assume that the weight of an edge between any two pixels depends only on the superpixels these pixels belong to. Our quantized edge CRF is an approximation to the Gaussian edge CRF, and gets closer to it as superpixel size decreases. Being an approximation, our model offers an intuition about the regularization properties of the Guassian edge Full-CRF. For efficient inference, we first consider the two-label case and develop an approximate method based on transforming the original problem into a smaller domain. Then we handle multi-label CRF by showing how to implement expansion moves. In both binary and multi-label cases, our solutions have significantly lower energy compared to that of mean field inference. We also show the effectiveness of our approach on semantic segmentation task.
Tasks	Semantic Segmentation
Published	2018-09-13
URL	http://arxiv.org/abs/1809.04995v1
PDF	http://arxiv.org/pdf/1809.04995v1.pdf
PWC	https://paperswithcode.com/paper/efficient-graph-cut-optimization-for-full
Repo
Framework

LEARN Codes: Inventing Low-latency Codes via Recurrent Neural Networks


Title	LEARN Codes: Inventing Low-latency Codes via Recurrent Neural Networks
Authors	Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
Abstract	Designing channel codes under low latency constraints is one of the most demanding requirements in 5G standards. However, sharp characterizations of the performances of traditional codes are only available in the large block-length limit. Code designs are guided by those asymptotic analyses and require large block lengths and long latency to achieve the desired error rate. Furthermore, when the codes designed for one channel (e.g. Additive White Gaussian Noise (AWGN) channel) are used for another (e.g. non-AWGN channels), heuristics are necessary to achieve any nontrivial performance -thereby severely lacking in robustness as well as adaptivity. Obtained by jointly designing Recurrent Neural Network (RNN) based encoder and decoder, we propose an end-to-end learned neural code which outperforms canonical convolutional code under block settings. With this gained experience of designing a novel neural block code, we propose a new class of codes under low latency constraint - Low-latency Efficient Adaptive Robust Neural (LEARN) codes, which outperforms the state-of-the-art low latency codes as well as exhibits robustness and adaptivity properties. LEARN codes show the potential of designing new versatile and universal codes for future communications via tools of modern deep learning coupled with communication engineering insights.
Tasks
Published	2018-11-30
URL	http://arxiv.org/abs/1811.12707v1
PDF	http://arxiv.org/pdf/1811.12707v1.pdf
PWC	https://paperswithcode.com/paper/learn-codes-inventing-low-latency-codes-via
Repo
Framework

Online Learning in Kernelized Markov Decision Processes


Title	Online Learning in Kernelized Markov Decision Processes
Authors	Sayak Ray Chowdhury, Aditya Gopalan
Abstract	We consider online learning for minimizing regret in unknown, episodic Markov decision processes (MDPs) with continuous states and actions. We develop variants of the UCRL and posterior sampling algorithms that employ nonparametric Gaussian process priors to generalize across the state and action spaces. When the transition and reward functions of the true MDP are members of the associated Reproducing Kernel Hilbert Spaces of functions induced by symmetric psd kernels (frequentist setting), we show that the algorithms enjoy sublinear regret bounds. The bounds are in terms of explicit structural parameters of the kernels, namely a novel generalization of the information gain metric from kernelized bandit, and highlight the influence of transition and reward function structure on the learning performance. Our results are applicable to multidimensional state and action spaces with composite kernel structures, and generalize results from the literature on kernelized bandits, and the adaptive control of parametric linear dynamical systems with quadratic costs.
Tasks
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08052v2
PDF	http://arxiv.org/pdf/1805.08052v2.pdf
PWC	https://paperswithcode.com/paper/online-learning-in-kernelized-markov-decision
Repo
Framework

Counterfactuals uncover the modular structure of deep generative models


Title	Counterfactuals uncover the modular structure of deep generative models
Authors	Michel Besserve, Arash Mehrjou, Rémy Sun, Bernhard Schölkopf
Abstract	Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to perform meaningful and controllable transformations in the data space remains challenging without some form of supervision. While previous work has focused on exploiting statistical independence to disentangle latent factors, we argue that such requirement is too restrictive and propose instead a non-statistical framework that relies on counterfactual manipulations to uncover a modular structure of the network composed of disentangled groups of internal variables. Experiments with a variety of generative models trained on complex image datasets show the obtained modules can be used to design targeted interventions. This opens the way to applications such as computationally efficient style transfer and the automated assessment of robustness to contextual changes in pattern recognition systems.
Tasks	Style Transfer
Published	2018-12-08
URL	https://arxiv.org/abs/1812.03253v2
PDF	https://arxiv.org/pdf/1812.03253v2.pdf
PWC	https://paperswithcode.com/paper/counterfactuals-uncover-the-modular-structure
Repo
Framework

Mining Threat Intelligence about Open-Source Projects and Libraries from Code Repository Issues and Bug Reports


Title	Mining Threat Intelligence about Open-Source Projects and Libraries from Code Repository Issues and Bug Reports
Authors	Lorenzo Neil, Sudip Mittal, Anupam Joshi
Abstract	Open-Source Projects and Libraries are being used in software development while also bearing multiple security vulnerabilities. This use of third party ecosystem creates a new kind of attack surface for a product in development. An intelligent attacker can attack a product by exploiting one of the vulnerabilities present in linked projects and libraries. In this paper, we mine threat intelligence about open source projects and libraries from bugs and issues reported on public code repositories. We also track library and project dependencies for installed software on a client machine. We represent and store this threat intelligence, along with the software dependencies in a security knowledge graph. Security analysts and developers can then query and receive alerts from the knowledge graph if any threat intelligence is found about linked libraries and projects, utilized in their products.
Tasks
Published	2018-08-09
URL	http://arxiv.org/abs/1808.04673v1
PDF	http://arxiv.org/pdf/1808.04673v1.pdf
PWC	https://paperswithcode.com/paper/mining-threat-intelligence-about-open-source
Repo
Framework

Reduce, Reuse, Recycle: New uses for old QA resources


Title	Reduce, Reuse, Recycle: New uses for old QA resources
Authors	Jeff Mitchell, Sebastian Riedel
Abstract	We investigate applying repurposed generic QA data and models to a recently proposed relation extraction task. We find that training on SQuAD produces better zero-shot performance and more robust generalisation compared to the task specific training set. We also show that standard QA architectures (e.g. FastQA or BiDAF) can be applied to the slot filling queries without the need for model modification.
Tasks	Relation Extraction, Slot Filling
Published	2018-04-22
URL	http://arxiv.org/abs/1804.08125v2
PDF	http://arxiv.org/pdf/1804.08125v2.pdf
PWC	https://paperswithcode.com/paper/reduce-reuse-recycle-new-uses-for-old-qa
Repo
Framework

2CoBel : An Efficient Belief Function Extension for Two-dimensional Continuous Spaces


Title	2CoBel : An Efficient Belief Function Extension for Two-dimensional Continuous Spaces
Authors	Nicola Pellicanò, Sylvie Le Hégarat-Mascle, Emanuel Aldea
Abstract	This paper introduces an innovative approach for handling 2D compound hypotheses within the Belief Function Theory framework. We propose a polygon-based generic rep- resentation which relies on polygon clipping operators. This approach allows us to account in the computational cost for the precision of the representation independently of the cardinality of the discernment frame. For the BBA combination and decision making, we propose efficient algorithms which rely on hashes for fast lookup, and on a topological ordering of the focal elements within a directed acyclic graph encoding their interconnections. Additionally, an implementation of the functionalities proposed in this paper is provided as an open source library. Experimental results on a pedestrian localization problem are reported. The experiments show that the solution is accurate and that it fully benefits from the scalability of the 2D search space granularity provided by our representation.
Tasks	Decision Making
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08857v1
PDF	http://arxiv.org/pdf/1803.08857v1.pdf
PWC	https://paperswithcode.com/paper/2cobel-an-efficient-belief-function-extension
Repo
Framework

Learning to Generate Facial Depth Maps


Title	Learning to Generate Facial Depth Maps
Authors	Stefano Pini, Filippo Grazioli, Guido Borghi, Roberto Vezzani, Rita Cucchiara
Abstract	In this paper, an adversarial architecture for facial depth map estimation from monocular intensity images is presented. By following an image-to-image approach, we combine the advantages of supervised learning and adversarial training, proposing a conditional Generative Adversarial Network that effectively learns to translate intensity face images into the corresponding depth maps. Two public datasets, namely Biwi database and Pandora dataset, are exploited to demonstrate that the proposed model generates high-quality synthetic depth images, both in terms of visual appearance and informative content. Furthermore, we show that the model is capable of predicting distinctive facial details by testing the generated depth maps through a deep model trained on authentic depth maps for the face verification task.
Tasks	Face Verification
Published	2018-05-30
URL	http://arxiv.org/abs/1805.11927v1
PDF	http://arxiv.org/pdf/1805.11927v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-generate-facial-depth-maps
Repo
Framework

Predicting Outcome of Indian Premier League (IPL) Matches Using Machine Learning


Title	Predicting Outcome of Indian Premier League (IPL) Matches Using Machine Learning
Authors	Rabindra Lamsal, Ayesha Choudhary
Abstract	Cricket, especially the Twenty20 format, has maximum uncertainty, where a single over can completely change the momentum of the game. With millions of people following the Indian Premier League (IPL), developing a model for predicting the outcome of its matches is a real-world problem. A cricket match depends upon various factors, and in this work, the factors which significantly influence the outcome of a Twenty20 cricket match are identified. Each player’s performance in the field is considered to find out the overall weight (relative strength) of the teams. A multivariate regression based solution is proposed to calculate points of each player in the league and the overall weight of a team is computed based on the past performance of the players who have appeared most for the team. Finally, a dataset was modeled based on the identified seven factors which influence the outcome of an IPL match. Six machine learning models were trained and used for predicting the outcome of each 2018 IPL match, 15 minutes before the gameplay, immediately after the toss. The prediction results are impressive. The problems with the dataset and how the accuracy of the classifier can be improved further is discussed.
Tasks	Feature Selection
Published	2018-09-26
URL	https://arxiv.org/abs/1809.09813v4
PDF	https://arxiv.org/pdf/1809.09813v4.pdf
PWC	https://paperswithcode.com/paper/predicting-outcome-of-indian-premier-league
Repo
Framework

Can Adversarially Robust Learning Leverage Computational Hardness?


Title	Can Adversarially Robust Learning Leverage Computational Hardness?
Authors	Saeed Mahloujifar, Mohammad Mahmoody
Abstract	Making learners robust to adversarial perturbation at test time (i.e., evasion attacks) or training time (i.e., poisoning attacks) has emerged as a challenging task. It is known that for some natural settings, sublinear perturbations in the training phase or the testing phase can drastically decrease the quality of the predictions. These negative results, however, are information theoretic and only prove the existence of such successful adversarial perturbations. A natural question for these settings is whether or not we can make classifiers computationally robust to polynomial-time attacks. In this work, we prove strong barriers against achieving such envisioned computational robustness both for evasion and poisoning attacks. In particular, we show that if the test instances come from a product distribution (e.g., uniform over ${0,1}^n$ or $[0,1]^n$, or isotropic $n$-variate Gaussian) and that there is an initial constant error, then there exists a polynomial-time attack that finds adversarial examples of Hamming distance $O(\sqrt n)$. For poisoning attacks, we prove that for any learning algorithm with sample complexity $m$ and any efficiently computable “predicate” defining some “bad” property $B$ for the produced hypothesis (e.g., failing on a particular test) that happens with an initial constant probability, there exist polynomial-time online poisoning attacks that tamper with $O (\sqrt m)$ many examples, replace them with other correctly labeled examples, and increases the probability of the bad event $B$ to $\approx 1$. Both of our poisoning and evasion attacks are black-box in how they access their corresponding components of the system (i.e., the hypothesis, the concept, and the learning algorithm) and make no further assumptions about the classifier or the learning algorithm producing the classifier.
Tasks
Published	2018-10-02
URL	http://arxiv.org/abs/1810.01407v3
PDF	http://arxiv.org/pdf/1810.01407v3.pdf
PWC	https://paperswithcode.com/paper/can-adversarially-robust-learning-leverage
Repo
Framework

Deep Appearance Maps


Title	Deep Appearance Maps
Authors	Maxim Maximov, Laura Leal-Taixé, Mario Fritz, Tobias Ritschel
Abstract	We propose a deep representation of appearance, i. e., the relation of color, surface orientation, viewer position, material and illumination. Previous approaches have useddeep learning to extract classic appearance representationsrelating to reflectance model parameters (e. g., Phong) orillumination (e. g., HDR environment maps). We suggest todirectly represent appearance itself as a network we call aDeep Appearance Map (DAM). This is a 4D generalizationover 2D reflectance maps, which held the view direction fixed. First, we show how a DAM can be learned from images or video frames and later be used to synthesize appearance, given new surface orientations and viewer positions. Second, we demonstrate how another network can be used to map from an image or video frames to a DAM network to reproduce this appearance, without using a lengthy optimization such as stochastic gradient descent (learning-to-learn). Finally, we show the example of an appearance estimation-and-segmentation task, mapping from an image showingmultiple materials to multiple deep appearance maps.
Tasks
Published	2018-04-03
URL	https://arxiv.org/abs/1804.00863v3
PDF	https://arxiv.org/pdf/1804.00863v3.pdf
PWC	https://paperswithcode.com/paper/deep-appearance-maps
Repo
Framework

Multi-resolution neural networks for tracking seismic horizons from few training images


Title	Multi-resolution neural networks for tracking seismic horizons from few training images
Authors	Bas Peters, Justin Granek, Eldad Haber
Abstract	Detecting a specific horizon in seismic images is a valuable tool for geological interpretation. Because hand-picking the locations of the horizon is a time-consuming process, automated computational methods were developed starting three decades ago. Older techniques for such picking include interpolation of control points however, in recent years neural networks have been used for this task. Until now, most networks trained on small patches from larger images. This limits the networks ability to learn from large-scale geologic structures. Moreover, currently available networks and training strategies require label patches that have full and continuous annotations, which are also time-consuming to generate. We propose a projected loss-function for training convolutional networks with a multi-resolution structure, including variants of the U-net. Our networks learn from a small number of large seismic images without creating patches. The projected loss-function enables training on labels with just a few annotated pixels and has no issue with the other unknown label pixels. Training uses all data without reserving some for validation. Only the labels are split into training/testing. Contrary to other work on horizon tracking, we train the network to perform non-linear regression, and not classification. As such, we propose labels as the convolution of a Gaussian kernel and the known horizon locations that indicate uncertainty in the labels. The network output is the probability of the horizon location. We demonstrate the proposed computational ingredients on two different datasets, for horizon extrapolation and interpolation. We show that the predictions of our methodology are accurate even in areas far from known horizon locations because our learning strategy exploits all data in large seismic images.
Tasks
Published	2018-12-26
URL	http://arxiv.org/abs/1812.11092v1
PDF	http://arxiv.org/pdf/1812.11092v1.pdf
PWC	https://paperswithcode.com/paper/multi-resolution-neural-networks-for-tracking
Repo
Framework

Efficient Road Lane Marking Detection with Deep Learning


Title	Efficient Road Lane Marking Detection with Deep Learning
Authors	Ping-Rong Chen, Shao-Yuan Lo, Hsueh-Ming Hang, Sheng-Wei Chan, Jing-Jhih Lin
Abstract	Lane mark detection is an important element in the road scene analysis for Advanced Driver Assistant System (ADAS). Limited by the onboard computing power, it is still a challenge to reduce system complexity and maintain high accuracy at the same time. In this paper, we propose a Lane Marking Detector (LMD) using a deep convolutional neural network to extract robust lane marking features. To improve its performance with a target of lower complexity, the dilated convolution is adopted. A shallower and thinner structure is designed to decrease the computational cost. Moreover, we also design post-processing algorithms to construct 3rd-order polynomial models to fit into the curved lanes. Our system shows promising results on the captured road scenes.
Tasks
Published	2018-09-11
URL	http://arxiv.org/abs/1809.03994v1
PDF	http://arxiv.org/pdf/1809.03994v1.pdf
PWC	https://paperswithcode.com/paper/efficient-road-lane-marking-detection-with
Repo
Framework

Object cosegmentation using deep Siamese network


Title	Object cosegmentation using deep Siamese network
Authors	Prerana Mukherjee, Brejesh Lall, Snehith Lattupally
Abstract	Object cosegmentation addresses the problem of discovering similar objects from multiple images and segmenting them as foreground simultaneously. In this paper, we propose a novel end-to-end pipeline to segment the similar objects simultaneously from relevant set of images using supervised learning via deep-learning framework. We experiment with multiple set of object proposal generation techniques and perform extensive numerical evaluations by training the Siamese network with generated object proposals. Similar objects proposals for the test images are retrieved using the ANNOY (Approximate Nearest Neighbor) library and deep semantic segmentation is performed on them. Finally, we form a collage from the segmented similar objects based on the relative importance of the objects.
Tasks	Object Proposal Generation, Semantic Segmentation
Published	2018-03-07
URL	http://arxiv.org/abs/1803.02555v2
PDF	http://arxiv.org/pdf/1803.02555v2.pdf
PWC	https://paperswithcode.com/paper/object-cosegmentation-using-deep-siamese
Repo
Framework

Differential Temporal Difference Learning


Title	Differential Temporal Difference Learning
Authors	Adithya M. Devraj, Ioannis Kontoyiannis, Sean P. Meyn
Abstract	Value functions derived from Markov decision processes arise as a central component of algorithms as well as performance metrics in many statistics and engineering applications of machine learning techniques. Computation of the solution to the associated Bellman equations is challenging in most practical cases of interest. A popular class of approximation techniques, known as Temporal Difference (TD) learning algorithms, are an important sub-class of general reinforcement learning methods. The algorithms introduced in this paper are intended to resolve two well-known difficulties of TD-learning approaches: Their slow convergence due to very high variance, and the fact that, for the problem of computing the relative value function, consistent algorithms exist only in special cases. First we show that the gradients of these value functions admit a representation that lends itself to algorithm design. Based on this result, a new class of differential TD-learning algorithms is introduced. For Markovian models on Euclidean space with smooth dynamics, the algorithms are shown to be consistent under general conditions. Numerical results show dramatic variance reduction when compared to standard methods.
Tasks
Published	2018-12-28
URL	https://arxiv.org/abs/1812.11137v2
PDF	https://arxiv.org/pdf/1812.11137v2.pdf
PWC	https://paperswithcode.com/paper/differential-temporal-difference-learning
Repo
Framework