Paper Group ANR 999
3D-Aware Scene Manipulation via Inverse Graphics. A Common Framework for Natural Gradient and Taylor based Optimisation using Manifold Theory. QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation. Unsupervised Domain Adaptation Based on Source-guided Discrepancy. Binge Watching: Scaling Affordance Learning from Sitcoms …
3D-Aware Scene Manipulation via Inverse Graphics
| Title | 3D-Aware Scene Manipulation via Inverse Graphics |
| Authors | Shunyu Yao, Tzu Ming Harry Hsu, Jun-Yan Zhu, Jiajun Wu, Antonio Torralba, William T. Freeman, Joshua B. Tenenbaum |
| Abstract | We aim to obtain an interpretable, expressive, and disentangled scene representation that contains comprehensive structural and textural information for each object. Previous scene representations learned by neural networks are often uninterpretable, limited to a single object, or lacking 3D knowledge. In this work, we propose 3D scene de-rendering networks (3D-SDN) to address the above issues by integrating disentangled representations for semantics, geometry, and appearance into a deep generative model. Our scene encoder performs inverse graphics, translating a scene into a structured object-wise representation. Our decoder has two components: a differentiable shape renderer and a neural texture generator. The disentanglement of semantics, geometry, and appearance supports 3D-aware scene manipulation, e.g., rotating and moving objects freely while keeping the consistent shape and texture, and changing the object appearance without affecting its shape. Experiments demonstrate that our editing scheme based on 3D-SDN is superior to its 2D counterpart. |
| Tasks | |
| Published | 2018-08-28 |
| URL | http://arxiv.org/abs/1808.09351v4 |
| http://arxiv.org/pdf/1808.09351v4.pdf | |
| PWC | https://paperswithcode.com/paper/3d-aware-scene-manipulation-via-inverse |
| Repo | |
| Framework | |
A Common Framework for Natural Gradient and Taylor based Optimisation using Manifold Theory
| Title | A Common Framework for Natural Gradient and Taylor based Optimisation using Manifold Theory |
| Authors | Adnan Haider |
| Abstract | This technical report constructs a theoretical framework to relate standard Taylor approximation based optimisation methods with Natural Gradient (NG), a method which is Fisher efficient with probabilistic models. Such a framework will be shown to also provide mathematical justification to combine higher order methods with the method of NG. |
| Tasks | |
| Published | 2018-03-26 |
| URL | http://arxiv.org/abs/1803.09791v3 |
| http://arxiv.org/pdf/1803.09791v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-common-framework-for-natural-gradient-and |
| Repo | |
| Framework | |
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
| Title | QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation |
| Authors | Dmitry Kalashnikov, Alex Irpan, Peter Pastor, Julian Ibarz, Alexander Herzog, Eric Jang, Deirdre Quillen, Ethan Holly, Mrinal Kalakrishnan, Vincent Vanhoucke, Sergey Levine |
| Abstract | In this paper, we study the problem of learning vision-based dynamic manipulation skills using a scalable reinforcement learning approach. We study this problem in the context of grasping, a longstanding challenge in robotic manipulation. In contrast to static learning behaviors that choose a grasp point and then execute the desired grasp, our method enables closed-loop vision-based control, whereby the robot continuously updates its grasp strategy based on the most recent observations to optimize long-horizon grasp success. To that end, we introduce QT-Opt, a scalable self-supervised vision-based reinforcement learning framework that can leverage over 580k real-world grasp attempts to train a deep neural network Q-function with over 1.2M parameters to perform closed-loop, real-world grasping that generalizes to 96% grasp success on unseen objects. Aside from attaining a very high success rate, our method exhibits behaviors that are quite distinct from more standard grasping systems: using only RGB vision-based perception from an over-the-shoulder camera, our method automatically learns regrasping strategies, probes objects to find the most effective grasps, learns to reposition objects and perform other non-prehensile pre-grasp manipulations, and responds dynamically to disturbances and perturbations. |
| Tasks | |
| Published | 2018-06-27 |
| URL | http://arxiv.org/abs/1806.10293v3 |
| http://arxiv.org/pdf/1806.10293v3.pdf | |
| PWC | https://paperswithcode.com/paper/qt-opt-scalable-deep-reinforcement-learning |
| Repo | |
| Framework | |
Unsupervised Domain Adaptation Based on Source-guided Discrepancy
| Title | Unsupervised Domain Adaptation Based on Source-guided Discrepancy |
| Authors | Seiichi Kuroki, Nontawat Charoenphakdee, Han Bao, Junya Honda, Issei Sato, Masashi Sugiyama |
| Abstract | Unsupervised domain adaptation is the problem setting where data generating distributions in the source and target domains are different, and labels in the target domain are unavailable. One important question in unsupervised domain adaptation is how to measure the difference between the source and target domains. A previously proposed discrepancy that does not use the source domain labels requires high computational cost to estimate and may lead to a loose generalization error bound in the target domain. To mitigate these problems, we propose a novel discrepancy called source-guided discrepancy (S-disc), which exploits labels in the source domain. As a consequence, S-disc can be computed efficiently with a finite sample convergence guarantee. In addition, we show that S-disc can provide a tighter generalization error bound than the one based on an existing discrepancy. Finally, we report experimental results that demonstrate the advantages of S-disc over the existing discrepancies. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2018-09-11 |
| URL | http://arxiv.org/abs/1809.03839v3 |
| http://arxiv.org/pdf/1809.03839v3.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-based-on |
| Repo | |
| Framework | |
Binge Watching: Scaling Affordance Learning from Sitcoms
| Title | Binge Watching: Scaling Affordance Learning from Sitcoms |
| Authors | Xiaolong Wang, Rohit Girdhar, Abhinav Gupta |
| Abstract | In recent years, there has been a renewed interest in jointly modeling perception and action. At the core of this investigation is the idea of modeling affordances(Affordances are opportunities of interaction in the scene. In other words, it represents what actions can the object be used for). However, when it comes to predicting affordances, even the state of the art approaches still do not use any ConvNets. Why is that? Unlike semantic or 3D tasks, there still does not exist any large-scale dataset for affordances. In this paper, we tackle the challenge of creating one of the biggest dataset for learning affordances. We use seven sitcoms to extract a diverse set of scenes and how actors interact with different objects in the scenes. Our dataset consists of more than 10K scenes and 28K ways humans can interact with these 10K images. We also propose a two-step approach to predict affordances in a new scene. In the first step, given a location in the scene we classify which of the 30 pose classes is the likely affordance pose. Given the pose class and the scene, we then use a Variational Autoencoder (VAE) to extract the scale and deformation of the pose. The VAE allows us to sample the distribution of possible poses at test time. Finally, we show the importance of large-scale data in learning a generalizable and robust model of affordances. |
| Tasks | |
| Published | 2018-04-09 |
| URL | http://arxiv.org/abs/1804.03080v1 |
| http://arxiv.org/pdf/1804.03080v1.pdf | |
| PWC | https://paperswithcode.com/paper/binge-watching-scaling-affordance-learning |
| Repo | |
| Framework | |
Sentence Object Notation: Multilingual sentence notation based on Wordnet
| Title | Sentence Object Notation: Multilingual sentence notation based on Wordnet |
| Authors | Abdelkrime Aries, Djamel Eddine Zegour, Walid Khaled Hidouci |
| Abstract | The representation of sentences is a very important task. It can be used as a way to exchange data inter-applications. One main characteristic, that a notation must have, is a minimal size and a representative form. This can reduce the transfer time, and hopefully the processing time as well. Usually, sentence representation is associated to the processed language. The grammar of this language affects how we represent the sentence. To avoid language-dependent notations, we have to come up with a new representation which don’t use words, but their meanings. This can be done using a lexicon like wordnet, instead of words we use their synsets. As for syntactic relations, they have to be universal as much as possible. Our new notation is called STON “SenTences Object Notation”, which somehow has similarities to JSON. It is meant to be minimal, representative and language-independent syntactic representation. Also, we want it to be readable and easy to be created. This simplifies developing simple automatic generators and creating test banks manually. Its benefit is to be used as a medium between different parts of applications like: text summarization, language translation, etc. The notation is based on 4 languages: Arabic, English, Franch and Japanese; and there are some cases where these languages don’t agree on one representation. Also, given the diversity of grammatical structure of different world languages, this annotation may fail for some languages which allows more future improvements. |
| Tasks | Text Summarization |
| Published | 2018-01-03 |
| URL | http://arxiv.org/abs/1801.00984v2 |
| http://arxiv.org/pdf/1801.00984v2.pdf | |
| PWC | https://paperswithcode.com/paper/sentence-object-notation-multilingual |
| Repo | |
| Framework | |
Compositional planning in Markov decision processes: Temporal abstraction meets generalized logic composition
| Title | Compositional planning in Markov decision processes: Temporal abstraction meets generalized logic composition |
| Authors | Xuan Liu, Jie Fu |
| Abstract | In hierarchical planning for Markov decision processes (MDPs), temporal abstraction allows planning with macro-actions that take place at different time scale in form of sequential composition. In this paper, we propose a novel approach to compositional reasoning and hierarchical planning for MDPs under temporal logic constraints. In addition to sequential composition, we introduce a composition of policies based on generalized logic composition: Given sub-policies for sub-tasks and a new task expressed as logic compositions of subtasks, a semi-optimal policy, which is optimal in planning with only sub-policies, can be obtained by simply composing sub-polices. Thus, a synthesis algorithm is developed to compute optimal policies efficiently by planning with primitive actions, policies for sub-tasks, and the compositions of sub-policies, for maximizing the probability of satisfying temporal logic specifications. We demonstrate the correctness and efficiency of the proposed method in stochastic planning examples with a single agent and multiple task specifications. |
| Tasks | |
| Published | 2018-10-05 |
| URL | https://arxiv.org/abs/1810.02497v2 |
| https://arxiv.org/pdf/1810.02497v2.pdf | |
| PWC | https://paperswithcode.com/paper/compositional-planning-in-markov-decision |
| Repo | |
| Framework | |
Model-free Consensus Maximization for Non-Rigid Shapes
| Title | Model-free Consensus Maximization for Non-Rigid Shapes |
| Authors | Thomas Probst, Ajad Chhatkuli, Danda Pani Paudel, Luc Van Gool |
| Abstract | Many computer vision methods use consensus maximization to relate measurements containing outliers with the correct transformation model. In the context of rigid shapes, this is typically done using Random Sampling and Consensus (RANSAC) by estimating an analytical model that agrees with the largest number of measurements (inliers). However, small parameter models may not be always available. In this paper, we formulate the model-free consensus maximization as an Integer Program in a graph using `rules’ on measurements. We then provide a method to solve it optimally using the Branch and Bound (BnB) paradigm. We focus its application on non-rigid shapes, where we apply the method to remove outlier 3D correspondences and achieve performance superior to the state of the art. Our method works with outlier ratio as high as 80%. We further derive a similar formulation for 3D template to image matching, achieving similar or better performance compared to the state of the art. | |
| Tasks | |
| Published | 2018-07-05 |
| URL | http://arxiv.org/abs/1807.01963v2 |
| http://arxiv.org/pdf/1807.01963v2.pdf | |
| PWC | https://paperswithcode.com/paper/model-free-consensus-maximization-for-non |
| Repo | |
| Framework | |
A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks
| Title | A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks |
| Authors | Qian Wang, Ning Jia, Toby P. Breckon |
| Abstract | Recent studies on multi-label image classification have focused on designing more complex architectures of deep neural networks such as the use of attention mechanisms and region proposal networks. Although performance gains have been reported, the backbone deep models of the proposed approaches and the evaluation metrics employed in different works vary, making it difficult to compare each fairly. Moreover, due to the lack of properly investigated baselines, the advantage introduced by the proposed techniques are often ambiguous. To address these issues, we make a thorough investigation of the mainstream deep convolutional neural network architectures for multi-label image classification and present a strong baseline. With the use of proper data augmentation techniques and model ensembles, the basic deep architectures can achieve better performance than many existing more complex ones on three benchmark datasets, providing great insight for the future studies on multi-label image classification. |
| Tasks | Data Augmentation, Image Classification |
| Published | 2018-11-20 |
| URL | https://arxiv.org/abs/1811.08412v3 |
| https://arxiv.org/pdf/1811.08412v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-baseline-for-multi-label-image |
| Repo | |
| Framework | |
Multi-objective evolutionary algorithms for quantum circuit discovery
| Title | Multi-objective evolutionary algorithms for quantum circuit discovery |
| Authors | Václav Potoček, Alan P. Reynolds, Alessandro Fedrizzi, David W. Corne |
| Abstract | Quantum hardware continues to advance, yet finding new quantum algorithms - quantum software - remains a challenge, with classically trained computer programmers having little intuition of how computational tasks may be performed in the quantum realm. As such, the idea of developing automated tools for algorithm development is even more appealing for quantum computing than for classical. Here we develop a robust, multi-objective evolutionary search strategy to design quantum circuits ‘from scratch’, by combining and parameterizing a task-generic library of quantum circuit elements. When applied to ‘ab initio’ design of quantum circuits for the input/output mapping requirements of the quantum Fourier transform and Grover’s search algorithm, it finds textbook circuit designs, along with alternative structures that achieve the same functionality. Exploiting its multi-objective nature, the discovery algorithm can trade off performance measures such as accuracy, circuit width or depth, gate count, or implementability - a crucial requirement for first-generation quantum processors and applications. |
| Tasks | |
| Published | 2018-12-11 |
| URL | http://arxiv.org/abs/1812.04458v1 |
| http://arxiv.org/pdf/1812.04458v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-objective-evolutionary-algorithms-for |
| Repo | |
| Framework | |
Online Reciprocal Recommendation with Theoretical Performance Guarantees
| Title | Online Reciprocal Recommendation with Theoretical Performance Guarantees |
| Authors | Fabio Vitale, Nikos Parotsidis, Claudio Gentile |
| Abstract | A reciprocal recommendation problem is one where the goal of learning is not just to predict a user’s preference towards a passive item (e.g., a book), but to recommend the targeted user on one side another user from the other side such that a mutual interest between the two exists. The problem thus is sharply different from the more traditional items-to-users recommendation, since a good match requires meeting the preferences of both users. We initiate a rigorous theoretical investigation of the reciprocal recommendation task in a specific framework of sequential learning. We point out general limitations, formulate reasonable assumptions enabling effective learning and, under these assumptions, we design and analyze a computationally efficient algorithm that uncovers mutual likes at a pace comparable to those achieved by a clearvoyant algorithm knowing all user preferences in advance. Finally, we validate our algorithm against synthetic and real-world datasets, showing improved empirical performance over simple baselines. |
| Tasks | |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01182v1 |
| http://arxiv.org/pdf/1806.01182v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-reciprocal-recommendation-with |
| Repo | |
| Framework | |
Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing
| Title | Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing |
| Authors | Davide Bacciu, Federico Errica, Alessio Micheli |
| Abstract | We introduce the Contextual Graph Markov Model, an approach combining ideas from generative models and neural networks for the processing of graph data. It founds on a constructive methodology to build a deep architecture comprising layers of probabilistic models that learn to encode the structured information in an incremental fashion. Context is diffused in an efficient and scalable way across the graph vertexes and edges. The resulting graph encoding is used in combination with discriminative models to address structure classification benchmarks. |
| Tasks | |
| Published | 2018-05-27 |
| URL | https://arxiv.org/abs/1805.10636v2 |
| https://arxiv.org/pdf/1805.10636v2.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-graph-markov-model-a-deep-and |
| Repo | |
| Framework | |
Deep Learning of the Nonlinear Schrödinger Equation in Fiber-Optic Communications
| Title | Deep Learning of the Nonlinear Schrödinger Equation in Fiber-Optic Communications |
| Authors | Christian Häger, Henry D. Pfister |
| Abstract | An important problem in fiber-optic communications is to invert the nonlinear Schr"odinger equation in real time to reverse the deterministic effects of the channel. Interestingly, the popular split-step Fourier method (SSFM) leads to a computation graph that is reminiscent of a deep neural network. This observation allows one to leverage tools from machine learning to reduce complexity. In particular, the main disadvantage of the SSFM is that its complexity using M steps is at least M times larger than a linear equalizer. This is because the linear SSFM operator is a dense matrix. In previous work, truncation methods such as frequency sampling, wavelets, or least-squares have been used to obtain “cheaper” operators that can be implemented using filters. However, a large number of filter taps are typically required to limit truncation errors. For example, Ip and Kahn showed that for a 10 Gbaud signal and 2000 km optical link, a truncated SSFM with 25 steps would require 70-tap filters in each step and 100 times more operations than linear equalization. We find that, by jointly optimizing all filters with deep learning, the complexity can be reduced significantly for similar accuracy. Using optimized 5-tap and 3-tap filters in an alternating fashion, one requires only around 2-6 times the complexity of linear equalization, depending on the implementation. |
| Tasks | |
| Published | 2018-04-09 |
| URL | http://arxiv.org/abs/1804.02799v1 |
| http://arxiv.org/pdf/1804.02799v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-of-the-nonlinear-schrodinger |
| Repo | |
| Framework | |
Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising
| Title | Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising |
| Authors | Di Wu, Xiujun Chen, Xun Yang, Hao Wang, Qing Tan, Xiaoxun Zhang, Jian Xu, Kun Gai |
| Abstract | Real-time bidding (RTB) is an important mechanism in online display advertising, where a proper bid for each page view plays an essential role for good marketing results. Budget constrained bidding is a typical scenario in RTB where the advertisers hope to maximize the total value of the winning impressions under a pre-set budget constraint. However, the optimal bidding strategy is hard to be derived due to the complexity and volatility of the auction environment. To address these challenges, in this paper, we formulate budget constrained bidding as a Markov Decision Process and propose a model-free reinforcement learning framework to resolve the optimization problem. Our analysis shows that the immediate reward from environment is misleading under a critical resource constraint. Therefore, we innovate a reward function design methodology for the reinforcement learning problems with constraints. Based on the new reward design, we employ a deep neural network to learn the appropriate reward so that the optimal policy can be learned effectively. Different from the prior model-based work, which suffers from the scalability problem, our framework is easy to be deployed in large-scale industrial applications. The experimental evaluations demonstrate the effectiveness of our framework on large-scale real datasets. |
| Tasks | |
| Published | 2018-02-23 |
| URL | http://arxiv.org/abs/1802.08365v6 |
| http://arxiv.org/pdf/1802.08365v6.pdf | |
| PWC | https://paperswithcode.com/paper/budget-constrained-bidding-by-model-free |
| Repo | |
| Framework | |
A One-Sided Classification Toolkit with Applications in the Analysis of Spectroscopy Data
| Title | A One-Sided Classification Toolkit with Applications in the Analysis of Spectroscopy Data |
| Authors | Frank G. Glavin |
| Abstract | This dissertation investigates the use of one-sided classification algorithms in the application of separating hazardous chlorinated solvents from other materials, based on their Raman spectra. The experimentation is carried out using a new one-sided classification toolkit that was designed and developed from the ground up. In the one-sided classification paradigm, the objective is to separate elements of the target class from all outliers. These one-sided classifiers are generally chosen, in practice, when there is a deficiency of some sort in the training examples. Sometimes outlier examples can be rare, expensive to label, or even entirely absent. However, this author would like to note that they can be equally applicable when outlier examples are plentiful but nonetheless not statistically representative of the complete outlier concept. It is this scenario that is explicitly dealt with in this research work. In these circumstances, one-sided classifiers have been found to be more robust that conventional multi-class classifiers. The term “unexpected” outliers is introduced to represent outlier examples, encountered in the test set, that have been taken from a different distribution to the training set examples. These are examples that are a result of an inadequate representation of all possible outliers in the training set. It can often be impossible to fully characterise outlier examples given the fact that they can represent the immeasurable quantity of “everything else” that is not a target. The findings from this research have shown the potential drawbacks of using conventional multi-class classification algorithms when the test data come from a completely different distribution to that of the training samples. |
| Tasks | |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.06915v1 |
| http://arxiv.org/pdf/1806.06915v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-one-sided-classification-toolkit-with |
| Repo | |
| Framework | |
