Paper Group ANR 1036
Fast Object Class Labelling via Speech. Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention. DragonPaint: Rule based bootstrapping for small data with an application to cartoon coloring. Real-Time Inference of User Types to Assist with More Inclusive Social Media Activism Campaigns. Relating Leverage S …
Fast Object Class Labelling via Speech
| Title | Fast Object Class Labelling via Speech |
| Authors | Michael Gygli, Vittorio Ferrari |
| Abstract | Object class labelling is the task of annotating images with labels on the presence or absence of objects from a given class vocabulary. Simply asking one yes/no question per class, however, has a cost that is linear in the vocabulary size and is thus inefficient for large vocabularies. Modern approaches rely on a hierarchical organization of the vocabulary to reduce annotation time, but remain expensive (several minutes per image for the 200 classes in ILSVRC). Instead, we propose a new interface where classes are annotated via speech. Speaking is fast and allows for direct access to the class name, without searching through a list or hierarchy. As additional advantages, annotators can simultaneously speak and scan the image for objects, the interface can be kept extremely simple, and using it requires less mouse movement. As annotators using our interface should only say words from a given class vocabulary, we propose a dedicated task that trains them to do so. Through experiments on COCO and ILSVRC, we show our method yields high-quality annotations at 2.3x - 14.9x less annotation time than existing methods. |
| Tasks | |
| Published | 2018-11-23 |
| URL | http://arxiv.org/abs/1811.09461v2 |
| http://arxiv.org/pdf/1811.09461v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-object-class-labelling-via-speech |
| Repo | |
| Framework | |
Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention
| Title | Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention |
| Authors | Honglun Zhang, Wenqing Chen, Jidong Tian, Yongkun Wang, Yaohui Jin |
| Abstract | Recently unpaired multi-domain image-to-image translation has attracted great interests and obtained remarkable progress, where a label vector is utilized to indicate multi-domain information. In this paper, we propose SAT (Show, Attend and Translate), an unified and explainable generative adversarial network equipped with visual attention that can perform unpaired image-to-image translation for multiple domains. By introducing an action vector, we treat the original translation tasks as problems of arithmetic addition and subtraction. Visual attention is applied to guarantee that only the regions relevant to the target domains are translated. Extensive experiments on a facial attribute dataset demonstrate the superiority of our approach and the generated attention masks better explain what SAT attends when translating images. |
| Tasks | Image-to-Image Translation |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07483v2 |
| http://arxiv.org/pdf/1811.07483v2.pdf | |
| PWC | https://paperswithcode.com/paper/show-attend-and-translate-unpaired-multi |
| Repo | |
| Framework | |
DragonPaint: Rule based bootstrapping for small data with an application to cartoon coloring
| Title | DragonPaint: Rule based bootstrapping for small data with an application to cartoon coloring |
| Authors | K. Gretchen Greene |
| Abstract | In this paper, we confront the problem of deep learning’s big labeled data requirements, offer a rule based strategy for extreme augmentation of small data sets and apply that strategy with the image to image translation model by Isola et al. (2016) to automate cel style cartoon coloring with very limited training data. While our experimental results using geometric rules and transformations demonstrate the performance of our methods on an image translation task with industry applications in art, design and animation, we also propose the use of rules on partial data sets as a generalizable small data strategy, potentially applicable across data types and domains. |
| Tasks | Image-to-Image Translation |
| Published | 2018-11-07 |
| URL | http://arxiv.org/abs/1811.03151v1 |
| http://arxiv.org/pdf/1811.03151v1.pdf | |
| PWC | https://paperswithcode.com/paper/dragonpaint-rule-based-bootstrapping-for |
| Repo | |
| Framework | |
Real-Time Inference of User Types to Assist with More Inclusive Social Media Activism Campaigns
| Title | Real-Time Inference of User Types to Assist with More Inclusive Social Media Activism Campaigns |
| Authors | Habib Karbasian, Hemant Purohit, Rajat Handa, Aqdas Malik, Aditya Johri |
| Abstract | Social media provides a mechanism for people to engage with social causes across a range of issues. It also provides a strategic tool to those looking to advance a cause to exchange, promote or publicize their ideas. In such instances, AI can be either an asset if used appropriately or a barrier. One of the key issues for a workforce diversity campaign is to understand in real-time who is participating - specifically, whether the participants are individuals or organizations, and in case of individuals, whether they are male or female. In this paper, we present a study to demonstrate a case for AI for social good that develops a model to infer in real-time the different user types participating in a cause-driven hashtag campaign on Twitter, ILookLikeAnEngineer (ILLAE). A generic framework is devised to classify a Twitter user into three classes: organization, male and female in a real-time manner. The framework is tested against two datasets (ILLAE and a general dataset) and outperforms the baseline binary classifiers for categorizing organization/individual and male/female. The proposed model can be applied to future social cause-driven campaigns to get real-time insights on the macro-level social behavior of participants. |
| Tasks | |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09304v1 |
| http://arxiv.org/pdf/1804.09304v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-inference-of-user-types-to-assist |
| Repo | |
| Framework | |
Relating Leverage Scores and Density using Regularized Christoffel Functions
| Title | Relating Leverage Scores and Density using Regularized Christoffel Functions |
| Authors | Edouard Pauwels, Francis Bach, Jean-Philippe Vert |
| Abstract | Statistical leverage scores emerged as a fundamental tool for matrix sketching and column sampling with applications to low rank approximation, regression, random feature learning and quadrature. Yet, the very nature of this quantity is barely understood. Borrowing ideas from the orthogonal polynomial literature, we introduce the regularized Christoffel function associated to a positive definite kernel. This uncovers a variational formulation for leverage scores for kernel methods and allows to elucidate their relationships with the chosen kernel as well as population density. Our main result quantitatively describes a decreasing relation between leverage score and population density for a broad class of kernels on Euclidean spaces. Numerical simulations support our findings. |
| Tasks | |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.07943v2 |
| http://arxiv.org/pdf/1805.07943v2.pdf | |
| PWC | https://paperswithcode.com/paper/relating-leverage-scores-and-density-using |
| Repo | |
| Framework | |
Ensemble-based Adaptive Single-shot Multi-box Detector
| Title | Ensemble-based Adaptive Single-shot Multi-box Detector |
| Authors | Viral Thakar, Walid Ahmed, Mohammad M Soltani, Jia Yuan Yu |
| Abstract | We propose two improvements to the SSD—single shot multibox detector. First, we propose an adaptive approach for default box selection in SSD. This uses data to reduce the uncertainty in the selection of best aspect ratios for the default boxes and improves performance of SSD for datasets containing small and complex objects (e.g., equipments at construction sites). We do so by finding the distribution of aspect ratios of the given training dataset, and then choosing representative values. Secondly, we propose an ensemble algorithm, using SSD as components, which improves the performance of SSD, especially for small amount of training datasets. Compared to the conventional SSD algorithm, adaptive box selection improves mean average precision by 3%, while ensemble-based SSD improves it by 8%. |
| Tasks | |
| Published | 2018-08-17 |
| URL | http://arxiv.org/abs/1808.05727v1 |
| http://arxiv.org/pdf/1808.05727v1.pdf | |
| PWC | https://paperswithcode.com/paper/ensemble-based-adaptive-single-shot-multi-box |
| Repo | |
| Framework | |
Motion Guided LIDAR-camera Self-calibration and Accelerated Depth Upsampling
| Title | Motion Guided LIDAR-camera Self-calibration and Accelerated Depth Upsampling |
| Authors | Juan Castorena, Gint Puskorius, Gaurav Pandey |
| Abstract | In this work we describe a novel motion guided method for targetless self-calibration of a LiDAR and camera and use the re-projection of LiDAR points onto the image reference frame for real-time depth upsampling. The calibration parameters are estimated by optimizing an objective function that penalizes distances between 2D and re-projected 3D motion vectors obtained from time-synchronized image and point cloud sequences. For upsampling, we propose a simple, yet effective and time efficient formulation that minimizes depth gradients subject to an equality constraint involving the LiDAR measurements. We test our algorithms on real data from urban environments and demonstrate that our two methods are effective and suitable to mobile robotics and autonomous vehicle applications imposing real-time requirements. |
| Tasks | Calibration, Depth Estimation, Super-Resolution |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10681v2 |
| http://arxiv.org/pdf/1803.10681v2.pdf | |
| PWC | https://paperswithcode.com/paper/motion-guided-lidar-camera-autocalibration |
| Repo | |
| Framework | |
Surrogate Outcomes and Transportability
| Title | Surrogate Outcomes and Transportability |
| Authors | Santtu Tikka, Juha Karvanen |
| Abstract | Identification of causal effects is one of the most fundamental tasks of causal inference. We consider an identifiability problem where some experimental and observational data are available but neither data alone is sufficient for the identification of the causal effect of interest. Instead of the outcome of interest, surrogate outcomes are measured in the experiments. This problem is a generalization of identifiability using surrogate experiments and we label it as surrogate outcome identifiability. We show that the concept of transportability provides a sufficient criteria for determining surrogate outcome identifiability for a large class of queries. |
| Tasks | Causal Inference |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07172v4 |
| http://arxiv.org/pdf/1806.07172v4.pdf | |
| PWC | https://paperswithcode.com/paper/surrogate-outcomes-and-transportability |
| Repo | |
| Framework | |
Generative Sensing: Transforming Unreliable Sensor Data for Reliable Recognition
| Title | Generative Sensing: Transforming Unreliable Sensor Data for Reliable Recognition |
| Authors | Lina Karam, Tejas Borkar, Yu Cao, Junseok Chae |
| Abstract | This paper introduces a deep learning enabled generative sensing framework which integrates low-end sensors with computational intelligence to attain a high recognition accuracy on par with that attained with high-end sensors. The proposed generative sensing framework aims at transforming low-end, low-quality sensor data into higher quality sensor data in terms of achieved classification accuracy. The low-end data can be transformed into higher quality data of the same modality or into data of another modality. Different from existing methods for image generation, the proposed framework is based on discriminative models and targets to maximize the recognition accuracy rather than a similarity measure. This is achieved through the introduction of selective feature regeneration in a deep neural network (DNN). The proposed generative sensing will essentially transform low-quality sensor data into high-quality information for robust perception. Results are presented to illustrate the performance of the proposed framework. |
| Tasks | Image Generation |
| Published | 2018-01-08 |
| URL | http://arxiv.org/abs/1801.02684v1 |
| http://arxiv.org/pdf/1801.02684v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-sensing-transforming-unreliable |
| Repo | |
| Framework | |
Hierarchical correlation reconstruction with missing data, for example for biology-inspired neuron
| Title | Hierarchical correlation reconstruction with missing data, for example for biology-inspired neuron |
| Authors | Jarek Duda |
| Abstract | Machine learning often needs to model density from a multidimensional data sample, including correlations between coordinates. Additionally, we often have missing data case: that data points can miss values for some of coordinates. This article adapts rapid parametric density estimation approach for this purpose: modelling density as a linear combination of orthonormal functions, for which $L^2$ optimization says that (independently) estimated coefficient for a given function is just average over the sample of value of this function. Hierarchical correlation reconstruction first models probability density for each separate coordinate using all its appearances in data sample, then adds corrections from independently modelled pairwise correlations using all samples having both coordinates, and so on independently adding correlations for growing numbers of variables using often decreasing evidence in data sample. A basic application of such modelled multidimensional density can be imputation of missing coordinates: by inserting known coordinates to the density, and taking expected values for the missing coordinates, or even their entire joint probability distribution. Presented method can be compared with cascade correlations approach, offering several advantages in flexibility and accuracy. It can be also used as artificial neuron: maximizing prediction capabilities for only local behavior - modelling and predicting local connections. |
| Tasks | Density Estimation, Imputation |
| Published | 2018-04-17 |
| URL | http://arxiv.org/abs/1804.06218v4 |
| http://arxiv.org/pdf/1804.06218v4.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-correlation-reconstruction-with |
| Repo | |
| Framework | |
Polar Feature Based Deep Architectures for Automatic Modulation Classification Considering Channel Fading
| Title | Polar Feature Based Deep Architectures for Automatic Modulation Classification Considering Channel Fading |
| Authors | Chieh-Fang Teng, Ching-Chun Liao, Chun-Hsiang Chen, An-Yeu Wu |
| Abstract | To develop intelligent receivers, automatic modulation classification (AMC) plays an important role for better spectrum utilization. The emerging deep learning (DL) technique has received much attention in AMC due to its superior performance in classifying data with deep structure. In this work, a novel polar-based deep learning architecture with channel compensation network (CCN) is proposed. Our test results show that learning features from polar domain (r-theta) can improve recognition accuracy by 5% and reduce training overhead by 48%. Besides, the proposed CCN is also robust to channel fading, such as amplitude and phase offsets, and can improve the recognition accuracy by 14% under practical channel environments. |
| Tasks | |
| Published | 2018-10-04 |
| URL | http://arxiv.org/abs/1810.02027v2 |
| http://arxiv.org/pdf/1810.02027v2.pdf | |
| PWC | https://paperswithcode.com/paper/polar-feature-based-deep-architectures-for |
| Repo | |
| Framework | |
Ghost imaging with the human eye
| Title | Ghost imaging with the human eye |
| Authors | Alessandro Boccolini, Alessandro Fedrizzi, Daniele Faccio |
| Abstract | Computational ghost imaging relies on the decomposition of an image into patterns that are summed together with weights that measure the overlap of each pattern with the scene being imaged. These tasks rely on a computer. Here we demonstrate that the computational integration can be performed directly with the human eye. We use this human ghost imaging technique to evaluate the temporal response of the eye and establish the image persistence time to be around 20 ms followed by a further 20 ms exponential decay. These persistence times are in agreement with previous studies but can now potentially be extended to include a more precise characterisation of visual stimuli and provide a new experimental tool for the study of visual perception. |
| Tasks | |
| Published | 2018-08-13 |
| URL | http://arxiv.org/abs/1808.05137v1 |
| http://arxiv.org/pdf/1808.05137v1.pdf | |
| PWC | https://paperswithcode.com/paper/ghost-imaging-with-the-human-eye |
| Repo | |
| Framework | |
Exact Guarantees on the Absence of Spurious Local Minima for Non-negative Rank-1 Robust Principal Component Analysis
| Title | Exact Guarantees on the Absence of Spurious Local Minima for Non-negative Rank-1 Robust Principal Component Analysis |
| Authors | Salar Fattahi, Somayeh Sojoudi |
| Abstract | This work is concerned with the non-negative rank-1 robust principal component analysis (RPCA), where the goal is to recover the dominant non-negative principal components of a data matrix precisely, where a number of measurements could be grossly corrupted with sparse and arbitrary large noise. Most of the known techniques for solving the RPCA rely on convex relaxation methods by lifting the problem to a higher dimension, which significantly increase the number of variables. As an alternative, the well-known Burer-Monteiro approach can be used to cast the RPCA as a non-convex and non-smooth $\ell_1$ optimization problem with a significantly smaller number of variables. In this work, we show that the low-dimensional formulation of the symmetric and asymmetric positive rank-1 RPCA based on the Burer-Monteiro approach has benign landscape, i.e., 1) it does not have any spurious local solution, 2) has a unique global solution, and 3) its unique global solution coincides with the true components. An implication of this result is that simple local search algorithms are guaranteed to achieve a zero global optimality gap when directly applied to the low-dimensional formulation. Furthermore, we provide strong deterministic and probabilistic guarantees for the exact recovery of the true principal components. In particular, it is shown that a constant fraction of the measurements could be grossly corrupted and yet they would not create any spurious local solution. |
| Tasks | |
| Published | 2018-12-30 |
| URL | https://arxiv.org/abs/1812.11466v2 |
| https://arxiv.org/pdf/1812.11466v2.pdf | |
| PWC | https://paperswithcode.com/paper/exact-guarantees-on-the-absence-of-spurious |
| Repo | |
| Framework | |
Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL
| Title | Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL |
| Authors | Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor |
| Abstract | Deep reinforcement learning (DRL) has achieved great successes in recent years with the help of novel methods and higher compute power. However, there are still several challenges to be addressed such as convergence to locally optimal policies and long training times. In this paper, firstly, we augment Asynchronous Advantage Actor-Critic (A3C) method with a novel self-supervised auxiliary task, i.e. \emph{Terminal Prediction}, measuring temporal closeness to terminal states, namely A3C-TP. Secondly, we propose a new framework where planning algorithms such as Monte Carlo tree search or other sources of (simulated) demonstrators can be integrated to asynchronous distributed DRL methods. Compared to vanilla A3C, our proposed methods both learn faster and converge to better policies on a two-player mini version of the Pommerman game. |
| Tasks | |
| Published | 2018-11-30 |
| URL | http://arxiv.org/abs/1812.00045v1 |
| http://arxiv.org/pdf/1812.00045v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-monte-carlo-tree-search-as-a |
| Repo | |
| Framework | |
An Integrated Development Environment for Planning Domain Modeling
| Title | An Integrated Development Environment for Planning Domain Modeling |
| Authors | Yuncong Li, Hankz Hankui Zhuo |
| Abstract | In order to make the task, description of planning domains and problems, more comprehensive for non-experts in planning, the visual representation has been used in planning domain modeling in recent years. However, current knowledge engineering tools with visual modeling, like itSIMPLE (Vaquero et al. 2012) and VIZ (Vodr'a\v{z}ka and Chrpa 2010), are less efficient than the traditional method of hand-coding by a PDDL expert using a text editor, and rarely involved in finetuning planning domains depending on the plan validation. Aim at this, we present an integrated development environment KAVI for planning domain modeling inspired by itSIMPLE and VIZ. KAVI using an abstract domain knowledge base to improve the efficiency of planning domain visual modeling. By integrating planners and a plan validator, KAVI proposes a method to fine-tune planning domains based on the plan validation. |
| Tasks | |
| Published | 2018-04-19 |
| URL | http://arxiv.org/abs/1804.07013v1 |
| http://arxiv.org/pdf/1804.07013v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-integrated-development-environment-for |
| Repo | |
| Framework | |
