Paper Group ANR 638
Light field super resolution through controlled micro-shifts of light field sensor. Extending Defensive Distillation. Consequentialist conditional cooperation in social dilemmas with imperfect information. Dynamic Multiscale Tree Learning Using Ensemble Strong Classifiers for Multi-label Segmentation of Medical Images with Lesions. Dual Supervised …
Light field super resolution through controlled micro-shifts of light field sensor
| Title | Light field super resolution through controlled micro-shifts of light field sensor |
| Authors | M. Umair Mukati, Bahadir K. Gunturk |
| Abstract | Light field cameras enable new capabilities, such as post-capture refocusing and aperture control, through capturing directional and spatial distribution of light rays in space. Micro-lens array based light field camera design is often preferred due to its light transmission efficiency, cost-effectiveness and compactness. One drawback of the micro-lens array based light field cameras is low spatial resolution due to the fact that a single sensor is shared to capture both spatial and angular information. To address the low spatial resolution issue, we present a light field imaging approach, where multiple light fields are captured and fused to improve the spatial resolution. For each capture, the light field sensor is shifted by a pre-determined fraction of a micro-lens size using an XY translation stage for optimal performance. |
| Tasks | Super-Resolution |
| Published | 2017-09-27 |
| URL | http://arxiv.org/abs/1709.09422v2 |
| http://arxiv.org/pdf/1709.09422v2.pdf | |
| PWC | https://paperswithcode.com/paper/light-field-super-resolution-through |
| Repo | |
| Framework | |
Extending Defensive Distillation
| Title | Extending Defensive Distillation |
| Authors | Nicolas Papernot, Patrick McDaniel |
| Abstract | Machine learning is vulnerable to adversarial examples: inputs carefully modified to force misclassification. Designing defenses against such inputs remains largely an open problem. In this work, we revisit defensive distillation—which is one of the mechanisms proposed to mitigate adversarial examples—to address its limitations. We view our results not only as an effective way of addressing some of the recently discovered attacks but also as reinforcing the importance of improved training techniques. |
| Tasks | |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05264v1 |
| http://arxiv.org/pdf/1705.05264v1.pdf | |
| PWC | https://paperswithcode.com/paper/extending-defensive-distillation |
| Repo | |
| Framework | |
Consequentialist conditional cooperation in social dilemmas with imperfect information
| Title | Consequentialist conditional cooperation in social dilemmas with imperfect information |
| Authors | Alexander Peysakhovich, Adam Lerer |
| Abstract | Social dilemmas, where mutual cooperation can lead to high payoffs but participants face incentives to cheat, are ubiquitous in multi-agent interaction. We wish to construct agents that cooperate with pure cooperators, avoid exploitation by pure defectors, and incentivize cooperation from the rest. However, often the actions taken by a partner are (partially) unobserved or the consequences of individual actions are hard to predict. We show that in a large class of games good strategies can be constructed by conditioning one’s behavior solely on outcomes (ie. one’s past rewards). We call this consequentialist conditional cooperation. We show how to construct such strategies using deep reinforcement learning techniques and demonstrate, both analytically and experimentally, that they are effective in social dilemmas beyond simple matrix games. We also show the limitations of relying purely on consequences and discuss the need for understanding both the consequences of and the intentions behind an action. |
| Tasks | |
| Published | 2017-10-19 |
| URL | http://arxiv.org/abs/1710.06975v2 |
| http://arxiv.org/pdf/1710.06975v2.pdf | |
| PWC | https://paperswithcode.com/paper/consequentialist-conditional-cooperation-in |
| Repo | |
| Framework | |
Dynamic Multiscale Tree Learning Using Ensemble Strong Classifiers for Multi-label Segmentation of Medical Images with Lesions
| Title | Dynamic Multiscale Tree Learning Using Ensemble Strong Classifiers for Multi-label Segmentation of Medical Images with Lesions |
| Authors | Samya Amiri, Mohamed Ali Mahjoub, Islem Rekik |
| Abstract | We introduce a dynamic multiscale tree (DMT) architecture that learns how to leverage the strengths of different existing classifiers for supervised multi-label image segmentation. Unlike previous works that simply aggregate or cascade classifiers for addressing image segmentation and labeling tasks, we propose to embed strong classifiers into a tree structure that allows bi-directional flow of information between its classifier nodes to gradually improve their performances. Our DMT is a generic classification model that inherently embeds different cascades of classifiers while enhancing learning transfer between them to boost up their classification accuracies. Specifically, each node in our DMT can nest a Structured Random Forest (SRF) classifier or a Bayesian Network (BN) classifier. The proposed SRF-BN DMT architecture has several appealing properties. First, while SRF operates at a patch-level (regular image region), BN operates at the super-pixel level (irregular image region), thereby enabling the DMT to integrate multi-level image knowledge in the learning process. Second, although BN is powerful in modeling dependencies between image elements (superpixels, edges) and their features, the learning of its structure and parameters is challenging. On the other hand, SRF may fail to accurately detect very irregular object boundaries. The proposed DMT robustly overcomes these limitations for both classifiers through the ascending and descending flow of contextual information between each parent node and its children nodes. Third, we train DMT using different scales, where we progressively decrease the patch and superpixel sizes as we go deeper along the tree edges nearing its leaf nodes. Last, DMT demonstrates its outperformance in comparison to several state-of-the-art segmentation methods for multi-labeling of brain images with gliomas. |
| Tasks | Semantic Segmentation |
| Published | 2017-09-05 |
| URL | http://arxiv.org/abs/1709.01602v1 |
| http://arxiv.org/pdf/1709.01602v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-multiscale-tree-learning-using |
| Repo | |
| Framework | |
Dual Supervised Learning
| Title | Dual Supervised Learning |
| Authors | Yingce Xia, Tao Qin, Wei Chen, Jiang Bian, Nenghai Yu, Tie-Yan Liu |
| Abstract | Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have intrinsic connections with each other due to the probabilistic correlation between their models. This connection is, however, not effectively utilized today, since people usually train the models of two dual tasks separately and independently. In this work, we propose training the models of two dual tasks simultaneously, and explicitly exploiting the probabilistic correlation between them to regularize the training process. For ease of reference, we call the proposed approach \emph{dual supervised learning}. We demonstrate that dual supervised learning can improve the practical performances of both tasks, for various applications including machine translation, image processing, and sentiment analysis. |
| Tasks | Image Classification, Image Generation, Machine Translation, Sentiment Analysis, Speech Recognition |
| Published | 2017-07-03 |
| URL | http://arxiv.org/abs/1707.00415v1 |
| http://arxiv.org/pdf/1707.00415v1.pdf | |
| PWC | https://paperswithcode.com/paper/dual-supervised-learning |
| Repo | |
| Framework | |
Learning a visuomotor controller for real world robotic grasping using simulated depth images
| Title | Learning a visuomotor controller for real world robotic grasping using simulated depth images |
| Authors | Ulrich Viereck, Andreas ten Pas, Kate Saenko, Robert Platt |
| Abstract | We want to build robots that are useful in unstructured real world applications, such as doing work in the household. Grasping in particular is an important skill in this domain, yet it remains a challenge. One of the key hurdles is handling unexpected changes or motion in the objects being grasped and kinematic noise or other errors in the robot. This paper proposes an approach to learning a closed-loop controller for robotic grasping that dynamically guides the gripper to the object. We use a wrist-mounted sensor to acquire depth images in front of the gripper and train a convolutional neural network to learn a distance function to true grasps for grasp configurations over an image. The training sensor data is generated in simulation, a major advantage over previous work that uses real robot experience, which is costly to obtain. Despite being trained in simulation, our approach works well on real noisy sensor images. We compare our controller in simulated and real robot experiments to a strong baseline for grasp pose detection, and find that our approach significantly outperforms the baseline in the presence of kinematic noise, perceptual errors and disturbances of the object during grasping. |
| Tasks | Robotic Grasping |
| Published | 2017-06-14 |
| URL | http://arxiv.org/abs/1706.04652v3 |
| http://arxiv.org/pdf/1706.04652v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-visuomotor-controller-for-real |
| Repo | |
| Framework | |
Recovery of damped exponentials using structured low rank matrix completion
| Title | Recovery of damped exponentials using structured low rank matrix completion |
| Authors | Arvind Balachandrasekaran, Vincent Magnotta, Mathews Jacob |
| Abstract | We introduce a structured low rank matrix completion algorithm to recover a series of images from their under-sampled measurements, where the signal along the parameter dimension at every pixel is described by a linear combination of exponentials. We exploit the exponential behavior of the signal at every pixel, along with the spatial smoothness of the exponential parameters to derive an annihilation relation in the Fourier domain. This relation translates to a low-rank property on a structured matrix constructed from the Fourier samples. We enforce the low rank property of the structured matrix as a regularization prior to recover the images. Since the direct use of current low rank matrix recovery schemes to this problem is associated with high computational complexity and memory demand, we adopt an iterative re-weighted least squares (IRLS) algorithm, which facilitates the exploitation of the convolutional structure of the matrix. Novel approximations involving two dimensional Fast Fourier Transforms (FFT) are introduced to drastically reduce the memory demand and computational complexity, which facilitates the extension of structured low rank methods to large scale three dimensional problems. We demonstrate our algorithm in the MR parameter mapping setting and show improvement over the state-of-the-art methods. |
| Tasks | Low-Rank Matrix Completion, Matrix Completion |
| Published | 2017-04-14 |
| URL | http://arxiv.org/abs/1704.04511v2 |
| http://arxiv.org/pdf/1704.04511v2.pdf | |
| PWC | https://paperswithcode.com/paper/recovery-of-damped-exponentials-using |
| Repo | |
| Framework | |
Dialogue Act Recognition via CRF-Attentive Structured Network
| Title | Dialogue Act Recognition via CRF-Attentive Structured Network |
| Authors | Zheqian Chen, Rongqin Yang, Zhou Zhao, Deng Cai, Xiaofei He |
| Abstract | Dialogue Act Recognition (DAR) is a challenging problem in dialogue interpretation, which aims to attach semantic labels to utterances and characterize the speaker’s intention. Currently, many existing approaches formulate the DAR problem ranging from multi-classification to structured prediction, which suffer from handcrafted feature extensions and attentive contextual structural dependencies. In this paper, we consider the problem of DAR from the viewpoint of extending richer Conditional Random Field (CRF) structural dependencies without abandoning end-to-end training. We incorporate hierarchical semantic inference with memory mechanism on the utterance modeling. We then extend structured attention network to the linear-chain conditional random field layer which takes into account both contextual utterances and corresponding dialogue acts. The extensive experiments on two major benchmark datasets Switchboard Dialogue Act (SWDA) and Meeting Recorder Dialogue Act (MRDA) datasets show that our method achieves better performance than other state-of-the-art solutions to the problem. It is a remarkable fact that our method is nearly close to the human annotator’s performance on SWDA within 2% gap. |
| Tasks | Dialogue Act Classification, Dialogue Interpretation, Structured Prediction |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05568v1 |
| http://arxiv.org/pdf/1711.05568v1.pdf | |
| PWC | https://paperswithcode.com/paper/dialogue-act-recognition-via-crf-attentive |
| Repo | |
| Framework | |
Experimental learning of quantum states
| Title | Experimental learning of quantum states |
| Authors | Andrea Rocchetto, Scott Aaronson, Simone Severini, Gonzalo Carvacho, Davide Poderini, Iris Agresti, Marco Bentivegna, Fabio Sciarrino |
| Abstract | The number of parameters describing a quantum state is well known to grow exponentially with the number of particles. This scaling clearly limits our ability to do tomography to systems with no more than a few qubits and has been used to argue against the universal validity of quantum mechanics itself. However, from a computational learning theory perspective, it can be shown that, in a probabilistic setting, quantum states can be approximately learned using only a linear number of measurements. Here we experimentally demonstrate this linear scaling in optical systems with up to 6 qubits. Our results highlight the power of computational learning theory to investigate quantum information, provide the first experimental demonstration that quantum states can be “probably approximately learned” with access to a number of copies of the state that scales linearly with the number of qubits, and pave the way to probing quantum states at new, larger scales. |
| Tasks | |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1712.00127v1 |
| http://arxiv.org/pdf/1712.00127v1.pdf | |
| PWC | https://paperswithcode.com/paper/experimental-learning-of-quantum-states |
| Repo | |
| Framework | |
Block Compressive Sensing of Image and Video with Nonlocal Lagrangian Multiplier and Patch-based Sparse Representation
| Title | Block Compressive Sensing of Image and Video with Nonlocal Lagrangian Multiplier and Patch-based Sparse Representation |
| Authors | Trinh Van Chien, Khanh Quoc Dinh, Byeungwoo Jeon, Martin Burger |
| Abstract | Although block compressive sensing (BCS) makes it tractable to sense large-sized images and video, its recovery performance has yet to be significantly improved because its recovered images or video usually suffer from blurred edges, loss of details, and high-frequency oscillatory artifacts, especially at a low subrate. This paper addresses these problems by designing a modified total variation technique that employs multi-block gradient processing, a denoised Lagrangian multiplier, and patch-based sparse representation. In the case of video, the proposed recovery method is able to exploit both spatial and temporal similarities. Simulation results confirm the improved performance of the proposed method for compressive sensing of images and video in terms of both objective and subjective qualities. |
| Tasks | Compressive Sensing |
| Published | 2017-03-15 |
| URL | http://arxiv.org/abs/1703.05130v1 |
| http://arxiv.org/pdf/1703.05130v1.pdf | |
| PWC | https://paperswithcode.com/paper/block-compressive-sensing-of-image-and-video |
| Repo | |
| Framework | |
Evaluating and Modelling Hanabi-Playing Agents
| Title | Evaluating and Modelling Hanabi-Playing Agents |
| Authors | Joseph Walton-Rivers, Piers R. Williams, Richard Bartle, Diego Perez-Liebana, Simon M. Lucas |
| Abstract | Agent modelling involves considering how other agents will behave, in order to influence your own actions. In this paper, we explore the use of agent modelling in the hidden-information, collaborative card game Hanabi. We implement a number of rule-based agents, both from the literature and of our own devising, in addition to an Information Set Monte Carlo Tree Search (IS-MCTS) agent. We observe poor results from IS-MCTS, so construct a new, predictor version that uses a model of the agents with which it is paired. We observe a significant improvement in game-playing strength from this agent in comparison to IS-MCTS, resulting from its consideration of what the other agents in a game would do. In addition, we create a flawed rule-based agent to highlight the predictor’s capabilities with such an agent. |
| Tasks | Game of Hanabi |
| Published | 2017-04-24 |
| URL | http://arxiv.org/abs/1704.07069v1 |
| http://arxiv.org/pdf/1704.07069v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-and-modelling-hanabi-playing |
| Repo | |
| Framework | |
Graph Structure Learning from Unlabeled Data for Event Detection
| Title | Graph Structure Learning from Unlabeled Data for Event Detection |
| Authors | Sriram Somanchi, Daniel B. Neill |
| Abstract | Processes such as disease propagation and information diffusion often spread over some latent network structure which must be learned from observation. Given a set of unlabeled training examples representing occurrences of an event type of interest (e.g., a disease outbreak), our goal is to learn a graph structure that can be used to accurately detect future events of that type. Motivated by new theoretical results on the consistency of constrained and unconstrained subset scans, we propose a novel framework for learning graph structure from unlabeled data by comparing the most anomalous subsets detected with and without the graph constraints. Our framework uses the mean normalized log-likelihood ratio score to measure the quality of a graph structure, and efficiently searches for the highest-scoring graph structure. Using simulated disease outbreaks injected into real-world Emergency Department data from Allegheny County, we show that our method learns a structure similar to the true underlying graph, but enables faster and more accurate detection. |
| Tasks | |
| Published | 2017-01-05 |
| URL | http://arxiv.org/abs/1701.01470v1 |
| http://arxiv.org/pdf/1701.01470v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-structure-learning-from-unlabeled-data |
| Repo | |
| Framework | |
Optimal choice: new machine learning problem and its solution
| Title | Optimal choice: new machine learning problem and its solution |
| Authors | Marina Sapir |
| Abstract | The task of learning to pick a single preferred example out a finite set of examples, an “optimal choice problem”, is a supervised machine learning problem with complex, structured input. Problems of optimal choice emerge often in various practical applications. We formalize the problem, show that it does not satisfy the assumptions of statistical learning theory, yet it can be solved efficiently in some cases. We propose two approaches to solve the problem. Both of them reach good solutions on real life data from a signal processing application. |
| Tasks | |
| Published | 2017-06-26 |
| URL | http://arxiv.org/abs/1706.08439v2 |
| http://arxiv.org/pdf/1706.08439v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-choice-new-machine-learning-problem |
| Repo | |
| Framework | |
Improving Landmark Localization with Semi-Supervised Learning
| Title | Improving Landmark Localization with Semi-Supervised Learning |
| Authors | Sina Honari, Pavlo Molchanov, Stephen Tyree, Pascal Vincent, Christopher Pal, Jan Kautz |
| Abstract | We present two techniques to improve landmark localization in images from partially annotated datasets. Our primary goal is to leverage the common situation where precise landmark locations are only provided for a small data subset, but where class labels for classification or regression tasks related to the landmarks are more abundantly available. First, we propose the framework of sequential multitasking and explore it here through an architecture for landmark localization where training with class labels acts as an auxiliary signal to guide the landmark localization on unlabeled data. A key aspect of our approach is that errors can be backpropagated through a complete landmark localization model. Second, we propose and explore an unsupervised learning technique for landmark localization based on having a model predict equivariant landmarks with respect to transformations applied to the image. We show that these techniques, improve landmark prediction considerably and can learn effective detectors even when only a small fraction of the dataset has landmark labels. We present results on two toy datasets and four real datasets, with hands and faces, and report new state-of-the-art on two datasets in the wild, e.g. with only 5% of labeled images we outperform previous state-of-the-art trained on the AFLW dataset. |
| Tasks | |
| Published | 2017-09-05 |
| URL | http://arxiv.org/abs/1709.01591v7 |
| http://arxiv.org/pdf/1709.01591v7.pdf | |
| PWC | https://paperswithcode.com/paper/improving-landmark-localization-with-semi |
| Repo | |
| Framework | |
The Fog of War: A Machine Learning Approach to Forecasting Weather on Mars
| Title | The Fog of War: A Machine Learning Approach to Forecasting Weather on Mars |
| Authors | Daniele Bellutta |
| Abstract | For over a decade, scientists at NASA’s Jet Propulsion Laboratory (JPL) have been recording measurements from the Martian surface as a part of the Mars Exploration Rovers mission. One quantity of interest has been the opacity of Mars’s atmosphere for its importance in day-to-day estimations of the amount of power available to the rover from its solar arrays. This paper proposes the use of neural networks as a method for forecasting Martian atmospheric opacity that is more effective than the current empirical model. The more accurate prediction provided by these networks would allow operators at JPL to make more accurate predictions of the amount of energy available to the rover when they plan activities for coming sols. |
| Tasks | |
| Published | 2017-06-26 |
| URL | http://arxiv.org/abs/1706.08915v1 |
| http://arxiv.org/pdf/1706.08915v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-fog-of-war-a-machine-learning-approach-to |
| Repo | |
| Framework | |
