Paper Group ANR 676
Curiosity-driven reinforcement learning with homeostatic regulation. A Note on Coding and Standardization of Categorical Variables in (Sparse) Group Lasso Regression. Open Information Extraction on Scientific Text: An Evaluation. Accuracy, Uncertainty, and Adaptability of Automatic Myocardial ASL Segmentation using Deep CNN. Deep-RBF Networks Revis …
Curiosity-driven reinforcement learning with homeostatic regulation
| Title | Curiosity-driven reinforcement learning with homeostatic regulation |
| Authors | Ildefons Magrans de Abril, Ryota Kanai |
| Abstract | We propose a curiosity reward based on information theory principles and consistent with the animal instinct to maintain certain critical parameters within a bounded range. Our experimental validation shows the added value of the additional homeostatic drive to enhance the overall information gain of a reinforcement learning agent interacting with a complex environment using continuous actions. Our method builds upon two ideas: i) To take advantage of a new Bellman-like equation of information gain and ii) to simplify the computation of the local rewards by avoiding the approximation of complex distributions over continuous states and actions. |
| Tasks | |
| Published | 2018-01-23 |
| URL | http://arxiv.org/abs/1801.07440v2 |
| http://arxiv.org/pdf/1801.07440v2.pdf | |
| PWC | https://paperswithcode.com/paper/curiosity-driven-reinforcement-learning-with |
| Repo | |
| Framework | |
A Note on Coding and Standardization of Categorical Variables in (Sparse) Group Lasso Regression
| Title | A Note on Coding and Standardization of Categorical Variables in (Sparse) Group Lasso Regression |
| Authors | Felicitas J. Detmer, Martin Slawski |
| Abstract | Categorical regressor variables are usually handled by introducing a set of indicator variables, and imposing a linear constraint to ensure identifiability in the presence of an intercept, or equivalently, using one of various coding schemes. As proposed in Yuan and Lin [J. R. Statist. Soc. B, 68 (2006), 49-67], the group lasso is a natural and computationally convenient approach to perform variable selection in settings with categorical covariates. As pointed out by Simon and Tibshirani [Stat. Sin., 22 (2011), 983-1001], “standardization” by means of block-wise orthonormalization of column submatrices each corresponding to one group of variables can substantially boost performance. In this note, we study the aspect of standardization for the special case of categorical predictors in detail. The main result is that orthonormalization is not required; column-wise scaling of the design matrix followed by re-scaling and centering of the coefficients is shown to have exactly the same effect. Similar reductions can be achieved in the case of interactions. The extension to the so-called sparse group lasso, which additionally promotes within-group sparsity, is considered as well. The importance of proper standardization is illustrated via extensive simulations. |
| Tasks | |
| Published | 2018-05-17 |
| URL | http://arxiv.org/abs/1805.06915v1 |
| http://arxiv.org/pdf/1805.06915v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-note-on-coding-and-standardization-of |
| Repo | |
| Framework | |
Open Information Extraction on Scientific Text: An Evaluation
| Title | Open Information Extraction on Scientific Text: An Evaluation |
| Authors | Paul Groth, Michael Lauruhn, Antony Scerri, Ron Daniel Jr |
| Abstract | Open Information Extraction (OIE) is the task of the unsupervised creation of structured information from text. OIE is often used as a starting point for a number of downstream tasks including knowledge base construction, relation extraction, and question answering. While OIE methods are targeted at being domain independent, they have been evaluated primarily on newspaper, encyclopedic or general web text. In this article, we evaluate the performance of OIE on scientific texts originating from 10 different disciplines. To do so, we use two state-of-the-art OIE systems applying a crowd-sourcing approach. We find that OIE systems perform significantly worse on scientific text than encyclopedic text. We also provide an error analysis and suggest areas of work to reduce errors. Our corpus of sentences and judgments are made available. |
| Tasks | Open Information Extraction, Question Answering, Relation Extraction |
| Published | 2018-02-15 |
| URL | http://arxiv.org/abs/1802.05574v2 |
| http://arxiv.org/pdf/1802.05574v2.pdf | |
| PWC | https://paperswithcode.com/paper/open-information-extraction-on-scientific |
| Repo | |
| Framework | |
Accuracy, Uncertainty, and Adaptability of Automatic Myocardial ASL Segmentation using Deep CNN
| Title | Accuracy, Uncertainty, and Adaptability of Automatic Myocardial ASL Segmentation using Deep CNN |
| Authors | Hung P. Do, Yi Guo, Andrew J. Yoon, Krishna S. Nayak |
| Abstract | PURPOSE: To apply deep CNN to the segmentation task in myocardial arterial spin labeled (ASL) perfusion imaging and to develop methods that measure uncertainty and that adapt the CNN model to a specific false positive vs. false negative tradeoff. METHODS: The Monte Carlo dropout (MCD) U-Net was trained on data from 22 subjects and tested on data from 6 heart transplant recipients. Manual segmentation and regional myocardial blood flow (MBF) were available for comparison. We consider two global uncertainty measures, named Dice Uncertainty and MCD Uncertainty, which were calculated with and without the use of manual segmentation, respectively. Tversky loss function with a hyperparameter $\beta$ was used to adapt the model to a specific false positive vs. false negative tradeoff. RESULTS: The MCD U-Net achieved Dice coefficient of mean(std) = 0.91(0.04) on the test set. MBF measured using automatic segmentations was highly correlated to that measured using the manual segmentation ($R^2$ = 0.96). Dice Uncertainty and MCD Uncertainty were in good agreement ($R^2$ = 0.64). As $\beta$ increased, the false positive rate systematically decreased and false negative rate systematically increased. CONCLUSION: We demonstrate the feasibility of deep CNN for automatic segmentation of myocardial ASL, with good accuracy. We also introduce two simple methods for assessing model uncertainty. Finally, we demonstrate the ability to adapt the CNN model to a specific false positive vs. false negative tradeoff. These findings are directly relevant to automatic segmentation in quantitative cardiac MRI and are broadly applicable to automatic segmentation problems in diagnostic imaging. |
| Tasks | |
| Published | 2018-12-10 |
| URL | https://arxiv.org/abs/1812.03974v4 |
| https://arxiv.org/pdf/1812.03974v4.pdf | |
| PWC | https://paperswithcode.com/paper/accuracy-uncertainty-and-adaptability-of |
| Repo | |
| Framework | |
Deep-RBF Networks Revisited: Robust Classification with Rejection
| Title | Deep-RBF Networks Revisited: Robust Classification with Rejection |
| Authors | Pourya Habib Zadeh, Reshad Hosseini, Suvrit Sra |
| Abstract | One of the main drawbacks of deep neural networks, like many other classifiers, is their vulnerability to adversarial attacks. An important reason for their vulnerability is assigning high confidence to regions with few or even no feature points. By feature points, we mean a nonlinear transformation of the input space extracting a meaningful representation of the input data. On the other hand, deep-RBF networks assign high confidence only to the regions containing enough feature points, but they have been discounted due to the widely-held belief that they have the vanishing gradient problem. In this paper, we revisit the deep-RBF networks by first giving a general formulation for them, and then proposing a family of cost functions thereof inspired by metric learning. In the proposed deep-RBF learning algorithm, the vanishing gradient problem does not occur. We make these networks robust to adversarial attack by adding the reject option to their output layer. Through several experiments on the MNIST dataset, we demonstrate that our proposed method not only achieves significant classification accuracy but is also very resistant to various adversarial attacks. |
| Tasks | Adversarial Attack, Metric Learning |
| Published | 2018-12-07 |
| URL | http://arxiv.org/abs/1812.03190v1 |
| http://arxiv.org/pdf/1812.03190v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-rbf-networks-revisited-robust |
| Repo | |
| Framework | |
Fully Automated Organ Segmentation in Male Pelvic CT Images
| Title | Fully Automated Organ Segmentation in Male Pelvic CT Images |
| Authors | Anjali Balagopal, Samaneh Kazemifar, Dan Nguyen, Mu-Han Lin, Raquibul Hannan, Amir Owrangi, Steve Jiang |
| Abstract | Accurate segmentation of prostate and surrounding organs at risk is important for prostate cancer radiotherapy treatment planning. We present a fully automated workflow for male pelvic CT image segmentation using deep learning. The architecture consists of a 2D localization network followed by a 3D segmentation network for volumetric segmentation of prostate, bladder, rectum, and femoral heads. We used a multi-channel 2D U-Net followed by a 3D U-Net with encoding arm modified with aggregated residual networks, known as ResNeXt. The models were trained and tested on a pelvic CT image dataset comprising 136 patients. Test results show that 3D U-Net based segmentation achieves mean (SD) Dice coefficient values of 90 (2.0)% ,96 (3.0)%, 95 (1.3)%, 95 (1.5)%, and 84 (3.7)% for prostate, left femoral head, right femoral head, bladder, and rectum, respectively, using the proposed fully automated segmentation method. |
| Tasks | Semantic Segmentation |
| Published | 2018-05-31 |
| URL | http://arxiv.org/abs/1805.12526v1 |
| http://arxiv.org/pdf/1805.12526v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-automated-organ-segmentation-in-male |
| Repo | |
| Framework | |
Event-based Face Detection and Tracking in the Blink of an Eye
| Title | Event-based Face Detection and Tracking in the Blink of an Eye |
| Authors | Gregor Lenz, Sio-Hoi Ieng, Ryad Benosman |
| Abstract | We present the first purely event-based method for face detection using the high temporal resolution of an event-based camera. We will rely on a new feature that has never been used for such a task that relies on detecting eye blinks. Eye blinks are a unique natural dynamic signature of human faces that is captured well by event-based sensors that rely on relative changes of luminance. Although an eye blink can be captured with conventional cameras, we will show that the dynamics of eye blinks combined with the fact that two eyes act simultaneously allows to derive a robust methodology for face detection at a low computational cost and high temporal resolution. We show that eye blinks have a unique temporal signature over time that can be easily detected by correlating the acquired local activity with a generic temporal model of eye blinks that has been generated from a wide population of users. We furthermore show that once the face is reliably detected it is possible to apply a probabilistic framework to track the spatial position of a face for each incoming event while updating the position of trackers. Results are shown for several indoor and outdoor experiments. We will also release an annotated data set that can be used for future work on the topic. |
| Tasks | Face Detection |
| Published | 2018-03-27 |
| URL | http://arxiv.org/abs/1803.10106v3 |
| http://arxiv.org/pdf/1803.10106v3.pdf | |
| PWC | https://paperswithcode.com/paper/high-speed-event-based-face-detection-and |
| Repo | |
| Framework | |
Robots Learning to Say `No’: Prohibition and Rejective Mechanisms in Acquisition of Linguistic Negation
| Title | Robots Learning to Say `No’: Prohibition and Rejective Mechanisms in Acquisition of Linguistic Negation | |
| Authors | Frank Förster, Joe Saunders, Hagen Lehmann, Chrystopher L. Nehaniv |
| Abstract | No' belongs to the first ten words used by children and embodies the first active form of linguistic negation. Despite its early occurrence the details of its acquisition process remain largely unknown. The circumstance that no’ cannot be construed as a label for perceptible objects or events puts it outside of the scope of most modern accounts of language acquisition. Moreover, most symbol grounding architectures will struggle to ground the word due to its non-referential character. In an experimental study involving the child-like humanoid robot iCub that was designed to illuminate the acquisition process of negation words, the robot is deployed in several rounds of speech-wise unconstrained interaction with na"ive participants acting as its language teachers. The results corroborate the hypothesis that affect or volition plays a pivotal role in the socially distributed acquisition process. Negation words are prosodically salient within prohibitive utterances and negative intent interpretations such that they can be easily isolated from the teacher’s speech signal. These words subsequently may be grounded in negative affective states. However, observations of the nature of prohibitive acts and the temporal relationships between its linguistic and extra-linguistic components raise serious questions over the suitability of Hebbian-type algorithms for language grounding. |
| Tasks | Language Acquisition |
| Published | 2018-10-28 |
| URL | http://arxiv.org/abs/1810.11804v1 |
| http://arxiv.org/pdf/1810.11804v1.pdf | |
| PWC | https://paperswithcode.com/paper/robots-learning-to-say-no-prohibition-and |
| Repo | |
| Framework | |
Locally Differentially-Private Randomized Response for Discrete Distribution Learning
| Title | Locally Differentially-Private Randomized Response for Discrete Distribution Learning |
| Authors | Adriano Pastore, Michael Gastpar |
| Abstract | We consider a setup in which confidential i.i.d. samples $X_1,\dotsc,X_n$ from an unknown finite-support distribution $\boldsymbol{p}$ are passed through $n$ copies of a discrete privatization channel (a.k.a. mechanism) producing outputs $Y_1,\dotsc,Y_n$. The channel law guarantees a local differential privacy of $\epsilon$. Subject to a prescribed privacy level $\epsilon$, the optimal channel should be designed such that an estimate of the source distribution based on the channel outputs $Y_1,\dotsc,Y_n$ converges as fast as possible to the exact value $\boldsymbol{p}$. For this purpose we study the convergence to zero of three distribution distance metrics: $f$-divergence, mean-squared error and total variation. We derive the respective normalized first-order terms of convergence (as $n\to\infty$), which for a given target privacy $\epsilon$ represent a rule-of-thumb factor by which the sample size must be augmented so as to achieve the same estimation accuracy as that of a non-randomizing channel. We formulate the privacy-fidelity trade-off problem as being that of minimizing said first-order term under a privacy constraint $\epsilon$. We further identify a scalar quantity that captures the essence of this trade-off, and prove bounds and data-processing inequalities on this quantity. For some specific instances of the privacy-fidelity trade-off problem, we derive inner and outer bounds on the optimal trade-off curve. |
| Tasks | |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1811.12257v1 |
| http://arxiv.org/pdf/1811.12257v1.pdf | |
| PWC | https://paperswithcode.com/paper/locally-differentially-private-randomized |
| Repo | |
| Framework | |
Parallel sequential Monte Carlo for stochastic gradient-free nonconvex optimization
| Title | Parallel sequential Monte Carlo for stochastic gradient-free nonconvex optimization |
| Authors | Ömer Deniz Akyildiz, Dan Crisan, Joaquín Míguez |
| Abstract | We introduce and analyze a parallel sequential Monte Carlo methodology for the numerical solution of optimization problems that involve the minimization of a cost function that consists of the sum of many individual components. The proposed scheme is a stochastic zeroth order optimization algorithm which demands only the capability to evaluate small subsets of components of the cost function. It can be depicted as a bank of samplers that generate particle approximations of several sequences of probability measures. These measures are constructed in such a way that they have associated probability density functions whose global maxima coincide with the global minima of the original cost function. The algorithm selects the best performing sampler and uses it to approximate a global minimum of the cost function. We prove analytically that the resulting estimator converges to a global minimum of the cost function almost surely and provide explicit convergence rates in terms of the number of generated Monte Carlo samples. We show, by way of numerical examples, that the algorithm can tackle cost functions with multiple minima or with broad “flat” regions which are hard to minimize using gradient-based techniques. |
| Tasks | Stochastic Optimization |
| Published | 2018-11-23 |
| URL | https://arxiv.org/abs/1811.09469v3 |
| https://arxiv.org/pdf/1811.09469v3.pdf | |
| PWC | https://paperswithcode.com/paper/parallel-sequential-monte-carlo-for |
| Repo | |
| Framework | |
R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate
| Title | R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate |
| Authors | Jingzhao Zhang, Hongyi Zhang, Suvrit Sra |
| Abstract | We study smooth stochastic optimization problems on Riemannian manifolds. Via adapting the recently proposed SPIDER algorithm \citep{fang2018spider} (a variance reduced stochastic method) to Riemannian manifold, we can achieve faster rate than known algorithms in both the finite sum and stochastic settings. Unlike previous works, by \emph{not} resorting to bounding iterate distances, our analysis yields curvature independent convergence rates for both the nonconvex and strongly convex cases. |
| Tasks | Stochastic Optimization |
| Published | 2018-11-10 |
| URL | http://arxiv.org/abs/1811.04194v3 |
| http://arxiv.org/pdf/1811.04194v3.pdf | |
| PWC | https://paperswithcode.com/paper/r-spider-a-fast-riemannian-stochastic |
| Repo | |
| Framework | |
A Fast Face Detection Method via Convolutional Neural Network
| Title | A Fast Face Detection Method via Convolutional Neural Network |
| Authors | Guanjun Guo, Hanzi Wang, Yan Yan, Jin Zheng, Bo Li |
| Abstract | Current face or object detection methods via convolutional neural network (such as OverFeat, R-CNN and DenseNet) explicitly extract multi-scale features based on an image pyramid. However, such a strategy increases the computational burden for face detection. In this paper, we propose a fast face detection method based on discriminative complete features (DCFs) extracted by an elaborately designed convolutional neural network, where face detection is directly performed on the complete feature maps. DCFs have shown the ability of scale invariance, which is beneficial for face detection with high speed and promising performance. Therefore, extracting multi-scale features on an image pyramid employed in the conventional methods is not required in the proposed method, which can greatly improve its efficiency for face detection. Experimental results on several popular face detection datasets show the efficiency and the effectiveness of the proposed method for face detection. |
| Tasks | Face Detection, Object Detection |
| Published | 2018-03-27 |
| URL | http://arxiv.org/abs/1803.10103v1 |
| http://arxiv.org/pdf/1803.10103v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-fast-face-detection-method-via |
| Repo | |
| Framework | |
Seeing Small Faces from Robust Anchor’s Perspective
| Title | Seeing Small Faces from Robust Anchor’s Perspective |
| Authors | Chenchen Zhu, Ran Tao, Khoa Luu, Marios Savvides |
| Abstract | This paper introduces a novel anchor design to support anchor-based face detection for superior scale-invariant performance, especially on tiny faces. To achieve this, we explicitly address the problem that anchor-based detectors drop performance drastically on faces with tiny sizes, e.g. less than 16x16 pixels. In this paper, we investigate why this is the case. We discover that current anchor design cannot guarantee high overlaps between tiny faces and anchor boxes, which increases the difficulty of training. The new Expected Max Overlapping (EMO) score is proposed which can theoretically explain the low overlapping issue and inspire several effective strategies of new anchor design leading to higher face overlaps, including anchor stride reduction with new network architectures, extra shifted anchors, and stochastic face shifting. Comprehensive experiments show that our proposed method significantly outperforms the baseline anchor-based detector, while consistently achieving state-of-the-art results on challenging face detection datasets with competitive runtime speed. |
| Tasks | Face Detection |
| Published | 2018-02-25 |
| URL | http://arxiv.org/abs/1802.09058v1 |
| http://arxiv.org/pdf/1802.09058v1.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-small-faces-from-robust-anchors |
| Repo | |
| Framework | |
Category-level 6D Object Pose Recovery in Depth Images
| Title | Category-level 6D Object Pose Recovery in Depth Images |
| Authors | Caner Sahin, Tae-Kyun Kim |
| Abstract | Intra-class variations, distribution shifts among source and target domains are the major challenges of category-level tasks. In this study, we address category-level full 6D object pose estimation in the context of depth modality, introducing a novel part-based architecture that can tackle the above-mentioned challenges. Our architecture particularly adapts the distribution shifts arising from shape discrepancies, and naturally removes the variations of texture, illumination, pose, etc., so we call it as “Intrinsic Structure Adaptor (ISA)". We engineer ISA based on the followings: i) “Semantically Selected Centers (SSC)” are proposed in order to define the “6D pose” at the level of categories. ii) 3D skeleton structures, which we derive as shape-invariant features, are used to represent the parts extracted from the instances of given categories, and privileged one-class learning is employed based on these parts. iii) Graph matching is performed during training in such a way that the adaptation/generalization capability of the proposed architecture is improved across unseen instances. Experiments validate the promising performance of the proposed architecture on both synthetic and real datasets. |
| Tasks | 6D Pose Estimation using RGB, Graph Matching, Pose Estimation |
| Published | 2018-08-01 |
| URL | http://arxiv.org/abs/1808.00255v1 |
| http://arxiv.org/pdf/1808.00255v1.pdf | |
| PWC | https://paperswithcode.com/paper/category-level-6d-object-pose-recovery-in |
| Repo | |
| Framework | |
Support Vector Machine Active Learning Algorithms with Query-by-Committee versus Closest-to-Hyperplane Selection
| Title | Support Vector Machine Active Learning Algorithms with Query-by-Committee versus Closest-to-Hyperplane Selection |
| Authors | Michael Bloodgood |
| Abstract | This paper investigates and evaluates support vector machine active learning algorithms for use with imbalanced datasets, which commonly arise in many applications such as information extraction applications. Algorithms based on closest-to-hyperplane selection and query-by-committee selection are combined with methods for addressing imbalance such as positive amplification based on prevalence statistics from initial random samples. Three algorithms (ClosestPA, QBagPA, and QBoostPA) are presented and carefully evaluated on datasets for text classification and relation extraction. The ClosestPA algorithm is shown to consistently outperform the other two in a variety of ways and insights are provided as to why this is the case. |
| Tasks | Active Learning, Relation Extraction, Text Classification |
| Published | 2018-01-24 |
| URL | http://arxiv.org/abs/1801.07875v2 |
| http://arxiv.org/pdf/1801.07875v2.pdf | |
| PWC | https://paperswithcode.com/paper/support-vector-machine-active-learning |
| Repo | |
| Framework | |
