Paper Group ANR 505
Contextual Motifs: Increasing the Utility of Motifs using Contextual Data. Segmentation-by-Detection: A Cascade Network for Volumetric Medical Image Segmentation. Perturb-and-MPM: Quantifying Segmentation Uncertainty in Dense Multi-Label CRFs. Capturing Long-term Temporal Dependencies with Convolutional Networks for Continuous Emotion Recognition. …
Contextual Motifs: Increasing the Utility of Motifs using Contextual Data
| Title | Contextual Motifs: Increasing the Utility of Motifs using Contextual Data |
| Authors | Ian Fox, Lynn Ang, Mamta Jaiswal, Rodica Pop-Busui, Jenna Wiens |
| Abstract | Motifs are a powerful tool for analyzing physiological waveform data. Standard motif methods, however, ignore important contextual information (e.g., what the patient was doing at the time the data were collected). We hypothesize that these additional contextual data could increase the utility of motifs. Thus, we propose an extension to motifs, contextual motifs, that incorporates context. Recognizing that, oftentimes, context may be unobserved or unavailable, we focus on methods to jointly infer motifs and context. Applied to both simulated and real physiological data, our proposed approach improves upon existing motif methods in terms of the discriminative utility of the discovered motifs. In particular, we discovered contextual motifs in continuous glucose monitor (CGM) data collected from patients with type 1 diabetes. Compared to their contextless counterparts, these contextual motifs led to better predictions of hypo- and hyperglycemic events. Our results suggest that even when inferred, context is useful in both a long- and short-term prediction horizon when processing and interpreting physiological waveform data. |
| Tasks | |
| Published | 2017-03-06 |
| URL | http://arxiv.org/abs/1703.02144v2 |
| http://arxiv.org/pdf/1703.02144v2.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-motifs-increasing-the-utility-of |
| Repo | |
| Framework | |
Segmentation-by-Detection: A Cascade Network for Volumetric Medical Image Segmentation
| Title | Segmentation-by-Detection: A Cascade Network for Volumetric Medical Image Segmentation |
| Authors | Min Tang, Zichen Zhang, Dana Cobzas, Martin Jagersand, Jacob L. Jaremko |
| Abstract | We propose an attention mechanism for 3D medical image segmentation. The method, named segmentation-by-detection, is a cascade of a detection module followed by a segmentation module. The detection module enables a region of interest to come to attention and produces a set of object region candidates which are further used as an attention model. Rather than dealing with the entire volume, the segmentation module distills the information from the potential region. This scheme is an efficient solution for volumetric data as it reduces the influence of the surrounding noise which is especially important for medical data with low signal-to-noise ratio. Experimental results on 3D ultrasound data of the femoral head shows superiority of the proposed method when compared with a standard fully convolutional network like the U-Net. |
| Tasks | Medical Image Segmentation, Semantic Segmentation, Volumetric Medical Image Segmentation |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1711.00139v1 |
| http://arxiv.org/pdf/1711.00139v1.pdf | |
| PWC | https://paperswithcode.com/paper/segmentation-by-detection-a-cascade-network |
| Repo | |
| Framework | |
Perturb-and-MPM: Quantifying Segmentation Uncertainty in Dense Multi-Label CRFs
| Title | Perturb-and-MPM: Quantifying Segmentation Uncertainty in Dense Multi-Label CRFs |
| Authors | Raphael Meier, Urspeter Knecht, Alain Jungo, Roland Wiest, Mauricio Reyes |
| Abstract | This paper proposes a novel approach for uncertainty quantification in dense Conditional Random Fields (CRFs). The presented approach, called Perturb-and-MPM, enables efficient, approximate sampling from dense multi-label CRFs via random perturbations. An analytic error analysis was performed which identified the main cause of approximation error as well as showed that the error is bounded. Spatial uncertainty maps can be derived from the Perturb-and-MPM model, which can be used to visualize uncertainty in image segmentation results. The method is validated on synthetic and clinical Magnetic Resonance Imaging data. The effectiveness of the approach is demonstrated on the challenging problem of segmenting the tumor core in glioblastoma. We found that areas of high uncertainty correspond well to wrongly segmented image regions. Furthermore, we demonstrate the potential use of uncertainty maps to refine imaging biomarkers in the case of extent of resection and residual tumor volume in brain tumor patients. |
| Tasks | Semantic Segmentation |
| Published | 2017-03-01 |
| URL | http://arxiv.org/abs/1703.00312v2 |
| http://arxiv.org/pdf/1703.00312v2.pdf | |
| PWC | https://paperswithcode.com/paper/perturb-and-mpm-quantifying-segmentation |
| Repo | |
| Framework | |
Capturing Long-term Temporal Dependencies with Convolutional Networks for Continuous Emotion Recognition
| Title | Capturing Long-term Temporal Dependencies with Convolutional Networks for Continuous Emotion Recognition |
| Authors | Soheil Khorram, Zakaria Aldeneh, Dimitrios Dimitriadis, Melvin McInnis, Emily Mower Provost |
| Abstract | The goal of continuous emotion recognition is to assign an emotion value to every frame in a sequence of acoustic features. We show that incorporating long-term temporal dependencies is critical for continuous emotion recognition tasks. To this end, we first investigate architectures that use dilated convolutions. We show that even though such architectures outperform previously reported systems, the output signals produced from such architectures undergo erratic changes between consecutive time steps. This is inconsistent with the slow moving ground-truth emotion labels that are obtained from human annotators. To deal with this problem, we model a downsampled version of the input signal and then generate the output signal through upsampling. Not only does the resulting downsampling/upsampling network achieve good performance, it also generates smooth output trajectories. Our method yields the best known audio-only performance on the RECOLA dataset. |
| Tasks | Emotion Recognition |
| Published | 2017-08-23 |
| URL | http://arxiv.org/abs/1708.07050v1 |
| http://arxiv.org/pdf/1708.07050v1.pdf | |
| PWC | https://paperswithcode.com/paper/capturing-long-term-temporal-dependencies |
| Repo | |
| Framework | |
Recognizing Involuntary Actions from 3D Skeleton Data Using Body States
| Title | Recognizing Involuntary Actions from 3D Skeleton Data Using Body States |
| Authors | Mozhgan Mokari, Hoda Mohammadzade, Benyamin Ghojogh |
| Abstract | Human action recognition has been one of the most active fields of research in computer vision for last years. Two dimensional action recognition methods are facing serious challenges such as occlusion and missing the third dimension of data. Development of depth sensors has made it feasible to track positions of human body joints over time. This paper proposes a novel method of action recognition which uses temporal 3D skeletal Kinect data. This method introduces the definition of body states and then every action is modeled as a sequence of these states. The learning stage uses Fisher Linear Discriminant Analysis (LDA) to construct discriminant feature space for discriminating the body states. Moreover, this paper suggests the use of the Mahalonobis distance as an appropriate distance metric for the classification of the states of involuntary actions. Hidden Markov Model (HMM) is then used to model the temporal transition between the body states in each action. According to the results, this method significantly outperforms other popular methods, with recognition rate of 88.64% for eight different actions and up to 96.18% for classifying fall actions. |
| Tasks | Temporal Action Localization |
| Published | 2017-08-21 |
| URL | http://arxiv.org/abs/1708.06227v1 |
| http://arxiv.org/pdf/1708.06227v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognizing-involuntary-actions-from-3d |
| Repo | |
| Framework | |
Overcoming model simplifications when quantifying predictive uncertainty
| Title | Overcoming model simplifications when quantifying predictive uncertainty |
| Authors | George M. Mathews, John Vial |
| Abstract | It is generally accepted that all models are wrong – the difficulty is determining which are useful. Here, a useful model is considered as one that is capable of combining data and expert knowledge, through an inversion or calibration process, to adequately characterize the uncertainty in predictions of interest. This paper derives conditions that specify which simplified models are useful and how they should be calibrated. To start, the notion of an optimal simplification is defined. This relates the model simplifications to the nature of the data and predictions, and determines when a standard probabilistic calibration scheme is capable of accurately characterizing uncertainty. Furthermore, two additional conditions are defined for suboptimal models that determine when the simplifications can be safely ignored. The first allows a suboptimally simplified model to be used in a way that replicates the performance of an optimal model. This is achieved through the judicial selection of a prior term for the calibration process that explicitly includes the nature of the data, predictions and modelling simplifications. The second considers the dependency structure between the predictions and the available data to gain insights into when the simplifications can be overcome by using the right calibration data. Furthermore, the derived conditions are related to the commonly used calibration schemes based on Tikhonov and subspace regularization. To allow concrete insights to be obtained, the analysis is performed under a linear expansion of the model equations and where the predictive uncertainty is characterized via second order moments only. |
| Tasks | Calibration |
| Published | 2017-03-21 |
| URL | http://arxiv.org/abs/1703.07198v1 |
| http://arxiv.org/pdf/1703.07198v1.pdf | |
| PWC | https://paperswithcode.com/paper/overcoming-model-simplifications-when |
| Repo | |
| Framework | |
Tactics to Directly Map CNN graphs on Embedded FPGAs
| Title | Tactics to Directly Map CNN graphs on Embedded FPGAs |
| Authors | Kamel Abdelouahab, Maxime Pelcat, Jocelyn Sérot, Cédric Bourrasset, François Berry, Jocelyn Serot |
| Abstract | Deep Convolutional Neural Networks (CNNs) are the state-of-the-art in image classification. Since CNN feed forward propagation involves highly regular parallel computation, it benefits from a significant speed-up when running on fine grain parallel programmable logic devices. As a consequence, several studies have proposed FPGA-based accelerators for CNNs. However, because of the large computationalpower required by CNNs, none of the previous studies has proposed a direct mapping of the CNN onto the physical resources of an FPGA, allocating each processing actor to its own hardware instance.In this paper, we demonstrate the feasibility of the so called direct hardware mapping (DHM) and discuss several tactics we explore to make DHM usable in practice. As a proof of concept, we introduce the HADDOC2 open source tool, that automatically transforms a CNN description into a synthesizable hardware description with platform-independent direct hardware mapping. |
| Tasks | Image Classification |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1712.04322v1 |
| http://arxiv.org/pdf/1712.04322v1.pdf | |
| PWC | https://paperswithcode.com/paper/tactics-to-directly-map-cnn-graphs-on |
| Repo | |
| Framework | |
Infinite Mixture Model of Markov Chains
| Title | Infinite Mixture Model of Markov Chains |
| Authors | Jan Reubold, Thorsten Strufe, Ulf Brefeld |
| Abstract | We propose a Bayesian nonparametric mixture model for prediction- and information extraction tasks with an efficient inference scheme. It models categorical-valued time series that exhibit dynamics from multiple underlying patterns (e.g. user behavior traces). We simplify the idea of capturing these patterns by hierarchical hidden Markov models (HHMMs) - and extend the existing approaches by the additional representation of structural information. Our empirical results are based on both synthetic- and real world data. They indicate that the results are easily interpretable, and that the model excels at segmentation and prediction performance: it successfully identifies the generating patterns and can be used for effective prediction of future observations. |
| Tasks | Time Series |
| Published | 2017-06-19 |
| URL | http://arxiv.org/abs/1706.06178v1 |
| http://arxiv.org/pdf/1706.06178v1.pdf | |
| PWC | https://paperswithcode.com/paper/infinite-mixture-model-of-markov-chains |
| Repo | |
| Framework | |
Changing Model Behavior at Test-Time Using Reinforcement Learning
| Title | Changing Model Behavior at Test-Time Using Reinforcement Learning |
| Authors | Augustus Odena, Dieterich Lawson, Christopher Olah |
| Abstract | Machine learning models are often used at test-time subject to constraints and trade-offs not present at training-time. For example, a computer vision model operating on an embedded device may need to perform real-time inference, or a translation model operating on a cell phone may wish to bound its average compute time in order to be power-efficient. In this work we describe a mixture-of-experts model and show how to change its test-time resource-usage on a per-input basis using reinforcement learning. We test our method on a small MNIST-based example. |
| Tasks | |
| Published | 2017-02-24 |
| URL | http://arxiv.org/abs/1702.07780v1 |
| http://arxiv.org/pdf/1702.07780v1.pdf | |
| PWC | https://paperswithcode.com/paper/changing-model-behavior-at-test-time-using |
| Repo | |
| Framework | |
Rapid focus map surveying for whole slide imaging with continues sample motion
| Title | Rapid focus map surveying for whole slide imaging with continues sample motion |
| Authors | Jun Liao, Yutong Jiang, Zichao Bian, Bahareh Mahrou, Aparna Nambiar, Alexander W. Magsam, Kaikai Guo, Yong Ku Cho, Guoan Zheng |
| Abstract | Whole slide imaging (WSI) has recently been cleared for primary diagnosis in the US. A critical challenge of WSI is to perform accurate focusing in high speed. Traditional systems create a focus map prior to scanning. For each focus point on the map, sample needs to be static in the x-y plane and axial scanning is needed to maximize the contrast. Here we report a novel focus map surveying method for WSI. The reported method requires no axial scanning, no additional camera and lens, works for stained and transparent samples, and allows continuous sample motion in the surveying process. It can be used for both brightfield and fluorescence WSI. By using a 20X, 0.75 NA objective lens, we demonstrate a mean focusing error of ~0.08 microns in the static mode and ~0.17 microns in the continuous motion mode. The reported method may provide a turnkey solution for most existing WSI systems for its simplicity, robustness, accuracy, and high-speed. It may also standardize the imaging performance of WSI systems for digital pathology and find other applications in high-content microscopy such as DNA sequencing and time-lapse live-cell imaging. |
| Tasks | |
| Published | 2017-07-06 |
| URL | http://arxiv.org/abs/1707.03039v1 |
| http://arxiv.org/pdf/1707.03039v1.pdf | |
| PWC | https://paperswithcode.com/paper/rapid-focus-map-surveying-for-whole-slide |
| Repo | |
| Framework | |
Learning Populations of Parameters
| Title | Learning Populations of Parameters |
| Authors | Kevin Tian, Weihao Kong, Gregory Valiant |
| Abstract | Consider the following estimation problem: there are $n$ entities, each with an unknown parameter $p_i \in [0,1]$, and we observe $n$ independent random variables, $X_1,\ldots,X_n$, with $X_i \sim $ Binomial$(t, p_i)$. How accurately can one recover the “histogram” (i.e. cumulative density function) of the $p_i$'s? While the empirical estimates would recover the histogram to earth mover distance $\Theta(\frac{1}{\sqrt{t}})$ (equivalently, $\ell_1$ distance between the CDFs), we show that, provided $n$ is sufficiently large, we can achieve error $O(\frac{1}{t})$ which is information theoretically optimal. We also extend our results to the multi-dimensional parameter case, capturing settings where each member of the population has multiple associated parameters. Beyond the theoretical results, we demonstrate that the recovery algorithm performs well in practice on a variety of datasets, providing illuminating insights into several domains, including politics, sports analytics, and variation in the gender ratio of offspring. |
| Tasks | |
| Published | 2017-09-08 |
| URL | http://arxiv.org/abs/1709.02707v2 |
| http://arxiv.org/pdf/1709.02707v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-populations-of-parameters |
| Repo | |
| Framework | |
Subspace Selection to Suppress Confounding Source Domain Information in AAM Transfer Learning
| Title | Subspace Selection to Suppress Confounding Source Domain Information in AAM Transfer Learning |
| Authors | Azin Asgarian, Ahmed Bilal Ashraf, David Fleet, Babak Taati |
| Abstract | Active appearance models (AAMs) are a class of generative models that have seen tremendous success in face analysis. However, model learning depends on the availability of detailed annotation of canonical landmark points. As a result, when accurate AAM fitting is required on a different set of variations (expression, pose, identity), a new dataset is collected and annotated. To overcome the need for time consuming data collection and annotation, transfer learning approaches have received recent attention. The goal is to transfer knowledge from previously available datasets (source) to a new dataset (target). We propose a subspace transfer learning method, in which we select a subspace from the source that best describes the target space. We propose a metric to compute the directional similarity between the source eigenvectors and the target subspace. We show an equivalence between this metric and the variance of target data when projected onto source eigenvectors. Using this equivalence, we select a subset of source principal directions that capture the variance in target data. To define our model, we augment the selected source subspace with the target subspace learned from a handful of target examples. In experiments done on six publicly available datasets, we show that our approach outperforms the state of the art in terms of the RMS fitting error as well as the percentage of test examples for which AAM fitting converges to the ground truth. |
| Tasks | Transfer Learning |
| Published | 2017-08-28 |
| URL | http://arxiv.org/abs/1708.08508v2 |
| http://arxiv.org/pdf/1708.08508v2.pdf | |
| PWC | https://paperswithcode.com/paper/subspace-selection-to-suppress-confounding |
| Repo | |
| Framework | |
Activation Ensembles for Deep Neural Networks
| Title | Activation Ensembles for Deep Neural Networks |
| Authors | Mark Harmon, Diego Klabjan |
| Abstract | Many activation functions have been proposed in the past, but selecting an adequate one requires trial and error. We propose a new methodology of designing activation functions within a neural network at each layer. We call this technique an “activation ensemble” because it allows the use of multiple activation functions at each layer. This is done by introducing additional variables, $\alpha$, at each activation layer of a network to allow for multiple activation functions to be active at each neuron. By design, activations with larger $\alpha$ values at a neuron is equivalent to having the largest magnitude. Hence, those higher magnitude activations are “chosen” by the network. We implement the activation ensembles on a variety of datasets using an array of Feed Forward and Convolutional Neural Networks. By using the activation ensemble, we achieve superior results compared to traditional techniques. In addition, because of the flexibility of this methodology, we more deeply explore activation functions and the features that they capture. |
| Tasks | |
| Published | 2017-02-24 |
| URL | http://arxiv.org/abs/1702.07790v1 |
| http://arxiv.org/pdf/1702.07790v1.pdf | |
| PWC | https://paperswithcode.com/paper/activation-ensembles-for-deep-neural-networks |
| Repo | |
| Framework | |
Exploring Approximations for Floating-Point Arithmetic using UppSAT
| Title | Exploring Approximations for Floating-Point Arithmetic using UppSAT |
| Authors | Aleksandar Zeljic, Peter Backeman, Christoph M. Wintersteiger, Philipp Ruemmer |
| Abstract | We consider the problem of solving floating-point constraints obtained from software verification. We present UppSAT — a new implementation of a systematic approximation refinement framework [ZWR17] as an abstract SMT solver. Provided with an approximation and a decision procedure (implemented in an off-the-shelf SMT solver), UppSAT yields an approximating SMT solver. Additionally, UppSAT includes a library of predefined approximation components which can be combined and extended to define new encodings, orderings and solving strategies. We propose that UppSAT can be used as a sandbox for easy and flexible exploration of new approximations. To substantiate this, we explore several approximations of floating-point arithmetic. Approximations can be viewed as a composition of an encoding into a target theory, a precision ordering, and a number of strategies for model reconstruction and precision (or approximation) refinement. We present encodings of floating-point arithmetic into reduced precision floating-point arithmetic, real-arithmetic, and fixed-point arithmetic (encoded in the theory of bit-vectors). In an experimental evaluation, we compare the advantages and disadvantages of approximating solvers obtained by combining various encodings and decision procedures (based on existing state-of-the-art SMT solvers for floating-point, real, and bit-vector arithmetic). |
| Tasks | |
| Published | 2017-11-24 |
| URL | http://arxiv.org/abs/1711.08859v2 |
| http://arxiv.org/pdf/1711.08859v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-approximations-for-floating-point |
| Repo | |
| Framework | |
Multilevel Clustering via Wasserstein Means
| Title | Multilevel Clustering via Wasserstein Means |
| Authors | Nhat Ho, XuanLong Nguyen, Mikhail Yurochkin, Hung Hai Bui, Viet Huynh, Dinh Phung |
| Abstract | We propose a novel approach to the problem of multilevel clustering, which aims to simultaneously partition data in each group and discover grouping patterns among groups in a potentially large hierarchically structured corpus of data. Our method involves a joint optimization formulation over several spaces of discrete probability measures, which are endowed with Wasserstein distance metrics. We propose a number of variants of this problem, which admit fast optimization algorithms, by exploiting the connection to the problem of finding Wasserstein barycenters. Consistency properties are established for the estimates of both local and global clusters. Finally, experiment results with both synthetic and real data are presented to demonstrate the flexibility and scalability of the proposed approach. |
| Tasks | |
| Published | 2017-06-13 |
| URL | http://arxiv.org/abs/1706.03883v1 |
| http://arxiv.org/pdf/1706.03883v1.pdf | |
| PWC | https://paperswithcode.com/paper/multilevel-clustering-via-wasserstein-means |
| Repo | |
| Framework | |
