Paper Group ANR 38
A Progressive Visual Analytics Tool for Incremental Experimental Evaluation. A low-cost real-time 3D imaging system for contactless asthma observation. Global convergence of neuron birth-death dynamics. Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits. Product of Orthogonal Spheres Parameterization for Disentangled Representation …
A Progressive Visual Analytics Tool for Incremental Experimental Evaluation
| Title | A Progressive Visual Analytics Tool for Incremental Experimental Evaluation |
| Authors | Fabio Giachelle, Gianmaria Silvello |
| Abstract | This paper presents a visual tool, AVIATOR, that integrates the progressive visual analytics paradigm in the IR evaluation process. This tool serves to speed-up and facilitate the performance assessment of retrieval models enabling a result analysis through visual facilities. AVIATOR goes one step beyond the common “compute wait visualize” analytics paradigm, introducing a continuous evaluation mechanism that minimizes human and computational resource consumption. |
| Tasks | |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08754v1 |
| http://arxiv.org/pdf/1904.08754v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-progressive-visual-analytics-tool-for |
| Repo | |
| Framework | |
A low-cost real-time 3D imaging system for contactless asthma observation
| Title | A low-cost real-time 3D imaging system for contactless asthma observation |
| Authors | Sheona M. M. D. P. Sequeira, Beril Sirmacek |
| Abstract | Asthma is becoming a very serious problem with every passing day, especially in children. However, it is very difficult to detect this disorder in them, since the breathing motion of children tends to change when they reach an age of 6. This, thus makes it very difficult to monitor their respiratory state easily. In this paper, we present a cheap non-contact alternative to the current methods that are available. This is using a stereo camera, that captures a video of the patient breathing at a frame rate of 30Hz. For further processing, the captured video has to be rectified and converted into a point cloud. The obtained point clouds need to be aligned in order to have the output with respect to a common plane. They are then converted into a surface mesh. The depth is further estimated by subtracting every point cloud from the reference point cloud (the first frame). The output data, however, when plotted with respect to real time produces a very noisy plot. This is filtered by determining the signal frequency by taking the Fast Fourier Transform of the breathing signal. The system was tested under 4 different breathing conditions: deep, shallow and normal breathing and while coughing. On its success, it was tested with mixed breathing (combination of normal and shallow breathing) and was lastly compared with the output of the expensive 3dMD system. The comparison showed that using the stereo camera, we can reach to similar sensitivity for respiratory motion observation. The experimental results show that, the proposed method provides a major step towards development of low-cost home-based observation systems for asthma patients and care-givers. |
| Tasks | |
| Published | 2019-11-03 |
| URL | https://arxiv.org/abs/1911.00879v1 |
| https://arxiv.org/pdf/1911.00879v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-low-cost-real-time-3d-imaging-system-for |
| Repo | |
| Framework | |
Global convergence of neuron birth-death dynamics
| Title | Global convergence of neuron birth-death dynamics |
| Authors | Grant Rotskoff, Samy Jelassi, Joan Bruna, Eric Vanden-Eijnden |
| Abstract | Neural networks with a large number of parameters admit a mean-field description, which has recently served as a theoretical explanation for the favorable training properties of “overparameterized” models. In this regime, gradient descent obeys a deterministic partial differential equation (PDE) that converges to a globally optimal solution for networks with a single hidden layer under appropriate assumptions. In this work, we propose a non-local mass transport dynamics that leads to a modified PDE with the same minimizer. We implement this non-local dynamics as a stochastic neuronal birth-death process and we prove that it accelerates the rate of convergence in the mean-field limit. We subsequently realize this PDE with two classes of numerical schemes that converge to the mean-field equation, each of which can easily be implemented for neural networks with finite numbers of parameters. We illustrate our algorithms with two models to provide intuition for the mechanism through which convergence is accelerated. |
| Tasks | |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01843v2 |
| http://arxiv.org/pdf/1902.01843v2.pdf | |
| PWC | https://paperswithcode.com/paper/global-convergence-of-neuron-birth-death |
| Repo | |
| Framework | |
Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits
| Title | Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits |
| Authors | Yogev Bar-On, Yishay Mansour |
| Abstract | We study agents communicating over an underlying network by exchanging messages, in order to optimize their individual regret in a common nonstochastic multi-armed bandit problem. We derive regret minimization algorithms that guarantee for each agent $v$ an individual expected regret of $\widetilde{O}\left(\sqrt{\left(1+\frac{K}{\left\mathcal{N}\left(v\right)\right}\right)T}\right)$, where $T$ is the number of time steps, $K$ is the number of actions and $\mathcal{N}\left(v\right)$ is the set of neighbors of agent $v$ in the communication graph. We present algorithms both for the case that the communication graph is known to all the agents, and for the case that the graph is unknown. When the graph is unknown, each agent knows only the set of its neighbors and an upper bound on the total number of agents. The individual regret between the models differs only by a logarithmic factor. Our work resolves an open problem from [Cesa-Bianchi et al., 2019b]. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-07-07 |
| URL | https://arxiv.org/abs/1907.03346v3 |
| https://arxiv.org/pdf/1907.03346v3.pdf | |
| PWC | https://paperswithcode.com/paper/individual-regret-in-cooperative |
| Repo | |
| Framework | |
Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning
| Title | Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning |
| Authors | Ankita Shukla, Sarthak Bhagat, Shagun Uppal, Saket Anand, Pavan Turaga |
| Abstract | Learning representations that can disentangle explanatory attributes underlying the data improves interpretabilty as well as provides control on data generation. Various learning frameworks such as VAEs, GANs and auto-encoders have been used in the literature to learn such representations. Most often, the latent space is constrained to a partitioned representation or structured by a prior to impose disentangling. In this work, we advance the use of a latent representation based on a product space of Orthogonal Spheres PrOSe. The PrOSe model is motivated by the reasoning that latent-variables related to the physics of image-formation can under certain relaxed assumptions lead to spherical-spaces. Orthogonality between the spheres is motivated via physical independence models. Imposing the orthogonal-sphere constraint is much simpler than other complicated physical models, is fairly general and flexible, and extensible beyond the factors used to motivate its development. Under further relaxed assumptions of equal-sized latent blocks per factor, the constraint can be written down in closed form as an ortho-normality term in the loss function. We show that our approach improves the quality of disentanglement significantly. We find consistent improvement in disentanglement compared to several state-of-the-art approaches, across several benchmarks and metrics. |
| Tasks | Representation Learning |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09554v1 |
| https://arxiv.org/pdf/1907.09554v1.pdf | |
| PWC | https://paperswithcode.com/paper/product-of-orthogonal-spheres |
| Repo | |
| Framework | |
Searching Heterogeneous Personal Digital Traces
| Title | Searching Heterogeneous Personal Digital Traces |
| Authors | Daniela Vianna, Varvara Kalokyri, Alexander Borgida, Thu D. Nguyen, Amelie Marian |
| Abstract | Digital traces of our lives are now constantly produced by various connected devices, internet services and interactions. Our actions result in a multitude of heterogeneous data objects, or traces, kept in various locations in the cloud or on local devices. Users have very few tools to organize, understand, and search the digital traces they produce. We propose a simple but flexible data model to aggregate, organize, and find personal information within a collection of a user’s personal digital traces. Our model uses as basic dimensions the six questions: what, when, where, who, why, and how. These natural questions model universal aspects of a personal data collection and serve as unifying features of each personal data object, regardless of its source. We propose indexing and search techniques to aid users in searching for their past information in their unified personal digital data sets using our model. Experiments performed over real user data from a variety of data sources such as Facebook, Dropbox, and Gmail show that our approach significantly improves search accuracy when compared with traditional search tools. |
| Tasks | |
| Published | 2019-04-10 |
| URL | http://arxiv.org/abs/1904.05374v1 |
| http://arxiv.org/pdf/1904.05374v1.pdf | |
| PWC | https://paperswithcode.com/paper/searching-heterogeneous-personal-digital |
| Repo | |
| Framework | |
Cross-modality Knowledge Transfer for Prostate Segmentation from CT Scans
| Title | Cross-modality Knowledge Transfer for Prostate Segmentation from CT Scans |
| Authors | Yucheng Liu, Naji Khosravan, Yulin Liu, Joseph Stember, Jonathan Shoag, Christopher E. Barbieri, Ulas Bagci, Sachin Jambawalikar |
| Abstract | Creating large scale high-quality annotations is a known challenge in medical imaging. In this work, based on the CycleGAN algorithm, we propose leveraging annotations from one modality to be useful in other modalities. More specifically, the proposed algorithm creates highly realistic synthetic CT images (SynCT) from prostate MR images using unpaired data sets. By using SynCT images (without segmentation labels) and MR images (with segmentation labels available), we have trained a deep segmentation network for precise delineation of prostate from real CT scans. For the generator in our CycleGAN, the cycle consistency term is used to guarantee that SynCT shares the identical manually-drawn, high-quality masks originally delineated on MR images. Further, we introduce a cost function based on structural similarity index (SSIM) to improve the anatomical similarity between real and synthetic images. For segmentation followed by the SynCT generation from CycleGAN, automatic delineation is achieved through a 2.5D Residual U-Net. Quantitative evaluation demonstrates comparable segmentation results between our SynCT and radiologist drawn masks for real CT images, solving an important problem in medical image segmentation field when ground truth annotations are not available for the modality of interest. |
| Tasks | Medical Image Segmentation, Semantic Segmentation, Transfer Learning |
| Published | 2019-08-26 |
| URL | https://arxiv.org/abs/1908.10208v2 |
| https://arxiv.org/pdf/1908.10208v2.pdf | |
| PWC | https://paperswithcode.com/paper/cross-modality-knowledge-transfer-for |
| Repo | |
| Framework | |
Adversarial Defense Framework for Graph Neural Network
| Title | Adversarial Defense Framework for Graph Neural Network |
| Authors | Shen Wang, Zhengzhang Chen, Jingchao Ni, Xiao Yu, Zhichun Li, Haifeng Chen, Philip S. Yu |
| Abstract | Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities and defense GNN against the adversarial attacks? In this paper, we propose DefNet, an effective adversarial defense framework for GNNs. In particular, we first investigate the latent vulnerabilities in every layer of GNNs and propose corresponding strategies including dual-stage aggregation and bottleneck perceptron. Then, to cope with the scarcity of training data, we propose an adversarial contrastive learning method to train the GNN in a conditional GAN manner by leveraging the high-level graph representation. Extensive experiments on three public datasets demonstrate the effectiveness of DefNet in improving the robustness of popular GNN variants, such as Graph Convolutional Network and GraphSAGE, under various types of adversarial attacks. |
| Tasks | Adversarial Defense, Representation Learning |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03679v2 |
| https://arxiv.org/pdf/1905.03679v2.pdf | |
| PWC | https://paperswithcode.com/paper/190503679 |
| Repo | |
| Framework | |
Automatic Rodent Brain MRI Lesion Segmentation with Fully Convolutional Networks
| Title | Automatic Rodent Brain MRI Lesion Segmentation with Fully Convolutional Networks |
| Authors | Juan Miguel Valverde, Artem Shatillo, Riccardo de Feo, Olli Gröhn, Alejandra Sierra, Jussi Tohka |
| Abstract | Manual segmentation of rodent brain lesions from magnetic resonance images (MRIs) is an arduous, time-consuming and subjective task that is highly important in pre-clinical research. Several automatic methods have been developed for different human brain MRI segmentation, but little research has targeted automatic rodent lesion segmentation. The existing tools for performing automatic lesion segmentation in rodents are constrained by strict assumptions about the data. Deep learning has been successfully used for medical image segmentation. However, there has not been any deep learning approach specifically designed for tackling rodent brain lesion segmentation. In this work, we propose a novel Fully Convolutional Network (FCN), RatLesNet, for the aforementioned task. Our dataset consists of 131 T2-weighted rat brain scans from 4 different studies in which ischemic stroke was induced by transient middle cerebral artery occlusion. We compare our method with two other 3D FCNs originally developed for anatomical segmentation (VoxResNet and 3D-U-Net) with 5-fold cross-validation on a single study and a generalization test, where the training was done on a single study and testing on three remaining studies. The labels generated by our method were quantitatively and qualitatively better than the predictions of the compared methods. The average Dice coefficient achieved in the 5-fold cross-validation experiment with the proposed approach was 0.88, between 3.7% and 38% higher than the compared architectures. The presented architecture also outperformed the other FCNs at generalizing on different studies, achieving the average Dice coefficient of 0.79. |
| Tasks | Lesion Segmentation, Medical Image Segmentation, Semantic Segmentation |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08746v1 |
| https://arxiv.org/pdf/1908.08746v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-rodent-brain-mri-lesion |
| Repo | |
| Framework | |
Late or Earlier Information Fusion from Depth and Spectral Data? Large-Scale Digital Surface Model Refinement by Hybrid-cGAN
| Title | Late or Earlier Information Fusion from Depth and Spectral Data? Large-Scale Digital Surface Model Refinement by Hybrid-cGAN |
| Authors | Ksenia Bittner, Marco Körner, Peter Reinartz |
| Abstract | We present the workflow of a DSM refinement methodology using a Hybrid-cGAN where the generative part consists of two encoders and a common decoder which blends the spectral and height information within one network. The inputs to the Hybrid-cGAN are single-channel photogrammetric DSMs with continuous values and single-channel pan-chromatic (PAN) half-meter resolution satellite images. Experimental results demonstrate that the earlier information fusion from data with different physical meanings helps to propagate fine details and complete an inaccurate or missing 3D information about building forms. Moreover, it improves the building boundaries making them more rectilinear. |
| Tasks | |
| Published | 2019-04-22 |
| URL | http://arxiv.org/abs/1904.09935v1 |
| http://arxiv.org/pdf/1904.09935v1.pdf | |
| PWC | https://paperswithcode.com/paper/late-or-earlier-information-fusion-from-depth |
| Repo | |
| Framework | |
Kidney and Kidney Tumor Segmentation using a Logical Ensemble of U-nets with Volumetric Validation
| Title | Kidney and Kidney Tumor Segmentation using a Logical Ensemble of U-nets with Volumetric Validation |
| Authors | Jamie A. O’Reilly, Manas Sangworasil, Takenobu Matsuura |
| Abstract | Automated medical image segmentation is a priority research area for computational methods. In particular, detection of cancerous tumors represents a current challenge in this area with potential for real-world impact. This paper describes a method developed in response to the 2019 Kidney Tumor Segmentation Challenge (KiTS19). Axial computed tomography (CT) scans from 210 kidney cancer patients were used to develop and evaluate this automatic segmentation method based on a logical ensemble of fully-convolutional network (FCN) architectures, followed by volumetric validation. Data was pre-processed using conventional computer vision techniques, thresholding, histogram equalization, morphological operations, centering, zooming and resizing. Three binary FCN segmentation models were trained to classify kidney and tumor (2), and only tumor (1), respectively. Model output images were stacked and volumetrically validated to produce the final segmentation for each patient scan. The average F1 score from kidney and tumor pixel classifications was calculated as 0.6758 using preprocessed images and annotations; although restoring to the original image format reduced this score. It remains to be seen how this compares to other solutions. |
| Tasks | Computed Tomography (CT), Medical Image Segmentation, Semantic Segmentation |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.02625v1 |
| https://arxiv.org/pdf/1908.02625v1.pdf | |
| PWC | https://paperswithcode.com/paper/kidney-and-kidney-tumor-segmentation-using-a |
| Repo | |
| Framework | |
Generalization Bounds for Neural Networks via Approximate Description Length
| Title | Generalization Bounds for Neural Networks via Approximate Description Length |
| Authors | Amit Daniely, Elad Granot |
| Abstract | We investigate the sample complexity of networks with bounds on the magnitude of its weights. In particular, we consider the class [ H=\left{W_t\circ\rho\circ \ldots\circ\rho\circ W_{1} :W_1,\ldots,W_{t-1}\in M_{d, d}, W_t\in M_{1,d}\right} ] where the spectral norm of each $W_i$ is bounded by $O(1)$, the Frobenius norm is bounded by $R$, and $\rho$ is the sigmoid function $\frac{e^x}{1+e^x}$ or the smoothened ReLU function $ \ln (1+e^x)$. We show that for any depth $t$, if the inputs are in $[-1,1]^d$, the sample complexity of $H$ is $\tilde O\left(\frac{dR^2}{\epsilon^2}\right)$. This bound is optimal up to log-factors, and substantially improves over the previous state of the art of $\tilde O\left(\frac{d^2R^2}{\epsilon^2}\right)$. We furthermore show that this bound remains valid if instead of considering the magnitude of the $W_i$'s, we consider the magnitude of $W_i - W_i^0$, where $W_i^0$ are some reference matrices, with spectral norm of $O(1)$. By taking the $W_i^0$ to be the matrices at the onset of the training process, we get sample complexity bounds that are sub-linear in the number of parameters, in many typical regimes of parameters. To establish our results we develop a new technique to analyze the sample complexity of families $H$ of predictors. We start by defining a new notion of a randomized approximate description of functions $f:X\to\mathbb{R}^d$. We then show that if there is a way to approximately describe functions in a class $H$ using $d$ bits, then $d/\epsilon^2$ examples suffices to guarantee uniform convergence. Namely, that the empirical loss of all the functions in the class is $\epsilon$-close to the true loss. Finally, we develop a set of tools for calculating the approximate description length of classes of functions that can be presented as a composition of linear function classes and non-linear functions. |
| Tasks | |
| Published | 2019-10-13 |
| URL | https://arxiv.org/abs/1910.05697v1 |
| https://arxiv.org/pdf/1910.05697v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalization-bounds-for-neural-networks-via |
| Repo | |
| Framework | |
Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation
| Title | Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation |
| Authors | Maria G. Baldeon Calisto, Susana K. Lai-Yuen |
| Abstract | Segmentation is a critical step in medical image analysis. Fully Convolutional Networks (FCNs) have emerged as powerful segmentation models achieving state-of-the-art results in various medical image datasets. Network architectures are usually designed manually for a specific segmentation task so applying them to other medical datasets requires extensive experience and time. Moreover, the segmentation requires handling large volumetric data that results in big and complex architectures. Recently, methods that automatically design neural networks for medical image segmentation have been presented; however, most approaches either do not fully consider volumetric information or do not optimize the size of the network. In this paper, we propose a novel self-adaptive 2D-3D ensemble of FCNs for medical image segmentation that incorporates volumetric information and optimizes both the model’s performance and size. The model is composed of an ensemble of a 2D FCN that extracts intra-slice information, and a 3D FCN that exploits inter-slice information. The architectures of the 2D and 3D FCNs are automatically adapted to a medical image dataset using a multiobjective evolutionary based algorithm that minimizes both the segmentation error and number of parameters in the network. The proposed 2D-3D FCN ensemble was tested on the task of prostate segmentation on the image dataset from the PROMISE12 Grand Challenge. The resulting network is ranked in the top 10 submissions, surpassing the performance of other automatically-designed architectures while being considerably smaller in size. |
| Tasks | Medical Image Segmentation, Semantic Segmentation |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11587v1 |
| https://arxiv.org/pdf/1907.11587v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-adaptive-2d-3d-ensemble-of-fully |
| Repo | |
| Framework | |
Optimism in Reinforcement Learning with Generalized Linear Function Approximation
| Title | Optimism in Reinforcement Learning with Generalized Linear Function Approximation |
| Authors | Yining Wang, Ruosong Wang, Simon S. Du, Akshay Krishnamurthy |
| Abstract | We design a new provably efficient algorithm for episodic reinforcement learning with generalized linear function approximation. We analyze the algorithm under a new expressivity assumption that we call “optimistic closure,” which is strictly weaker than assumptions from prior analyses for the linear setting. With optimistic closure, we prove that our algorithm enjoys a regret bound of $\tilde{O}(\sqrt{d^3 T})$ where $d$ is the dimensionality of the state-action features and $T$ is the number of episodes. This is the first statistically and computationally efficient algorithm for reinforcement learning with generalized linear functions. |
| Tasks | |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.04136v1 |
| https://arxiv.org/pdf/1912.04136v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimism-in-reinforcement-learning-with |
| Repo | |
| Framework | |
Global and Local Interpretability for Cardiac MRI Classification
| Title | Global and Local Interpretability for Cardiac MRI Classification |
| Authors | James R. Clough, Ilkay Oksuz, Esther Puyol-Anton, Bram Ruijsink, Andrew P. King, Julia A. Schnabel |
| Abstract | Deep learning methods for classifying medical images have demonstrated impressive accuracy in a wide range of tasks but often these models are hard to interpret, limiting their applicability in clinical practice. In this work we introduce a convolutional neural network model for identifying disease in temporal sequences of cardiac MR segmentations which is interpretable in terms of clinically familiar measurements. The model is based around a variational autoencoder, reducing the input into a low-dimensional latent space in which classification occurs. We then use the recently developed concept activation vector' technique to associate concepts which are diagnostically meaningful (eg. clinical biomarkers such as low left-ventricular ejection fraction’) to certain vectors in the latent space. These concepts are then qualitatively inspected by observing the change in the image domain resulting from interpolations in the latent space in the direction of these vectors. As a result, when the model classifies images it is also capable of providing naturally interpretable concepts relevant to that classification and demonstrating the meaning of those concepts in the image domain. Our approach is demonstrated on the UK Biobank cardiac MRI dataset where we detect the presence of coronary artery disease. |
| Tasks | |
| Published | 2019-06-14 |
| URL | https://arxiv.org/abs/1906.06188v2 |
| https://arxiv.org/pdf/1906.06188v2.pdf | |
| PWC | https://paperswithcode.com/paper/global-and-local-interpretability-for-cardiac |
| Repo | |
| Framework | |
