Paper Group ANR 5
A PTAS for $\ell_p$-Low Rank Approximation. Simultaneous synthesis of FLAIR and segmentation of white matter hypointensities from T1 MRIs. Entropic Variable Projection for Explainability and Intepretability. DeepSeeNet: A deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus ph …
A PTAS for $\ell_p$-Low Rank Approximation
| Title | A PTAS for $\ell_p$-Low Rank Approximation |
| Authors | Frank Ban, Vijay Bhattiprolu, Karl Bringmann, Pavel Kolev, Euiwoong Lee, David P. Woodruff |
| Abstract | A number of recent works have studied algorithms for entrywise $\ell_p$-low rank approximation, namely, algorithms which given an $n \times d$ matrix $A$ (with $n \geq d$), output a rank-$k$ matrix $B$ minimizing $\A-B_p^p=\sum_{i,j}A_{i,j}-B_{i,j}^p$ when $p > 0$; and $\A-B_0=\sum_{i,j}[A_{i,j}\neq B_{i,j}]$ for $p=0$. On the algorithmic side, for $p \in (0,2)$, we give the first $(1+\epsilon)$-approximation algorithm running in time $n^{\text{poly}(k/\epsilon)}$. Further, for $p = 0$, we give the first almost-linear time approximation scheme for what we call the Generalized Binary $\ell_0$-Rank-$k$ problem. Our algorithm computes $(1+\epsilon)$-approximation in time $(1/\epsilon)^{2^{O(k)}/\epsilon^{2}} \cdot nd^{1+o(1)}$. On the hardness of approximation side, for $p \in (1,2)$, assuming the Small Set Expansion Hypothesis and the Exponential Time Hypothesis (ETH), we show that there exists $\delta := \delta(\alpha) > 0$ such that the entrywise $\ell_p$-Rank-$k$ problem has no $\alpha$-approximation algorithm running in time $2^{k^{\delta}}$. |
| Tasks | |
| Published | 2018-07-16 |
| URL | http://arxiv.org/abs/1807.06101v2 |
| http://arxiv.org/pdf/1807.06101v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-ptas-for-ell_p-low-rank-approximation |
| Repo | |
| Framework | |
Simultaneous synthesis of FLAIR and segmentation of white matter hypointensities from T1 MRIs
| Title | Simultaneous synthesis of FLAIR and segmentation of white matter hypointensities from T1 MRIs |
| Authors | Mauricio Orbes-Arteaga, M. Jorge Cardoso, Lauge Sørensen, Marc Modat, Sébastien Ourselin, Mads Nielsen, Akshay Pai |
| Abstract | Segmenting vascular pathologies such as white matter lesions in Brain magnetic resonance images (MRIs) require acquisition of multiple sequences such as T1-weighted (T1-w) –on which lesions appear hypointense– and fluid attenuated inversion recovery (FLAIR) sequence –where lesions appear hyperintense–. However, most of the existing retrospective datasets do not consist of FLAIR sequences. Existing missing modality imputation methods separate the process of imputation, and the process of segmentation. In this paper, we propose a method to link both modality imputation and segmentation using convolutional neural networks. We show that by jointly optimizing the imputation network and the segmentation network, the method not only produces more realistic synthetic FLAIR images from T1-w images, but also improves the segmentation of WMH from T1-w images only. |
| Tasks | Imputation |
| Published | 2018-08-20 |
| URL | http://arxiv.org/abs/1808.06519v1 |
| http://arxiv.org/pdf/1808.06519v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-synthesis-of-flair-and |
| Repo | |
| Framework | |
Entropic Variable Projection for Explainability and Intepretability
| Title | Entropic Variable Projection for Explainability and Intepretability |
| Authors | Francois Bachoc, Fabrice Gamboa, Max Halford, Jean-Michel Loubes, Laurent Risser |
| Abstract | In this paper, we present a new explainability formalism designed to explain how the possible values of each input variable in a whole test set impact the predictions given by black-box decision rules. This is particularly pertinent for instance to temper the trust in the predictions when specific variables are in a sensitive range of values, or more generally to explain the behaviour of machine learning decision rules in a context represented by the test set. Our main methodological contribution is to propose an information theory framework, based on entropic projections, in order to compute the influence of each input-output observation when emphasizing the impact of a variable. This formalism is thus the first unified and model agnostic framework enabling to interpret the dependence between the input variables, their impact on the prediction errors, and their influence on the output predictions. Importantly, it has in addition a low algorithmic complexity making it scalable to real-life large datasets. We illustrate our strategy by explaining complex decision rules learned using XGBoost and Random Forest classifiers. We finally make clear its differences with explainability strategies based on single observations, such as those of LIME or SHAP, when explaining the impact of different pixels on a deep learning classifier using the MNIST database. |
| Tasks | |
| Published | 2018-10-18 |
| URL | https://arxiv.org/abs/1810.07924v3 |
| https://arxiv.org/pdf/1810.07924v3.pdf | |
| PWC | https://paperswithcode.com/paper/entropic-variable-boosting-for-explainability |
| Repo | |
| Framework | |
DeepSeeNet: A deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs
| Title | DeepSeeNet: A deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs |
| Authors | Yifan Peng, Shazia Dharssi, Qingyu Chen, Tiarnan D. Keenan, Elvira Agrón, Wai T. Wong, Emily Y. Chew, Zhiyong Lu |
| Abstract | In assessing the severity of age-related macular degeneration (AMD), the Age-Related Eye Disease Study (AREDS) Simplified Severity Scale predicts the risk of progression to late AMD. However, its manual use requires the time-consuming participation of expert practitioners. Although several automated deep learning systems have been developed for classifying color fundus photographs (CFP) of individual eyes by AREDS severity score, none to date has used a patient-based scoring system that uses images from both eyes to assign a severity score. DeepSeeNet, a deep learning model, was developed to classify patients automatically by the AREDS Simplified Severity Scale (score 0-5) using bilateral CFP. DeepSeeNet was trained on 58,402 and tested on 900 images from the longitudinal follow-up of 4549 participants from AREDS. Gold standard labels were obtained using reading center grades. DeepSeeNet simulates the human grading process by first detecting individual AMD risk factors (drusen size, pigmentary abnormalities) for each eye and then calculating a patient-based AMD severity score using the AREDS Simplified Severity Scale. DeepSeeNet performed better on patient-based classification (accuracy = 0.671; kappa = 0.558) than retinal specialists (accuracy = 0.599; kappa = 0.467) with high AUC in the detection of large drusen (0.94), pigmentary abnormalities (0.93), and late AMD (0.97). DeepSeeNet demonstrated high accuracy with increased transparency in the automated assignment of individual patients to AMD risk categories based on the AREDS Simplified Severity Scale. These results highlight the potential of deep learning to assist and enhance clinical decision-making in patients with AMD, such as early AMD detection and risk prediction for developing late AMD. DeepSeeNet is publicly available on https://github.com/ncbi-nlp/DeepSeeNet. |
| Tasks | Decision Making |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07492v2 |
| http://arxiv.org/pdf/1811.07492v2.pdf | |
| PWC | https://paperswithcode.com/paper/deepseenet-a-deep-learning-model-for |
| Repo | |
| Framework | |
Automated segmentation on the entire cardiac cycle using a deep learning work-flow
| Title | Automated segmentation on the entire cardiac cycle using a deep learning work-flow |
| Authors | Nicoló Savioli, Miguel Silva Vieira, Pablo Lamata, Giovanni Montana |
| Abstract | The segmentation of the left ventricle (LV) from CINE MRI images is essential to infer important clinical parameters. Typically, machine learning algorithms for automated LV segmentation use annotated contours from only two cardiac phases, diastole, and systole. In this work, we present an analysis work-flow for fully-automated LV segmentation that learns from images acquired through the cardiac cycle. The workflow consists of three components: first, for each image in the sequence, we perform an automated localization and subsequent cropping of the bounding box containing the cardiac silhouette. Second, we identify the LV contours using a Temporal Fully Convolutional Neural Network (T-FCNN), which extends Fully Convolutional Neural Networks (FCNN) through a recurrent mechanism enforcing temporal coherence across consecutive frames. Finally, we further defined the boundaries using either one of two components: fully-connected Conditional Random Fields (CRFs) with Gaussian edge potentials and Semantic Flow. Our initial experiments suggest that significant improvement in performance can potentially be achieved by using a recurrent neural network component that explicitly learns cardiac motion patterns whilst performing LV segmentation. |
| Tasks | |
| Published | 2018-08-31 |
| URL | http://arxiv.org/abs/1809.01015v1 |
| http://arxiv.org/pdf/1809.01015v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-segmentation-on-the-entire-cardiac |
| Repo | |
| Framework | |
Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers
| Title | Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers |
| Authors | Fred Hohman, Minsuk Kahng, Robert Pienta, Duen Horng Chau |
| Abstract | Deep learning has recently seen rapid development and received significant attention due to its state-of-the-art performance on previously-thought hard problems. However, because of the internal complexity and nonlinear structure of deep neural networks, the underlying decision making processes for why these models are achieving such performance are challenging and sometimes mystifying to interpret. As deep learning spreads across domains, it is of paramount importance that we equip users of deep learning with tools for understanding when a model works correctly, when it fails, and ultimately how to improve its performance. Standardized toolkits for building neural networks have helped democratize deep learning; visual analytics systems have now been developed to support model explanation, interpretation, debugging, and improvement. We present a survey of the role of visual analytics in deep learning research, which highlights its short yet impactful history and thoroughly summarizes the state-of-the-art using a human-centered interrogative framework, focusing on the Five W’s and How (Why, Who, What, How, When, and Where). We conclude by highlighting research directions and open research problems. This survey helps researchers and practitioners in both visual analytics and deep learning to quickly learn key aspects of this young and rapidly growing body of research, whose impact spans a diverse range of domains. |
| Tasks | Decision Making |
| Published | 2018-01-21 |
| URL | http://arxiv.org/abs/1801.06889v3 |
| http://arxiv.org/pdf/1801.06889v3.pdf | |
| PWC | https://paperswithcode.com/paper/visual-analytics-in-deep-learning-an |
| Repo | |
| Framework | |
Blind Community Detection from Low-rank Excitations of a Graph Filter
| Title | Blind Community Detection from Low-rank Excitations of a Graph Filter |
| Authors | Hoi-To Wai, Santiago Segarra, Asuman E. Ozdaglar, Anna Scaglione, Ali Jadbabaie |
| Abstract | This paper considers a new framework to detect communities in a graph from the observation of signals at its nodes. We model the observed signals as noisy outputs of an unknown network process, represented as a graph filter that is excited by a set of unknown low-rank inputs/excitations. Application scenarios of this model include diffusion dynamics, pricing experiments, and opinion dynamics. Rather than learning the precise parameters of the graph itself, we aim at retrieving the community structure directly. The paper shows that communities can be detected by applying a spectral method to the covariance matrix of graph signals. Our analysis indicates that the community detection performance depends on a `low-pass’ property of the graph filter. We also show that the performance can be improved via a low-rank matrix plus sparse decomposition method when the latent parameter vectors are known. Numerical experiments demonstrate that our approach is effective. | |
| Tasks | Community Detection |
| Published | 2018-09-05 |
| URL | http://arxiv.org/abs/1809.01485v2 |
| http://arxiv.org/pdf/1809.01485v2.pdf | |
| PWC | https://paperswithcode.com/paper/blind-community-detection-from-low-rank |
| Repo | |
| Framework | |
Measuring Human-perceived Similarity in Heterogeneous Collections
| Title | Measuring Human-perceived Similarity in Heterogeneous Collections |
| Authors | Jesse Anderton, Pavel Metrikov, Virgil Pavlu, Javed Aslam |
| Abstract | We present a technique for estimating the similarity between objects such as movies or foods whose proper representation depends on human perception. Our technique combines a modest number of human similarity assessments to infer a pairwise similarity function between the objects. This similarity function captures some human notion of similarity which may be difficult or impossible to automatically extract, such as which movie from a collection would be a better substitute when the desired one is unavailable. In contrast to prior techniques, our method does not assume that all similarity questions on the collection can be answered or that all users perceive similarity in the same way. When combined with a user model, we find how each assessor’s tastes vary, affecting their perception of similarity. |
| Tasks | |
| Published | 2018-02-16 |
| URL | http://arxiv.org/abs/1802.05929v1 |
| http://arxiv.org/pdf/1802.05929v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-human-perceived-similarity-in |
| Repo | |
| Framework | |
A Problem Reduction Approach for Visual Relationships Detection
| Title | A Problem Reduction Approach for Visual Relationships Detection |
| Authors | Toshiyuki Fukuzawa |
| Abstract | Identifying different objects (man and cup) is an important problem on its own, but identifying the relationship between them (holding) is critical for many real world use cases. This paper describes an approach to reduce a visual relationship detection problem to object detection problems. The method was applied to Google AI Open Images V4 Visual Relationship Track Challenge, which was held in conjunction with 2018 European Conference on Computer Vision (ECCV 2018) and it finished as a prize winner. The challenge was to build an algorithm that detects pairs of objects in particular relations: things like “woman playing guitar,” “beer on table,” or “dog inside car.". |
| Tasks | Object Detection |
| Published | 2018-09-26 |
| URL | http://arxiv.org/abs/1809.09828v1 |
| http://arxiv.org/pdf/1809.09828v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-problem-reduction-approach-for-visual |
| Repo | |
| Framework | |
Finding Dory in the Crowd: Detecting Social Interactions using Multi-Modal Mobile Sensing
| Title | Finding Dory in the Crowd: Detecting Social Interactions using Multi-Modal Mobile Sensing |
| Authors | Kleomenis Katevas, Katrin Hänsel, Richard Clegg, Ilias Leontiadis, Hamed Haddadi, Laurissa Tokarchuk |
| Abstract | Remembering our day-to-day social interactions is challenging even if you aren’t a blue memory challenged fish. The ability to automatically detect and remember these types of interactions is not only beneficial for individuals interested in their behavior in crowded situations, but also of interest to those who analyze crowd behavior. Currently, detecting social interactions is often performed using a variety of methods including ethnographic studies, computer vision techniques and manual annotation-based data analysis. However, mobile phones offer easier means for data collection that is easy to analyze and can preserve the user’s privacy. In this work, we present a system for detecting stationary social interactions inside crowds, leveraging multi-modal mobile sensing data such as Bluetooth Smart (BLE), accelerometer and gyroscope. To inform the development of such system, we conducted a study with 24 participants, where we asked them to socialize with each other for 45 minutes. We built a machine learning system based on gradient-boosted trees that predicts both 1:1 and group interactions with 77.8% precision and 86.5% recall, a 30.2% performance increase compared to a proximity-based approach. By utilizing a community detection-based method, we further detected the various group formation that exist within the crowd. Using mobile phone sensors already carried by the majority of people in a crowd makes our approach particularly well suited to real-life analysis of crowd behavior and influence strategies. |
| Tasks | Community Detection |
| Published | 2018-08-30 |
| URL | http://arxiv.org/abs/1809.00947v2 |
| http://arxiv.org/pdf/1809.00947v2.pdf | |
| PWC | https://paperswithcode.com/paper/finding-dory-in-the-crowd-detecting-social |
| Repo | |
| Framework | |
Community detection in networks without observing edges
| Title | Community detection in networks without observing edges |
| Authors | Till Hoffmann, Leto Peel, Renaud Lambiotte, Nick S. Jones |
| Abstract | We develop a Bayesian hierarchical model to identify communities in networks for which we do not observe the edges directly, but instead observe a series of interdependent signals for each of the nodes. Fitting the model provides an end-to-end community detection algorithm that does not extract information as a sequence of point estimates but propagates uncertainties from the raw data to the community labels. Our approach naturally supports multiscale community detection as well as the selection of an optimal scale using model comparison. We study the properties of the algorithm using synthetic data and apply it to daily returns of constituents of the S&P100 index as well as climate data from US cities. |
| Tasks | Community Detection |
| Published | 2018-08-18 |
| URL | https://arxiv.org/abs/1808.06079v2 |
| https://arxiv.org/pdf/1808.06079v2.pdf | |
| PWC | https://paperswithcode.com/paper/community-detection-in-networks-with |
| Repo | |
| Framework | |
Trust-Based Collaborative Filtering: Tackling the Cold Start Problem Using Regular Equivalence
| Title | Trust-Based Collaborative Filtering: Tackling the Cold Start Problem Using Regular Equivalence |
| Authors | Tomislav Duricic, Emanuel Lacic, Dominik Kowald, Elisabeth Lex |
| Abstract | User-based Collaborative Filtering (CF) is one of the most popular approaches to create recommender systems. This approach is based on finding the most relevant k users from whose rating history we can extract items to recommend. CF, however, suffers from data sparsity and the cold-start problem since users often rate only a small fraction of available items. One solution is to incorporate additional information into the recommendation process such as explicit trust scores that are assigned by users to others or implicit trust relationships that result from social connections between users. Such relationships typically form a very sparse trust network, which can be utilized to generate recommendations for users based on people they trust. In our work, we explore the use of a measure from network science, i.e. regular equivalence, applied to a trust network to generate a similarity matrix that is used to select the k-nearest neighbors for recommending items. We evaluate our approach on Epinions and we find that we can outperform related methods for tackling cold-start users in terms of recommendation accuracy. |
| Tasks | Recommendation Systems |
| Published | 2018-07-18 |
| URL | https://arxiv.org/abs/1807.06839v1 |
| https://arxiv.org/pdf/1807.06839v1.pdf | |
| PWC | https://paperswithcode.com/paper/trust-based-collaborative-filtering-tackling |
| Repo | |
| Framework | |
Separation of water and fat signal in whole-body gradient echo scans using convolutional neural networks
| Title | Separation of water and fat signal in whole-body gradient echo scans using convolutional neural networks |
| Authors | Jonathan Andersson, Håkan Ahlström, Joel Kullberg |
| Abstract | Purpose: To perform and evaluate water-fat signal separation of whole-body gradient echo scans using convolutional neural networks. Methods: Whole-body gradient echo scans of 240 subjects, each consisting of 5 bipolar echoes, were used. Reference fat fraction maps were created using a conventional method. Convolutional neural networks, more specifically 2D U-nets, were trained using 5-fold cross-validation with 1 or several echoes as input, using the squared difference between the output and the reference fat fraction maps as the loss function. The outputs of the networks were assessed by the loss function, measured liver fat fractions, and visually. Training was performed using a graphics processing unit (GPU). Inference was performed using the GPU as well as a central processing unit (CPU). Results: The loss curves indicated convergence, and the final loss of the validation data decreased when using more echoes as input. The liver fat fractions could be estimated using only 1 echo, but results were improved by use of more echoes. Visual assessment found the quality of the outputs of the networks to be similar to the reference even when using only 1 echo, with slight improvements when using more echoes. Training a network took at most 28.6 h. Inference time of a whole-body scan took at most 3.7 s using the GPU and 5.8 min using the CPU. Conclusion: It is possible to perform water-fat signal separation of whole-body gradient echo scans using convolutional neural networks. Separation was possible using only 1 echo, although using more echoes improved the results. |
| Tasks | |
| Published | 2018-12-12 |
| URL | http://arxiv.org/abs/1812.04922v2 |
| http://arxiv.org/pdf/1812.04922v2.pdf | |
| PWC | https://paperswithcode.com/paper/separation-of-water-and-fat-signal-in-whole |
| Repo | |
| Framework | |
Autonomous Deep Learning: Incremental Learning of Denoising Autoencoder for Evolving Data Streams
| Title | Autonomous Deep Learning: Incremental Learning of Denoising Autoencoder for Evolving Data Streams |
| Authors | Mahardhika Pratama, Andri Ashfahani, Yew Soon Ong, Savitha Ramasamy, Edwin Lughofer |
| Abstract | The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves in-depth study because it characterizes a fixed network capacity which cannot adapt to rapidly changing environments. An automated construction of a denoising autoeconder, namely deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. DEVDAN features an open structure both in the generative phase and in the discriminative phase where input features can be automatically added and discarded on the fly. A network significance (NS) method is formulated in this paper and is derived from the bias-variance concept. This method is capable of estimating the statistical contribution of the network structure and its hidden units which precursors an ideal state to add or prune input features. Furthermore, DEVDAN is free of the problem- specific threshold and works fully in the single-pass learning fashion. The efficacy of DEVDAN is numerically validated using nine non-stationary data stream problems simulated under the prequential test-then-train protocol where DEVDAN is capable of delivering an improvement of classification accuracy to recently published online learning works while having flexibility in the automatic extraction of robust input features and in adapting to rapidly changing environments. |
| Tasks | Denoising |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.09081v1 |
| http://arxiv.org/pdf/1809.09081v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-deep-learning-incremental-learning |
| Repo | |
| Framework | |
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
| Title | Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies |
| Authors | Hanbyul Joo, Tomas Simon, Yaser Sheikh |
| Abstract | We present a unified deformation model for the markerless capture of multiple scales of human movement, including facial expressions, body motion, and hand gestures. An initial model is generated by locally stitching together models of the individual parts of the human body, which we refer to as the “Frankenstein” model. This model enables the full expression of part movements, including face and hands by a single seamless model. Using a large-scale capture of people wearing everyday clothes, we optimize the Frankenstein model to create “Adam”. Adam is a calibrated model that shares the same skeleton hierarchy as the initial model but can express hair and clothing geometry, making it directly usable for fitting people as they normally appear in everyday life. Finally, we demonstrate the use of these models for total motion tracking, simultaneously capturing the large-scale body movements and the subtle face and hand motion of a social group of people. |
| Tasks | |
| Published | 2018-01-05 |
| URL | http://arxiv.org/abs/1801.01615v1 |
| http://arxiv.org/pdf/1801.01615v1.pdf | |
| PWC | https://paperswithcode.com/paper/total-capture-a-3d-deformation-model-for |
| Repo | |
| Framework | |
