Paper Group ANR 1736
Evaluation of an AI system for the automated detection of glaucoma from stereoscopic optic disc photographs: the European Optic Disc Assessment Study. Demand Prediction for Electric Vehicle Sharing. Competitive Bridge Bidding with Deep Neural Networks. Context-Aware Zero-Shot Recognition. DSConv: Efficient Convolution Operator. Sample Efficient Pol …
Evaluation of an AI system for the automated detection of glaucoma from stereoscopic optic disc photographs: the European Optic Disc Assessment Study
| Title | Evaluation of an AI system for the automated detection of glaucoma from stereoscopic optic disc photographs: the European Optic Disc Assessment Study |
| Authors | Thomas W. Rogers, Nicolas Jaccard, Francis Carbonaro, Hans G. Lemij, Koenraad A. Vermeer, Nicolaas J. Reus, Sameer Trikha |
| Abstract | Objectives: To evaluate the performance of a deep learning based Artificial Intelligence (AI) software for detection of glaucoma from stereoscopic optic disc photographs, and to compare this performance to the performance of a large cohort of ophthalmologists and optometrists. Methods: A retrospective study evaluating the diagnostic performance of an AI software (Pegasus v1.0, Visulytix Ltd., London UK) and comparing it to that of 243 European ophthalmologists and 208 British optometrists, as determined in previous studies, for the detection of glaucomatous optic neuropathy from 94 scanned stereoscopic photographic slides scanned into digital format. Results: Pegasus was able to detect glaucomatous optic neuropathy with an accuracy of 83.4% (95% CI: 77.5-89.2). This is comparable to an average ophthalmologist accuracy of 80.5% (95% CI: 67.2-93.8) and average optometrist accuracy of 80% (95% CI: 67-88) on the same images. In addition, the AI system had an intra-observer agreement (Cohen’s Kappa, $\kappa$) of 0.74 (95% CI: 0.63-0.85), compared to 0.70 (range: -0.13-1.00; 95% CI: 0.67-0.73) and 0.71 (range: 0.08-1.00) for ophthalmologists and optometrists, respectively. There was no statistically significant difference between the performance of the deep learning system and ophthalmologists or optometrists. There was no statistically significant difference between the performance of the deep learning system and ophthalmologists or optometrists. Conclusion: The AI system obtained a diagnostic performance and repeatability comparable to that of the ophthalmologists and optometrists. We conclude that deep learning based AI systems, such as Pegasus, demonstrate significant promise in the assisted detection of glaucomatous optic neuropathy. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01272v1 |
| https://arxiv.org/pdf/1906.01272v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluation-of-an-ai-system-for-the-automated |
| Repo | |
| Framework | |
Demand Prediction for Electric Vehicle Sharing
| Title | Demand Prediction for Electric Vehicle Sharing |
| Authors | Man Luo, Hongkai Wen, Yi Luo, Bowen Du, Konstantin Klemmer, Hongming Zhu |
| Abstract | Electric Vehicle (EV) sharing systems have recently experienced unprecedented growth across the globe. Many car sharing service providers as well as automobile manufacturers are entering this competition by expanding both their EV fleets and renting/returning station networks, aiming to seize a share of the market and bring car sharing to the zero emissions level. During their fast expansion, one fundamental determinant for success is the capability of dynamically predicting the demand of stations. In this paper we propose a novel demand prediction approach, which is able to model the dynamics of the system and predict demand accordingly. We use a local temporal encoding process to handle the available historical data at individual stations, and a spatial encoding process to take correlations between stations into account with graph convolutional neural networks. The encoded features are fed to a prediction network, which forecasts both the long-term expected demand of the stations. We evaluate the proposed approach on real-world data collected from a major EV sharing platform. Experimental results demonstrate that our approach significantly outperforms the state of the art. |
| Tasks | Decision Making |
| Published | 2019-03-10 |
| URL | https://arxiv.org/abs/1903.04051v3 |
| https://arxiv.org/pdf/1903.04051v3.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-demand-prediction-for-expanding |
| Repo | |
| Framework | |
Competitive Bridge Bidding with Deep Neural Networks
| Title | Competitive Bridge Bidding with Deep Neural Networks |
| Authors | Jiang Rong, Tao Qin, Bo An |
| Abstract | The game of bridge consists of two stages: bidding and playing. While playing is proved to be relatively easy for computer programs, bidding is very challenging. During the bidding stage, each player knowing only his/her own cards needs to exchange information with his/her partner and interfere with opponents at the same time. Existing methods for solving perfect-information games cannot be directly applied to bidding. Most bridge programs are based on human-designed rules, which, however, cannot cover all situations and are usually ambiguous and even conflicting with each other. In this paper, we, for the first time, propose a competitive bidding system based on deep learning techniques, which exhibits two novelties. First, we design a compact representation to encode the private and public information available to a player for bidding. Second, based on the analysis of the impact of other players’ unknown cards on one’s final rewards, we design two neural networks to deal with imperfect information, the first one inferring the cards of the partner and the second one taking the outputs of the first one as part of its input to select a bid. Experimental results show that our bidding system outperforms the top rule-based program. |
| Tasks | |
| Published | 2019-03-03 |
| URL | http://arxiv.org/abs/1903.00900v2 |
| http://arxiv.org/pdf/1903.00900v2.pdf | |
| PWC | https://paperswithcode.com/paper/competitive-bridge-bidding-with-deep-neural |
| Repo | |
| Framework | |
Context-Aware Zero-Shot Recognition
| Title | Context-Aware Zero-Shot Recognition |
| Authors | Ruotian Luo, Ning Zhang, Bohyung Han, Linjie Yang |
| Abstract | We present a novel problem setting in zero-shot learning, zero-shot object recognition and detection in the context. Contrary to the traditional zero-shot learning methods, which simply infers unseen categories by transferring knowledge from the objects belonging to semantically similar seen categories, we aim to understand the identity of the novel objects in an image surrounded by the known objects using the inter-object relation prior. Specifically, we leverage the visual context and the geometric relationships between all pairs of objects in a single image, and capture the information useful to infer unseen categories. We integrate our context-aware zero-shot learning framework into the traditional zero-shot learning techniques seamlessly using a Conditional Random Field (CRF). The proposed algorithm is evaluated on both zero-shot region classification and zero-shot detection tasks. The results on Visual Genome (VG) dataset show that our model significantly boosts performance with the additional visual context compared to traditional methods. |
| Tasks | Object Recognition, Zero-Shot Learning |
| Published | 2019-04-19 |
| URL | http://arxiv.org/abs/1904.09320v3 |
| http://arxiv.org/pdf/1904.09320v3.pdf | |
| PWC | https://paperswithcode.com/paper/190409320 |
| Repo | |
| Framework | |
DSConv: Efficient Convolution Operator
| Title | DSConv: Efficient Convolution Operator |
| Authors | Marcelo Gennari, Roger Fawcett, Victor Adrian Prisacariu |
| Abstract | Quantization is a popular way of increasing the speed and lowering the memory usage of Convolution Neural Networks (CNNs). When labelled training data is available, network weights and activations have successfully been quantized down to 1-bit. The same cannot be said about the scenario when labelled training data is not available, e.g. when quantizing a pre-trained model, where current approaches show, at best, no loss of accuracy at 8-bit quantizations. We introduce DSConv, a flexible quantized convolution operator that replaces single-precision operations with their far less expensive integer counterparts, while maintaining the probability distributions over both the kernel weights and the outputs. We test our model as a plug-and-play replacement for standard convolution on most popular neural network architectures, ResNet, DenseNet, GoogLeNet, AlexNet and VGG-Net and demonstrate state-of-the-art results, with less than 1% loss of accuracy, without retraining, using only 4-bit quantization. We also show how a distillation-based adaptation stage with unlabelled data can improve results even further. |
| Tasks | Quantization |
| Published | 2019-01-07 |
| URL | https://arxiv.org/abs/1901.01928v2 |
| https://arxiv.org/pdf/1901.01928v2.pdf | |
| PWC | https://paperswithcode.com/paper/dsconv-efficient-convolution-operator |
| Repo | |
| Framework | |
Sample Efficient Policy Gradient Methods with Recursive Variance Reduction
| Title | Sample Efficient Policy Gradient Methods with Recursive Variance Reduction |
| Authors | Pan Xu, Felicia Gao, Quanquan Gu |
| Abstract | Improving the sample efficiency in reinforcement learning has been a long-standing research problem. In this work, we aim to reduce the sample complexity of existing policy gradient methods. We propose a novel policy gradient algorithm called SRVR-PG, which only requires $O(1/\epsilon^{3/2})$ episodes to find an $\epsilon$-approximate stationary point of the nonconcave performance function $J(\boldsymbol{\theta})$ (i.e., $\boldsymbol{\theta}$ such that $\nabla J(\boldsymbol{\theta})_2^2\leq\epsilon$). This sample complexity improves the existing result $O(1/\epsilon^{5/3})$ for stochastic variance reduced policy gradient algorithms by a factor of $O(1/\epsilon^{1/6})$. In addition, we also propose a variant of SRVR-PG with parameter exploration, which explores the initial policy parameter from a prior probability distribution. We conduct numerical experiments on classic control problems in reinforcement learning to validate the performance of our proposed algorithms. |
| Tasks | Policy Gradient Methods |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.08610v2 |
| https://arxiv.org/pdf/1909.08610v2.pdf | |
| PWC | https://paperswithcode.com/paper/sample-efficient-policy-gradient-methods-with |
| Repo | |
| Framework | |
Unsupervised Intuitive Physics from Past Experiences
| Title | Unsupervised Intuitive Physics from Past Experiences |
| Authors | Sébastien Ehrhardt, Aron Monszpart, Niloy J. Mitra, Andrea Vedaldi |
| Abstract | We are interested in learning models of intuitive physics similar to the ones that animals use for navigation, manipulation and planning. In addition to learning general physical principles, however, we are also interested in learning ``on the fly’', from a few experiences, physical properties specific to new environments. We do all this in an unsupervised manner, using a meta-learning formulation where the goal is to predict videos containing demonstrations of physical phenomena, such as objects moving and colliding with a complex background. We introduce the idea of summarizing past experiences in a very compact manner, in our case using dynamic images, and show that this can be used to solve the problem well and efficiently. Empirically, we show via extensive experiments and ablation studies, that our model learns to perform physical predictions that generalize well in time and space, as well as to a variable number of interacting physical objects. | |
| Tasks | Meta-Learning |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1905.10793v1 |
| https://arxiv.org/pdf/1905.10793v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-intuitive-physics-from-past |
| Repo | |
| Framework | |
On the number of variables to use in principal component regression
| Title | On the number of variables to use in principal component regression |
| Authors | Ji Xu, Daniel Hsu |
| Abstract | We study least squares linear regression over $N$ uncorrelated Gaussian features that are selected in order of decreasing variance. When the number of selected features $p$ is at most the sample size $n$, the estimator under consideration coincides with the principal component regression estimator; when $p>n$, the estimator is the least $\ell_2$ norm solution over the selected features. We give an average-case analysis of the out-of-sample prediction error as $p,n,N \to \infty$ with $p/N \to \alpha$ and $n/N \to \beta$, for some constants $\alpha \in [0,1]$ and $\beta \in (0,1)$. In this average-case setting, the prediction error exhibits a “double descent” shape as a function of $p$. We also establish conditions under which the minimum risk is achieved in the interpolating ($p>n$) regime. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01139v2 |
| https://arxiv.org/pdf/1906.01139v2.pdf | |
| PWC | https://paperswithcode.com/paper/how-many-variables-should-be-entered-in-a |
| Repo | |
| Framework | |
A Non-Asymptotic Analysis of Network Independence for Distributed Stochastic Gradient Descent
| Title | A Non-Asymptotic Analysis of Network Independence for Distributed Stochastic Gradient Descent |
| Authors | Shi Pu, Alex Olshevsky, Ioannis Ch. Paschalidis |
| Abstract | This paper is concerned with minimizing the average of $n$ cost functions over a network, in which agents may communicate and exchange information with their peers in the network. Specifically, we consider the setting where only noisy gradient information is available. To solve the problem, we study the standard distributed stochastic gradient descent (DSGD) method and perform a non-asymptotic convergence analysis. For strongly convex and smooth objective functions, we not only show that DSGD asymptotically achieves the optimal network independent convergence rate compared to centralized stochastic gradient descent (SGD), but also explicitly identify the non-asymptotic convergence rate as a function of characteristics of the objective functions and the network. Furthermore, we derive the time needed for DSGD to approach the asymptotic convergence rate, which behaves as $K_T=\mathcal{O}(\frac{n}{(1-\rho_w)^2})$, where $(1-\rho_w)$ denotes the spectral gap of the mixing matrix of communicating agents. Finally, we construct a “hard” optimization problem for which we show the transient time needed for DSGD to approach the asymptotic convergence rate is lower bounded by $\Omega(\frac{n}{(1-\rho_w)^2})$, implying the sharpness of the obtained result. |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02702v9 |
| https://arxiv.org/pdf/1906.02702v9.pdf | |
| PWC | https://paperswithcode.com/paper/a-non-asymptotic-analysis-of-network |
| Repo | |
| Framework | |
Self-supervised learning of inverse problem solvers in medical imaging
| Title | Self-supervised learning of inverse problem solvers in medical imaging |
| Authors | Ortal Senouf, Sanketh Vedula, Tomer Weiss, Alex Bronstein, Oleg Michailovich, Michael Zibulevsky |
| Abstract | In the past few years, deep learning-based methods have demonstrated enormous success for solving inverse problems in medical imaging. In this work, we address the following question:\textit{Given a set of measurements obtained from real imaging experiments, what is the best way to use a learnable model and the physics of the modality to solve the inverse problem and reconstruct the latent image?} Standard supervised learning based methods approach this problem by collecting data sets of known latent images and their corresponding measurements. However, these methods are often impractical due to the lack of availability of appropriately sized training sets, and, more generally, due to the inherent difficulty in measuring the “groundtruth” latent image. In light of this, we propose a self-supervised approach to training inverse models in medical imaging in the absence of aligned data. Our method only requiring access to the measurements and the forward model at training. We showcase its effectiveness on inverse problems arising in accelerated magnetic resonance imaging (MRI). |
| Tasks | |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.09325v1 |
| https://arxiv.org/pdf/1905.09325v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-learning-of-inverse-problem |
| Repo | |
| Framework | |
Coronary Artery Plaque Characterization from CCTA Scans using Deep Learning and Radiomics
| Title | Coronary Artery Plaque Characterization from CCTA Scans using Deep Learning and Radiomics |
| Authors | Felix Denzinger, Michael Wels, Nishant Ravikumar, Katharina Breininger, Anika Reidelshöfer, Joachim Eckert, Michael Sühling, Axel Schmermund, Andreas Maier |
| Abstract | Assessing coronary artery plaque segments in coronary CT angiography scans is an important task to improve patient management and clinical outcomes, as it can help to decide whether invasive investigation and treatment are necessary. In this work, we present three machine learning approaches capable of performing this task. The first approach is based on radiomics, where a plaque segmentation is used to calculate various shape-, intensity- and texture-based features under different image transformations. A second approach is based on deep learning and relies on centerline extraction as sole prerequisite. In the third approach, we fuse the deep learning approach with radiomic features. On our data the methods reached similar scores as simulated fractional flow reserve (FFR) measurements, which - in contrast to our methods - requires an exact segmentation of the whole coronary tree and often time-consuming manual interaction. In literature, the performance of simulated FFR reaches an AUC between 0.79-0.93 predicting an abnormal invasive FFR that demands revascularization. The radiomics approach achieves an AUC of 0.86, the deep learning approach 0.84 and the combined method 0.88 for predicting the revascularization decision directly. While all three proposed methods can be determined within seconds, the FFR simulation typically takes several minutes. Provided representative training data in sufficient quantities, we believe that the presented methods can be used to create systems for fully automatic non-invasive risk assessment for a variety of adverse cardiac events. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06075v2 |
| https://arxiv.org/pdf/1912.06075v2.pdf | |
| PWC | https://paperswithcode.com/paper/coronary-artery-plaque-characterization-from |
| Repo | |
| Framework | |
Collaboration Analysis Using Deep Learning
| Title | Collaboration Analysis Using Deep Learning |
| Authors | Zhang Guo, Kevin Yu, Rebecca Pearlman, Nassir Navab, Roghayeh Barmaki |
| Abstract | The analysis of the collaborative learning process is one of the growing fields of education research, which has many different analytic solutions. In this paper, we provided a new solution to improve automated collaborative learning analyses using deep neural networks. Instead of using self-reported questionnaires, which are subject to bias and noise, we automatically extract group-working information by object recognition results using Mask R-CNN method. This process is based on detecting the people and other objects from pictures and video clips of the collaborative learning process, then evaluate the mobile learning performance using the collaborative indicators. We tested our approach to automatically evaluate the group-work collaboration in a controlled study of thirty-three dyads while performing an anatomy body painting intervention. The results indicate that our approach recognizes the differences of collaborations among teams of treatment and control groups in the case study. This work introduces new methods for automated quality prediction of collaborations among human-human interactions using computer vision techniques. |
| Tasks | Object Recognition |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08066v1 |
| http://arxiv.org/pdf/1904.08066v1.pdf | |
| PWC | https://paperswithcode.com/paper/collaboration-analysis-using-deep-learning |
| Repo | |
| Framework | |
Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks
| Title | Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks |
| Authors | Zenan Ling, Haotian Ma, Yu Yang, Robert C. Qiu, Song-Chun Zhu, Quanshi Zhang |
| Abstract | In this paper, we propose to disentangle and interpret contextual effects that are encoded in a pre-trained deep neural network. We use our method to explain the gaming strategy of the alphaGo Zero model. Unlike previous studies that visualized image appearances corresponding to the network output or a neural activation only from a global perspective, our research aims to clarify how a certain input unit (dimension) collaborates with other units (dimensions) to constitute inference patterns of the neural network and thus contribute to the network output. The analysis of local contextual effects w.r.t. certain input units is of special values in real applications. Explaining the logic of the alphaGo Zero model is a typical application. In experiments, our method successfully disentangled the rationale of each move during the Go game. |
| Tasks | |
| Published | 2019-01-08 |
| URL | http://arxiv.org/abs/1901.02184v1 |
| http://arxiv.org/pdf/1901.02184v1.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-alphago-interpreting-contextual |
| Repo | |
| Framework | |
How Language-Neutral is Multilingual BERT?
| Title | How Language-Neutral is Multilingual BERT? |
| Authors | Jindřich Libovický, Rudolf Rosa, Alexander Fraser |
| Abstract | Multilingual BERT (mBERT) provides sentence representations for 104 languages, which are useful for many multi-lingual tasks. Previous work probed the cross-linguality of mBERT using zero-shot transfer learning on morphological and syntactic tasks. We instead focus on the semantic properties of mBERT. We show that mBERT representations can be split into a language-specific component and a language-neutral component, and that the language-neutral component is sufficiently general in terms of modeling semantics to allow high-accuracy word-alignment and sentence retrieval but is not yet good enough for the more difficult task of MT quality estimation. Our work presents interesting challenges which must be solved to build better language-neutral representations, particularly for tasks requiring linguistic transfer of semantics. |
| Tasks | Transfer Learning, Word Alignment |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03310v1 |
| https://arxiv.org/pdf/1911.03310v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-language-neutral-is-multilingual-bert |
| Repo | |
| Framework | |
Decentralized Learning of Generative Adversarial Networks from Non-iid Data
| Title | Decentralized Learning of Generative Adversarial Networks from Non-iid Data |
| Authors | Ryo Yonetani, Tomohiro Takahashi, Atsushi Hashimoto, Yoshitaka Ushiku |
| Abstract | This work addresses a new problem that learns generative adversarial networks (GANs) from multiple data collections that are each i) owned separately by different clients and ii) drawn from a non-identical distribution that comprises different classes. Given such non-iid data as input, we aim to learn a distribution involving all the classes input data can belong to, while keeping the data decentralized in each client storage. Our key contribution to this end is a new decentralized approach for learning GANs from non-iid data called Forgiver-First Update (F2U), which a) asks clients to train an individual discriminator with their own data and b) updates a generator to fool the most `forgiving’ discriminators who deem generated samples as the most real. Our theoretical analysis proves that this updating strategy allows the decentralized GAN to achieve a generator’s distribution with all the input classes as its global optimum based on f-divergence minimization. Moreover, we propose a relaxed version of F2U called Forgiver-First Aggregation (F2A) that performs well in practice, which adaptively aggregates the discriminators while emphasizing forgiving ones. Our empirical evaluations with image generation tasks demonstrated the effectiveness of our approach over state-of-the-art decentralized learning methods. | |
| Tasks | Image Generation |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09684v2 |
| https://arxiv.org/pdf/1905.09684v2.pdf | |
| PWC | https://paperswithcode.com/paper/decentralized-learning-of-generative |
| Repo | |
| Framework | |
