Paper Group ANR 1070
Classification of normal/abnormal heart sound recordings based on multi-domain features and back propagation neural network. Triple Attention Mixed Link Network for Single Image Super Resolution. On Regularized Losses for Weakly-supervised CNN Segmentation. High Dimensional Bayesian Optimization Using Dropout. IDD: A Dataset for Exploring Problems …
Classification of normal/abnormal heart sound recordings based on multi-domain features and back propagation neural network
Title | Classification of normal/abnormal heart sound recordings based on multi-domain features and back propagation neural network |
Authors | Hong Tang, Huaming Chen, Ting Li, Mingjun Zhong |
Abstract | This paper aims to classify a single PCG recording as normal or abnormal for computer-aided diagnosis. The proposed framework for this challenge has four steps: preprocessing, feature extraction, training and validation. In the preprocessing step, a recording is segmented into four states, i.e., the first heart sound, systolic interval, the second heart sound, and diastolic interval by the Springer Segmentation algorithm. In the feature extraction step, the authors extract 324 features from multi-domains to perform classification. A back propagation neural network is used as predication model. The optimal threshold for distinguishing normal and abnormal is determined by the statistics of model output for both normal and abnormal. The performance of the proposed predictor tested by the six training sets is sensitivity 0.812 and specificity 0.860 (overall accuracy is 0.836). However, the performance reduces to sensitivity 0.807 and specificity 0.829 (overall accuracy is 0.818) for the hidden test set. |
Tasks | |
Published | 2018-10-17 |
URL | http://arxiv.org/abs/1810.09253v1 |
http://arxiv.org/pdf/1810.09253v1.pdf | |
PWC | https://paperswithcode.com/paper/classification-of-normalabnormal-heart-sound |
Repo | |
Framework | |
Triple Attention Mixed Link Network for Single Image Super Resolution
Title | Triple Attention Mixed Link Network for Single Image Super Resolution |
Authors | Xi Cheng, Xiang Li, Jian Yang |
Abstract | Single image super resolution is of great importance as a low-level computer vision task. Recent approaches with deep convolutional neural networks have achieved im-pressive performance. However, existing architectures have limitations due to the less sophisticated structure along with less strong representational power. In this work, to significantly enhance the feature representation, we proposed Triple Attention mixed link Network (TAN) which consists of 1) three different aspects (i.e., kernel, spatial and channel) of attention mechanisms and 2) fu-sion of both powerful residual and dense connections (i.e., mixed link). Specifically, the network with multi kernel learns multi hierarchical representations under different receptive fields. The output features are recalibrated by the effective kernel and channel attentions and feed into next layer partly residual and partly dense, which filters the information and enable the network to learn more powerful representations. The features finally pass through the spatial attention in the reconstruction network which generates a fusion of local and global information, let the network restore more details and improves the quality of reconstructed images. Thanks to the diverse feature recalibrations and the advanced information flow topology, our proposed model is strong enough to per-form against the state-of-the-art methods on the bench-mark evaluations. |
Tasks | Image Super-Resolution, Super-Resolution |
Published | 2018-10-08 |
URL | http://arxiv.org/abs/1810.03254v1 |
http://arxiv.org/pdf/1810.03254v1.pdf | |
PWC | https://paperswithcode.com/paper/triple-attention-mixed-link-network-for |
Repo | |
Framework | |
On Regularized Losses for Weakly-supervised CNN Segmentation
Title | On Regularized Losses for Weakly-supervised CNN Segmentation |
Authors | Meng Tang, Federico Perazzi, Abdelaziz Djelouah, Ismail Ben Ayed, Christopher Schroers, Yuri Boykov |
Abstract | Minimization of regularized losses is a principled approach to weak supervision well-established in deep learning, in general. However, it is largely overlooked in semantic segmentation currently dominated by methods mimicking full supervision via “fake” fully-labeled training masks (proposals) generated from available partial input. To obtain such full masks the typical methods explicitly use standard regularization techniques for “shallow” segmentation, e.g. graph cuts or dense CRFs. In contrast, we integrate such standard regularizers directly into the loss functions over partial input. This approach simplifies weakly-supervised training by avoiding extra MRF/CRF inference steps or layers explicitly generating full masks, while improving both the quality and efficiency of training. This paper proposes and experimentally compares different losses integrating MRF/CRF regularization terms. We juxtapose our regularized losses with earlier proposal-generation methods using explicit regularization steps or layers. Our approach achieves state-of-the-art accuracy in semantic segmentation with near full-supervision quality. |
Tasks | Semantic Segmentation |
Published | 2018-03-26 |
URL | http://arxiv.org/abs/1803.09569v2 |
http://arxiv.org/pdf/1803.09569v2.pdf | |
PWC | https://paperswithcode.com/paper/on-regularized-losses-for-weakly-supervised |
Repo | |
Framework | |
High Dimensional Bayesian Optimization Using Dropout
Title | High Dimensional Bayesian Optimization Using Dropout |
Authors | Cheng Li, Sunil Gupta, Santu Rana, Vu Nguyen, Svetha Venkatesh, Alistair Shilton |
Abstract | Scaling Bayesian optimization to high dimensions is challenging task as the global optimization of high-dimensional acquisition function can be expensive and often infeasible. Existing methods depend either on limited active variables or the additive form of the objective function. We propose a new method for high-dimensional Bayesian optimization, that uses a dropout strategy to optimize only a subset of variables at each iteration. We derive theoretical bounds for the regret and show how it can inform the derivation of our algorithm. We demonstrate the efficacy of our algorithms for optimization on two benchmark functions and two real-world applications- training cascade classifiers and optimizing alloy composition. |
Tasks | |
Published | 2018-02-15 |
URL | http://arxiv.org/abs/1802.05400v1 |
http://arxiv.org/pdf/1802.05400v1.pdf | |
PWC | https://paperswithcode.com/paper/high-dimensional-bayesian-optimization-using |
Repo | |
Framework | |
IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments
Title | IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments |
Authors | Girish Varma, Anbumani Subramanian, Anoop Namboodiri, Manmohan Chandraker, C V Jawahar |
Abstract | While several datasets for autonomous navigation have become available in recent years, they tend to focus on structured driving environments. This usually corresponds to well-delineated infrastructure such as lanes, a small number of well-defined categories for traffic participants, low variation in object or background appearance and strict adherence to traffic rules. We propose IDD, a novel dataset for road scene understanding in unstructured environments where the above assumptions are largely not satisfied. It consists of 10,004 images, finely annotated with 34 classes collected from 182 drive sequences on Indian roads. The label set is expanded in comparison to popular benchmarks such as Cityscapes, to account for new classes. It also reflects label distributions of road scenes significantly different from existing datasets, with most classes displaying greater within-class diversity. Consistent with real driving behaviours, it also identifies new classes such as drivable areas besides the road. We propose a new four-level label hierarchy, which allows varying degrees of complexity and opens up possibilities for new training methods. Our empirical study provides an in-depth analysis of the label characteristics. State-of-the-art methods for semantic segmentation achieve much lower accuracies on our dataset, demonstrating its distinction compared to Cityscapes. Finally, we propose that our dataset is an ideal opportunity for new problems such as domain adaptation, few-shot learning and behaviour prediction in road scenes. |
Tasks | Autonomous Navigation, Domain Adaptation, Few-Shot Learning, Scene Understanding, Semantic Segmentation |
Published | 2018-11-26 |
URL | http://arxiv.org/abs/1811.10200v1 |
http://arxiv.org/pdf/1811.10200v1.pdf | |
PWC | https://paperswithcode.com/paper/idd-a-dataset-for-exploring-problems-of |
Repo | |
Framework | |
CrystalGAN: Learning to Discover Crystallographic Structures with Generative Adversarial Networks
Title | CrystalGAN: Learning to Discover Crystallographic Structures with Generative Adversarial Networks |
Authors | Asma Nouira, Nataliya Sokolovska, Jean-Claude Crivello |
Abstract | Our main motivation is to propose an efficient approach to generate novel multi-element stable chemical compounds that can be used in real world applications. This task can be formulated as a combinatorial problem, and it takes many hours of human experts to construct, and to evaluate new data. Unsupervised learning methods such as Generative Adversarial Networks (GANs) can be efficiently used to produce new data. Cross-domain Generative Adversarial Networks were reported to achieve exciting results in image processing applications. However, in the domain of materials science, there is a need to synthesize data with higher order complexity compared to observed samples, and the state-of-the-art cross-domain GANs can not be adapted directly. In this contribution, we propose a novel GAN called CrystalGAN which generates new chemically stable crystallographic structures with increased domain complexity. We introduce an original architecture, we provide the corresponding loss functions, and we show that the CrystalGAN generates very reasonable data. We illustrate the efficiency of the proposed method on a real original problem of novel hydrides discovery that can be further used in development of hydrogen storage materials. |
Tasks | |
Published | 2018-10-26 |
URL | https://arxiv.org/abs/1810.11203v3 |
https://arxiv.org/pdf/1810.11203v3.pdf | |
PWC | https://paperswithcode.com/paper/crystalgan-learning-to-discover |
Repo | |
Framework | |
DSNet for Real-Time Driving Scene Semantic Segmentation
Title | DSNet for Real-Time Driving Scene Semantic Segmentation |
Authors | Wenfu Wang, Zhijie Pan |
Abstract | We focus on the very challenging task of semantic segmentation for autonomous driving system. It must deliver decent semantic segmentation result for traffic critical objects real-time. In this paper, we propose a very efficient yet powerful deep neural network for driving scene semantic segmentation termed as Driving Segmentation Network (DSNet). DSNet achieves state-of-the-art balance between accuracy and inference speed through efficient units and architecture design inspired by ShuffleNet V2 and ENet. More importantly, DSNet highlights classes most critical with driving decision making through our novel Driving Importance-weighted Loss. We evaluate DSNet on Cityscapes dataset, our DSNet achieves 71.8% mean Intersection-over-Union (IoU) on validation set and 69.3% on test set. Class-wise IoU scores show that Driving Importance-weighted Loss could improve most driving critical classes by a large margin. Compared with ENet, DSNet is 18.9% more accurate and 1.1+ times faster which implies great potential for autonomous driving application. |
Tasks | Autonomous Driving, Decision Making, Semantic Segmentation |
Published | 2018-12-06 |
URL | https://arxiv.org/abs/1812.07049v2 |
https://arxiv.org/pdf/1812.07049v2.pdf | |
PWC | https://paperswithcode.com/paper/dsnet-for-real-time-driving-scene-semantic |
Repo | |
Framework | |
Semi-Supervised Domain Adaptation with Representation Learning for Semantic Segmentation across Time
Title | Semi-Supervised Domain Adaptation with Representation Learning for Semantic Segmentation across Time |
Authors | Assia Benbihi, Matthieu Geist, Cédric Pradalier |
Abstract | Deep learning generates state-of-the-art semantic segmentation provided that a large number of images together with pixel-wise annotations are available. To alleviate the expensive data collection process, we propose a semi-supervised domain adaptation method for the specific case of images with similar semantic content but different pixel distributions. A network trained with supervision on a past dataset is finetuned on the new dataset to conserve its features maps. The domain adaptation becomes a simple regression between feature maps and does not require annotations on the new dataset. This method reaches performances similar to classic transfer learning on the PASCAL VOC dataset with synthetic transformations. |
Tasks | Domain Adaptation, Representation Learning, Semantic Segmentation, Transfer Learning |
Published | 2018-05-10 |
URL | https://arxiv.org/abs/1805.04141v2 |
https://arxiv.org/pdf/1805.04141v2.pdf | |
PWC | https://paperswithcode.com/paper/deep-representation-learning-for-domain |
Repo | |
Framework | |
Patch-Based Sparse Representation For Bacterial Detection
Title | Patch-Based Sparse Representation For Bacterial Detection |
Authors | Ahmed Karam Eldaly, Yoann Altmann, Ahsan Akram, Antonios Perperidis, Kevin Dhaliwal, Stephen McLaughlin |
Abstract | In this paper, we propose an unsupervised approach for bacterial detection in optical endomicroscopy images. This approach splits each image into a set of overlapping patches and assumes that observed intensities are linear combinations of the actual intensity values associated with background image structures, corrupted by additive Gaussian noise and potentially by a sparse outlier term modelling anomalies (which are considered to be candidate bacteria). The actual intensity term representing background structures is modelled as a linear combination of a few atoms drawn from a dictionary which is learned from bacteria-free data and then fixed while analyzing new images. The bacteria detection task is formulated as a minimization problem and an alternating direction method of multipliers (ADMM) is then used to estimate the unknown parameters. Simulations conducted using two ex vivo lung datasets show good detection and correlation performance between bacteria counts identified by a trained clinician and those of the proposed method. |
Tasks | |
Published | 2018-10-29 |
URL | http://arxiv.org/abs/1810.12043v2 |
http://arxiv.org/pdf/1810.12043v2.pdf | |
PWC | https://paperswithcode.com/paper/patch-based-sparse-representation-for |
Repo | |
Framework | |
3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network
Title | 3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network |
Authors | Hongming Shan, Yi Zhang, Qingsong Yang, Uwe Kruger, Mannudeep K. Kalra, Ling Sun, Wenxiang Cong, Ge Wang |
Abstract | Low-dose computed tomography (CT) has attracted a major attention in the medical imaging field, since CT-associated x-ray radiation carries health risks for patients. The reduction of CT radiation dose, however, compromises the signal-to-noise ratio, and may compromise the image quality and the diagnostic performance. Recently, deep-learning-based algorithms have achieved promising results in low-dose CT denoising, especially convolutional neural network (CNN) and generative adversarial network (GAN). This article introduces a Contracting Path-based Convolutional Encoder-decoder (CPCE) network in 2D and 3D configurations within the GAN framework for low-dose CT denoising. A novel feature of our approach is that an initial 3D CPCE denoising model can be directly obtained by extending a trained 2D CNN and then fine-tuned to incorporate 3D spatial information from adjacent slices. Based on the transfer learning from 2D to 3D, the 3D network converges faster and achieves a better denoising performance than that trained from scratch. By comparing the CPCE with recently published methods based on the simulated Mayo dataset and the real MGH dataset, we demonstrate that the 3D CPCE denoising model has a better performance, suppressing image noise and preserving subtle structures. |
Tasks | Computed Tomography (CT), Denoising, Transfer Learning |
Published | 2018-02-15 |
URL | http://arxiv.org/abs/1802.05656v2 |
http://arxiv.org/pdf/1802.05656v2.pdf | |
PWC | https://paperswithcode.com/paper/3d-convolutional-encoder-decoder-network-for |
Repo | |
Framework | |
Learning to Teach
Title | Learning to Teach |
Authors | Yang Fan, Fei Tian, Tao Qin, Xiang-Yang Li, Tie-Yan Liu |
Abstract | Teaching plays a very important role in our society, by spreading human knowledge and educating our next generations. A good teacher will select appropriate teaching materials, impact suitable methodologies, and set up targeted examinations, according to the learning behaviors of the students. In the field of artificial intelligence, however, one has not fully explored the role of teaching, and pays most attention to machine \emph{learning}. In this paper, we argue that equal attention, if not more, should be paid to teaching, and furthermore, an optimization framework (instead of heuristics) should be used to obtain good teaching strategies. We call this approach `learning to teach’. In the approach, two intelligent agents interact with each other: a student model (which corresponds to the learner in traditional machine learning algorithms), and a teacher model (which determines the appropriate data, loss function, and hypothesis space to facilitate the training of the student model). The teacher model leverages the feedback from the student model to optimize its own teaching strategies by means of reinforcement learning, so as to achieve teacher-student co-evolution. To demonstrate the practical value of our proposed approach, we take the training of deep neural networks (DNN) as an example, and show that by using the learning to teach techniques, we are able to use much less training data and fewer iterations to achieve almost the same accuracy for different kinds of DNN models (e.g., multi-layer perceptron, convolutional neural networks and recurrent neural networks) under various machine learning tasks (e.g., image classification and text understanding). | |
Tasks | Image Classification |
Published | 2018-05-09 |
URL | http://arxiv.org/abs/1805.03643v1 |
http://arxiv.org/pdf/1805.03643v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-to-teach |
Repo | |
Framework | |
Deep Learning vs. Human Graders for Classifying Severity Levels of Diabetic Retinopathy in a Real-World Nationwide Screening Program
Title | Deep Learning vs. Human Graders for Classifying Severity Levels of Diabetic Retinopathy in a Real-World Nationwide Screening Program |
Authors | Paisan Raumviboonsuk, Jonathan Krause, Peranut Chotcomwongse, Rory Sayres, Rajiv Raman, Kasumi Widner, Bilson J L Campana, Sonia Phene, Kornwipa Hemarat, Mongkol Tadarati, Sukhum Silpa-Acha, Jirawut Limwattanayingyong, Chetan Rao, Oscar Kuruvilla, Jesse Jung, Jeffrey Tan, Surapong Orprayoon, Chawawat Kangwanwongpaisan, Ramase Sukulmalpaiboon, Chainarong Luengchaichawang, Jitumporn Fuangkaew, Pipat Kongsap, Lamyong Chualinpha, Sarawuth Saree, Srirat Kawinpanitan, Korntip Mitvongsa, Siriporn Lawanasakol, Chaiyasit Thepchatri, Lalita Wongpichedchai, Greg S Corrado, Lily Peng, Dale R Webster |
Abstract | Deep learning algorithms have been used to detect diabetic retinopathy (DR) with specialist-level accuracy. This study aims to validate one such algorithm on a large-scale clinical population, and compare the algorithm performance with that of human graders. 25,326 gradable retinal images of patients with diabetes from the community-based, nation-wide screening program of DR in Thailand were analyzed for DR severity and referable diabetic macular edema (DME). Grades adjudicated by a panel of international retinal specialists served as the reference standard. Across different severity levels of DR for determining referable disease, deep learning significantly reduced the false negative rate (by 23%) at the cost of slightly higher false positive rates (2%). Deep learning algorithms may serve as a valuable tool for DR screening. |
Tasks | |
Published | 2018-10-18 |
URL | http://arxiv.org/abs/1810.08290v1 |
http://arxiv.org/pdf/1810.08290v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-learning-vs-human-graders-for |
Repo | |
Framework | |
A Sheaf Model of Contradictions and Disagreements. Preliminary Report and Discussion
Title | A Sheaf Model of Contradictions and Disagreements. Preliminary Report and Discussion |
Authors | Wlodek Zadrozny, Luciana Garbayo |
Abstract | We introduce a new formal model – based on the mathematical construct of sheaves – for representing contradictory information in textual sources. This model has the advantage of letting us (a) identify the causes of the inconsistency; (b) measure how strong it is; (c) and do something about it, e.g. suggest ways to reconcile inconsistent advice. This model naturally represents the distinction between contradictions and disagreements. It is based on the idea of representing natural language sentences as formulas with parameters sitting on lattices, creating partial orders based on predicates shared by theories, and building sheaves on these partial orders with products of lattices as stalks. Degrees of disagreement are measured by the existence of global and local sections. Limitations of the sheaf approach and connections to recent work in natural language processing, as well as the topics of contextuality in physics, data fusion, topological data analysis and epistemology are also discussed. |
Tasks | Topological Data Analysis |
Published | 2018-01-27 |
URL | http://arxiv.org/abs/1801.09036v1 |
http://arxiv.org/pdf/1801.09036v1.pdf | |
PWC | https://paperswithcode.com/paper/a-sheaf-model-of-contradictions-and |
Repo | |
Framework | |
Efficient Algorithms and Lower Bounds for Robust Linear Regression
Title | Efficient Algorithms and Lower Bounds for Robust Linear Regression |
Authors | Ilias Diakonikolas, Weihao Kong, Alistair Stewart |
Abstract | We study the problem of high-dimensional linear regression in a robust model where an $\epsilon$-fraction of the samples can be adversarially corrupted. We focus on the fundamental setting where the covariates of the uncorrupted samples are drawn from a Gaussian distribution $\mathcal{N}(0, \Sigma)$ on $\mathbb{R}^d$. We give nearly tight upper bounds and computational lower bounds for this problem. Specifically, our main contributions are as follows: For the case that the covariance matrix is known to be the identity, we give a sample near-optimal and computationally efficient algorithm that outputs a candidate hypothesis vector $\widehat{\beta}$ which approximates the unknown regression vector $\beta$ within $\ell_2$-norm $O(\epsilon \log(1/\epsilon) \sigma)$, where $\sigma$ is the standard deviation of the random observation noise. An error of $\Omega (\epsilon \sigma)$ is information-theoretically necessary, even with infinite sample size. Prior work gave an algorithm for this problem with sample complexity $\tilde{\Omega}(d^2/\epsilon^2)$ whose error guarantee scales with the $\ell_2$-norm of $\beta$. For the case of unknown covariance, we show that we can efficiently achieve the same error guarantee as in the known covariance case using an additional $\tilde{O}(d^2/\epsilon^2)$ unlabeled examples. On the other hand, an error of $O(\epsilon \sigma)$ can be information-theoretically attained with $O(d/\epsilon^2)$ samples. We prove a Statistical Query (SQ) lower bound providing evidence that this quadratic tradeoff in the sample size is inherent. More specifically, we show that any polynomial time SQ learning algorithm for robust linear regression (in Huber’s contamination model) with estimation complexity $O(d^{2-c})$, where $c>0$ is an arbitrarily small constant, must incur an error of $\Omega(\sqrt{\epsilon} \sigma)$. |
Tasks | |
Published | 2018-05-31 |
URL | http://arxiv.org/abs/1806.00040v1 |
http://arxiv.org/pdf/1806.00040v1.pdf | |
PWC | https://paperswithcode.com/paper/efficient-algorithms-and-lower-bounds-for |
Repo | |
Framework | |
Theory of Generative Deep Learning : Probe Landscape of Empirical Error via Norm Based Capacity Control
Title | Theory of Generative Deep Learning : Probe Landscape of Empirical Error via Norm Based Capacity Control |
Authors | Wendi Xu, Ming Zhang |
Abstract | Despite its remarkable empirical success as a highly competitive branch of artificial intelligence, deep learning is often blamed for its widely known low interpretation and lack of firm and rigorous mathematical foundation. However, most theoretical endeavor is devoted in discriminative deep learning case, whose complementary part is generative deep learning. To the best of our knowledge, we firstly highlight landscape of empirical error in generative case to complete the full picture through exquisite design of image super resolution under norm based capacity control. Our theoretical advance in interpretation of the training dynamic is achieved from both mathematical and biological sides. |
Tasks | Image Super-Resolution, Super-Resolution |
Published | 2018-10-03 |
URL | http://arxiv.org/abs/1810.01622v1 |
http://arxiv.org/pdf/1810.01622v1.pdf | |
PWC | https://paperswithcode.com/paper/theory-of-generative-deep-learning-probe |
Repo | |
Framework | |