Paper Group ANR 509
Classification of Diabetic Retinopathy Images Using Multi-Class Multiple-Instance Learning Based on Color Correlogram Features. Creation of an Annotated Corpus of Spanish Radiology Reports. Adversarial Variational Bayes Methods for Tweedie Compound Poisson Mixed Models. Adaptive PCA for Time-Varying Data. Model-based Catheter Segmentation in MRI-im …
Classification of Diabetic Retinopathy Images Using Multi-Class Multiple-Instance Learning Based on Color Correlogram Features
| Title | Classification of Diabetic Retinopathy Images Using Multi-Class Multiple-Instance Learning Based on Color Correlogram Features |
| Authors | Ragav Venkatesan, Parag S. Chandakkar, Baoxin Li |
| Abstract | All people with diabetes have the risk of developing diabetic retinopathy (DR), a vision-threatening complication. Early detection and timely treatment can reduce the occurrence of blindness due to DR. Computer-aided diagnosis has the potential benefit of improving the accuracy and speed in DR detection. This study is concerned with automatic classification of images with microaneurysm (MA) and neovascularization (NV), two important DR clinical findings. Together with normal images, this presents a 3-class classification problem. We propose a modified color auto-correlogram feature (AutoCC) with low dimensionality that is spectrally tuned towards DR images. Recognizing the fact that the images with or without MA or NV are generally different only in small, localized regions, we propose to employ a multi-class, multiple-instance learning framework for performing the classification task using the proposed feature. Extensive experiments including comparison with a few state-of-art image classification approaches have been performed and the results suggest that the proposed approach is promising as it outperforms other methods by a large margin. |
| Tasks | Image Classification, Multiple Instance Learning |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01264v1 |
| http://arxiv.org/pdf/1704.01264v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-of-diabetic-retinopathy-images |
| Repo | |
| Framework | |
Creation of an Annotated Corpus of Spanish Radiology Reports
| Title | Creation of an Annotated Corpus of Spanish Radiology Reports |
| Authors | Viviana Cotik, Darío Filippo, Roland Roller, Hans Uszkoreit, Feiyu Xu |
| Abstract | This paper presents a new annotated corpus of 513 anonymized radiology reports written in Spanish. Reports were manually annotated with entities, negation and uncertainty terms and relations. The corpus was conceived as an evaluation resource for named entity recognition and relation extraction algorithms, and as input for the use of supervised methods. Biomedical annotated resources are scarce due to confidentiality issues and associated costs. This work provides some guidelines that could help other researchers to undertake similar tasks. |
| Tasks | Named Entity Recognition, Relation Extraction |
| Published | 2017-10-30 |
| URL | http://arxiv.org/abs/1710.11154v1 |
| http://arxiv.org/pdf/1710.11154v1.pdf | |
| PWC | https://paperswithcode.com/paper/creation-of-an-annotated-corpus-of-spanish |
| Repo | |
| Framework | |
Adversarial Variational Bayes Methods for Tweedie Compound Poisson Mixed Models
| Title | Adversarial Variational Bayes Methods for Tweedie Compound Poisson Mixed Models |
| Authors | Yaodong Yang, Rui Luo, Yuanyuan Liu |
| Abstract | The Tweedie Compound Poisson-Gamma model is routinely used for modeling non-negative continuous data with a discrete probability mass at zero. Mixed models with random effects account for the covariance structure related to the grouping hierarchy in the data. An important application of Tweedie mixed models is pricing the insurance policies, e.g. car insurance. However, the intractable likelihood function, the unknown variance function, and the hierarchical structure of mixed effects have presented considerable challenges for drawing inferences on Tweedie. In this study, we tackle the Bayesian Tweedie mixed-effects models via variational inference approaches. In particular, we empower the posterior approximation by implicit models trained in an adversarial setting. To reduce the variance of gradients, we reparameterize random effects, and integrate out one local latent variable of Tweedie. We also employ a flexible hyper prior to ensure the richness of the approximation. Our method is evaluated on both simulated and real-world data. Results show that the proposed method has smaller estimation bias on the random effects compared to traditional inference methods including MCMC; it also achieves a state-of-the-art predictive performance, meanwhile offering a richer estimation of the variance function. |
| Tasks | |
| Published | 2017-06-16 |
| URL | http://arxiv.org/abs/1706.05446v5 |
| http://arxiv.org/pdf/1706.05446v5.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-variational-bayes-methods-for |
| Repo | |
| Framework | |
Adaptive PCA for Time-Varying Data
| Title | Adaptive PCA for Time-Varying Data |
| Authors | Salaheddin Alakkari, John Dingliana |
| Abstract | In this paper, we present an online adaptive PCA algorithm that is able to compute the full dimensional eigenspace per new time-step of sequential data. The algorithm is based on a one-step update rule that considers all second order correlations between previous samples and the new time-step. Our algorithm has O(n) complexity per new time-step in its deterministic mode and O(1) complexity per new time-step in its stochastic mode. We test our algorithm on a number of time-varying datasets of different physical phenomena. Explained variance curves indicate that our technique provides an excellent approximation to the original eigenspace computed using standard PCA in batch mode. In addition, our experiments show that the stochastic mode, despite its much lower computational complexity, converges to the same eigenspace computed using the deterministic mode. |
| Tasks | |
| Published | 2017-09-07 |
| URL | http://arxiv.org/abs/1709.02373v2 |
| http://arxiv.org/pdf/1709.02373v2.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-pca-for-time-varying-data |
| Repo | |
| Framework | |
Model-based Catheter Segmentation in MRI-images
| Title | Model-based Catheter Segmentation in MRI-images |
| Authors | Andre Mastmeyer, Guillaume Pernelle, Lauren Barber, Steve Pieper, Dirk Fortmeier, Sandy Wells, Heinz Handels, Tina Kapur |
| Abstract | Accurate and reliable segmentation of catheters in MR-gui- ded interventions remains a challenge, and a step of critical importance in clinical workflows. In this work, under reasonable assumptions, me- chanical model based heuristics guide the segmentation process allows correct catheter identification rates greater than 98% (error 2.88 mm), and reduction in outliers to one-fourth compared to the state of the art. Given distal tips, searching towards the proximal ends of the catheters is guided by mechanical models that are estimated on a per-catheter basis. Their bending characteristics are used to constrain the image fea- ture based candidate points. The final catheter trajectories are hybrid sequences of individual points, each derived from model and image fea- tures. We evaluate the method on a database of 10 patient MRI scans including 101 manually segmented catheters. The mean errors were 1.40 mm and the median errors were 1.05 mm. The number of outliers devi- ating more than 2 mm from the gold standard is 7, and the number of outliers deviating more than 3 mm from the gold standard is just 2. |
| Tasks | |
| Published | 2017-05-18 |
| URL | http://arxiv.org/abs/1705.06712v1 |
| http://arxiv.org/pdf/1705.06712v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-based-catheter-segmentation-in-mri |
| Repo | |
| Framework | |
Deep Semantic Classification for 3D LiDAR Data
| Title | Deep Semantic Classification for 3D LiDAR Data |
| Authors | Ayush Dewan, Gabriel L. Oliveira, Wolfram Burgard |
| Abstract | Robots are expected to operate autonomously in dynamic environments. Understanding the underlying dynamic characteristics of objects is a key enabler for achieving this goal. In this paper, we propose a method for pointwise semantic classification of 3D LiDAR data into three classes: non-movable, movable and dynamic. We concentrate on understanding these specific semantics because they characterize important information required for an autonomous system. Non-movable points in the scene belong to unchanging segments of the environment, whereas the remaining classes corresponds to the changing parts of the scene. The difference between the movable and dynamic class is their motion state. The dynamic points can be perceived as moving, whereas movable objects can move, but are perceived as static. To learn the distinction between movable and non-movable points in the environment, we introduce an approach based on deep neural network and for detecting the dynamic points, we estimate pointwise motion. We propose a Bayes filter framework for combining the learned semantic cues with the motion cues to infer the required semantic classification. In extensive experiments, we compare our approach with other methods on a standard benchmark dataset and report competitive results in comparison to the existing state-of-the-art. Furthermore, we show an improvement in the classification of points by combining the semantic cues retrieved from the neural network with the motion cues. |
| Tasks | |
| Published | 2017-06-26 |
| URL | http://arxiv.org/abs/1706.08355v1 |
| http://arxiv.org/pdf/1706.08355v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-semantic-classification-for-3d-lidar |
| Repo | |
| Framework | |
Contextualizing Citations for Scientific Summarization using Word Embeddings and Domain Knowledge
| Title | Contextualizing Citations for Scientific Summarization using Word Embeddings and Domain Knowledge |
| Authors | Arman Cohan, Nazli Goharian |
| Abstract | Citation texts are sometimes not very informative or in some cases inaccurate by themselves; they need the appropriate context from the referenced paper to reflect its exact contributions. To address this problem, we propose an unsupervised model that uses distributed representation of words as well as domain knowledge to extract the appropriate context from the reference paper. Evaluation results show the effectiveness of our model by significantly outperforming the state-of-the-art. We furthermore demonstrate how an effective contextualization method results in improving citation-based summarization of the scientific articles. |
| Tasks | Word Embeddings |
| Published | 2017-05-23 |
| URL | http://arxiv.org/abs/1705.08063v1 |
| http://arxiv.org/pdf/1705.08063v1.pdf | |
| PWC | https://paperswithcode.com/paper/contextualizing-citations-for-scientific |
| Repo | |
| Framework | |
Do Convolutional Networks need to be Deep for Text Classification ?
| Title | Do Convolutional Networks need to be Deep for Text Classification ? |
| Authors | Hoa T. Le, Christophe Cerisara, Alexandre Denis |
| Abstract | We study in this work the importance of depth in convolutional models for text classification, either when character or word inputs are considered. We show on 5 standard text classification and sentiment analysis tasks that deep models indeed give better performances than shallow networks when the text input is represented as a sequence of characters. However, a simple shallow-and-wide network outperforms deep models such as DenseNet with word inputs. Our shallow word model further establishes new state-of-the-art performances on two datasets: Yelp Binary (95.9%) and Yelp Full (64.9%). |
| Tasks | Sentiment Analysis, Text Classification |
| Published | 2017-07-13 |
| URL | http://arxiv.org/abs/1707.04108v1 |
| http://arxiv.org/pdf/1707.04108v1.pdf | |
| PWC | https://paperswithcode.com/paper/do-convolutional-networks-need-to-be-deep-for |
| Repo | |
| Framework | |
Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space
| Title | Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space |
| Authors | José Miguel Hernández-Lobato, James Requeima, Edward O. Pyzer-Knapp, Alán Aspuru-Guzik |
| Abstract | Chemical space is so large that brute force searches for new interesting molecules are infeasible. High-throughput virtual screening via computer cluster simulations can speed up the discovery process by collecting very large amounts of data in parallel, e.g., up to hundreds or thousands of parallel measurements. Bayesian optimization (BO) can produce additional acceleration by sequentially identifying the most useful simulations or experiments to be performed next. However, current BO methods cannot scale to the large numbers of parallel measurements and the massive libraries of molecules currently used in high-throughput screening. Here, we propose a scalable solution based on a parallel and distributed implementation of Thompson sampling (PDTS). We show that, in small scale problems, PDTS performs similarly as parallel expected improvement (EI), a batch version of the most widely used BO heuristic. Additionally, in settings where parallel EI does not scale, PDTS outperforms other scalable baselines such as a greedy search, $\epsilon$-greedy approaches and a random search method. These results show that PDTS is a successful solution for large-scale parallel BO. |
| Tasks | |
| Published | 2017-06-06 |
| URL | http://arxiv.org/abs/1706.01825v1 |
| http://arxiv.org/pdf/1706.01825v1.pdf | |
| PWC | https://paperswithcode.com/paper/parallel-and-distributed-thompson-sampling |
| Repo | |
| Framework | |
Learning Binary Residual Representations for Domain-specific Video Streaming
| Title | Learning Binary Residual Representations for Domain-specific Video Streaming |
| Authors | Yi-Hsuan Tsai, Ming-Yu Liu, Deqing Sun, Ming-Hsuan Yang, Jan Kautz |
| Abstract | We study domain-specific video streaming. Specifically, we target a streaming setting where the videos to be streamed from a server to a client are all in the same domain and they have to be compressed to a small size for low-latency transmission. Several popular video streaming services, such as the video game streaming services of GeForce Now and Twitch, fall in this category. While conventional video compression standards such as H.264 are commonly used for this task, we hypothesize that one can leverage the property that the videos are all in the same domain to achieve better video quality. Based on this hypothesis, we propose a novel video compression pipeline. Specifically, we first apply H.264 to compress domain-specific videos. We then train a novel binary autoencoder to encode the leftover domain-specific residual information frame-by-frame into binary representations. These binary representations are then compressed and sent to the client together with the H.264 stream. In our experiments, we show that our pipeline yields consistent gains over standard H.264 compression across several benchmark datasets while using the same channel bandwidth. |
| Tasks | Video Compression |
| Published | 2017-12-14 |
| URL | http://arxiv.org/abs/1712.05087v1 |
| http://arxiv.org/pdf/1712.05087v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-binary-residual-representations-for |
| Repo | |
| Framework | |
Improving Part-of-Speech Tagging for NLP Pipelines
| Title | Improving Part-of-Speech Tagging for NLP Pipelines |
| Authors | Vishaal Jatav, Ravi Teja, Srini Bharadwaj, Venkat Srinivasan |
| Abstract | This paper outlines the results of sentence level linguistics based rules for improving part-of-speech tagging. It is well known that the performance of complex NLP systems is negatively affected if one of the preliminary stages is less than perfect. Errors in the initial stages in the pipeline have a snowballing effect on the pipeline’s end performance. We have created a set of linguistics based rules at the sentence level which adjust part-of-speech tags from state-of-the-art taggers. Comparison with state-of-the-art taggers on widely used benchmarks demonstrate significant improvements in tagging accuracy and consequently in the quality and accuracy of NLP systems. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2017-08-01 |
| URL | http://arxiv.org/abs/1708.00241v1 |
| http://arxiv.org/pdf/1708.00241v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-part-of-speech-tagging-for-nlp |
| Repo | |
| Framework | |
The Devil is in the Tails: Fine-grained Classification in the Wild
| Title | The Devil is in the Tails: Fine-grained Classification in the Wild |
| Authors | Grant Van Horn, Pietro Perona |
| Abstract | The world is long-tailed. What does this mean for computer vision and visual recognition? The main two implications are (1) the number of categories we need to consider in applications can be very large, and (2) the number of training examples for most categories can be very small. Current visual recognition algorithms have achieved excellent classification accuracy. However, they require many training examples to reach peak performance, which suggests that long-tailed distributions will not be dealt with well. We analyze this question in the context of eBird, a large fine-grained classification dataset, and a state-of-the-art deep network classification algorithm. We find that (a) peak classification performance on well-represented categories is excellent, (b) given enough data, classification performance suffers only minimally from an increase in the number of classes, (c) classification performance decays precipitously as the number of training examples decreases, (d) surprisingly, transfer learning is virtually absent in current methods. Our findings suggest that our community should come to grips with the question of long tails. |
| Tasks | Transfer Learning |
| Published | 2017-09-05 |
| URL | http://arxiv.org/abs/1709.01450v1 |
| http://arxiv.org/pdf/1709.01450v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-devil-is-in-the-tails-fine-grained |
| Repo | |
| Framework | |
Lower bounds over Boolean inputs for deep neural networks with ReLU gates
| Title | Lower bounds over Boolean inputs for deep neural networks with ReLU gates |
| Authors | Anirbit Mukherjee, Amitabh Basu |
| Abstract | Motivated by the resurgence of neural networks in being able to solve complex learning tasks we undertake a study of high depth networks using ReLU gates which implement the function $x \mapsto \max{0,x}$. We try to understand the role of depth in such neural networks by showing size lowerbounds against such network architectures in parameter regimes hitherto unexplored. In particular we show the following two main results about neural nets computing Boolean functions of input dimension $n$, 1. We use the method of random restrictions to show almost linear, $\Omega(\epsilon^{2(1-\delta)}n^{1-\delta})$, lower bound for completely weight unrestricted LTF-of-ReLU circuits to match the Andreev function on at least $\frac{1}{2} +\epsilon$ fraction of the inputs for $\epsilon > \sqrt{2\frac{\log^{\frac {2}{2-\delta}}(n)}{n}}$ for any $\delta \in (0,\frac 1 2)$ 2. We use the method of sign-rank to show exponential in dimension lower bounds for ReLU circuits ending in a LTF gate and of depths upto $O(n^{\xi})$ with $\xi < \frac{1}{8}$ with some restrictions on the weights in the bottom most layer. All other weights in these circuits are kept unrestricted. This in turns also implies the same lowerbounds for LTF circuits with the same architecture and the same weight restrictions on their bottom most layer. Along the way we also show that there exists a $\mathbb{R}^ n\rightarrow \mathbb{R}$ Sum-of-ReLU-of-ReLU function which Sum-of-ReLU neural nets can never represent no matter how large they are allowed to be. |
| Tasks | |
| Published | 2017-11-08 |
| URL | http://arxiv.org/abs/1711.03073v2 |
| http://arxiv.org/pdf/1711.03073v2.pdf | |
| PWC | https://paperswithcode.com/paper/lower-bounds-over-boolean-inputs-for-deep |
| Repo | |
| Framework | |
A Nonlinear Kernel Support Matrix Machine for Matrix Learning
| Title | A Nonlinear Kernel Support Matrix Machine for Matrix Learning |
| Authors | Yunfei Ye |
| Abstract | In many problems of supervised tensor learning (STL), real world data such as face images or MRI scans are naturally represented as matrices, which are also called as second order tensors. Most existing classifiers based on tensor representation, such as support tensor machine (STM) need to solve iteratively which occupy much time and may suffer from local minima. In this paper, we present a kernel support matrix machine (KSMM) to perform supervised learning when data are represented as matrices. KSMM is a general framework for the construction of matrix-based hyperplane to exploit structural information. We analyze a unifying optimization problem for which we propose an asymptotically convergent algorithm. Theoretical analysis for the generalization bounds is derived based on Rademacher complexity with respect to a probability distribution. We demonstrate the merits of the proposed method by exhaustive experiments on both simulation study and a number of real-word datasets from a variety of application domains. |
| Tasks | |
| Published | 2017-07-20 |
| URL | http://arxiv.org/abs/1707.06487v2 |
| http://arxiv.org/pdf/1707.06487v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-nonlinear-kernel-support-matrix-machine-for |
| Repo | |
| Framework | |
Consistency Results for Stationary Autoregressive Processes with Constrained Coefficients
| Title | Consistency Results for Stationary Autoregressive Processes with Constrained Coefficients |
| Authors | Alessio Sancetta |
| Abstract | We consider stationary autoregressive processes with coefficients restricted to an ellipsoid, which includes autoregressive processes with absolutely summable coefficients. We provide consistency results under different norms for the estimation of such processes using constrained and penalized estimators. As an application we show some weak form of universal consistency. Simulations show that directly including the constraint in the estimation can lead to more robust results. |
| Tasks | |
| Published | 2017-06-08 |
| URL | http://arxiv.org/abs/1706.02492v1 |
| http://arxiv.org/pdf/1706.02492v1.pdf | |
| PWC | https://paperswithcode.com/paper/consistency-results-for-stationary |
| Repo | |
| Framework | |
