Paper Group ANR 352
Learning Model Bias. Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network. Bregman-divergence-guided Legendre exponential dispersion model with finite cumulants (K-LED). Flow Rate Control in Smart District Heating Systems Using Deep Reinforcement Learning. On the Convergence of SARAH …
Learning Model Bias
| Title | Learning Model Bias |
| Authors | Jonathan Baxter |
| Abstract | In this paper the problem of {\em learning} appropriate domain-specific bias is addressed. It is shown that this can be achieved by learning many related tasks from the same domain, and a theorem is given bounding the number tasks that must be learnt. A corollary of the theorem is that if the tasks are known to possess a common {\em internal representation} or {\em preprocessing} then the number of examples required per task for good generalisation when learning $n$ tasks simultaneously scales like $O(a + \frac{b}{n})$, where $O(a)$ is a bound on the minimum number of examples required to learn a single task, and $O(a + b)$ is a bound on the number of examples required to learn each task independently. An experiment providing strong qualitative support for the theoretical results is reported. |
| Tasks | |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06164v1 |
| https://arxiv.org/pdf/1911.06164v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-model-bias |
| Repo | |
| Framework | |
Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network
| Title | Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network |
| Authors | Jivitesh Sharma, Ole-Christoffer Granmo, Morten Goodwin |
| Abstract | In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Frequency Cepstral Coefficients (GFCC), the Constant Q-transform (CQT) and Chromagram. Such multiple features have never been used before for signal or audio processing. And, we employ a deeper CNN (DCNN) compared to previous models, consisting of spatially separable convolutions working on time and feature domain separately. Alongside, we use attention modules that perform channel and spatial attention together. We use some data augmentation techniques to further boost performance. Our model is able to achieve state-of-the-art performance on all three benchmark environment sound classification datasets, i.e. the UrbanSound8K (97.52%), ESC-10 (95.75%) and ESC-50 (88.50%). To the best of our knowledge, this is the first time that a single environment sound classification model is able to achieve state-of-the-art results on all three datasets. For ESC-10 and ESC-50 datasets, the accuracy achieved by the proposed model is beyond human accuracy of 95.7% and 81.3% respectively. |
| Tasks | Data Augmentation |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.11219v6 |
| https://arxiv.org/pdf/1908.11219v6.pdf | |
| PWC | https://paperswithcode.com/paper/environment-sound-classification-using |
| Repo | |
| Framework | |
Bregman-divergence-guided Legendre exponential dispersion model with finite cumulants (K-LED)
| Title | Bregman-divergence-guided Legendre exponential dispersion model with finite cumulants (K-LED) |
| Authors | Hyenkyun Woo |
| Abstract | Exponential dispersion model is a useful framework in machine learning and statistics. Primarily, thanks to the additive structure of the model, it can be achieved without difficulty to estimate parameters including mean. However, tight conditions on cumulant function, such as analyticity, strict convexity, and steepness, reduce the class of exponential dispersion model. In this work, we present relaxed exponential dispersion model K-LED (Legendre exponential dispersion model with K cumulants). The cumulant function of the proposed model is a convex function of Legendre type having continuous partial derivatives of K-th order on the interior of a convex domain. Most of the K-LED models are developed via Bregman-divergence-guided log-concave density function with coercivity shape constraints. The main advantage of the proposed model is that the first cumulant (or the mean parameter space) of the 1-LED model is easily computed through the extended global optimum property of Bregman divergence. An extended normal distribution is introduced as an example of 1-LED based on Tweedie distribution. On top of that, we present 2-LED satisfying mean-variance relation of quasi-likelihood function. There is an equivalence between a subclass of quasi-likelihood function and a regular 2-LED model, of which the canonical parameter space is open. A typical example is a regular 2-LED model with power variance function, i.e., a variance is in proportion to the power of the mean of observations. This model is equivalent to a subclass of beta-divergence (or a subclass of quasi-likelihood function with power variance function). Furthermore, a new parameterized K-LED model, the cumulant function of which is the convex extended logistic loss function, is proposed. This model includes Bernoulli distribution and Poisson distribution. |
| Tasks | |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.03025v1 |
| https://arxiv.org/pdf/1910.03025v1.pdf | |
| PWC | https://paperswithcode.com/paper/bregman-divergence-guided-legendre |
| Repo | |
| Framework | |
Flow Rate Control in Smart District Heating Systems Using Deep Reinforcement Learning
| Title | Flow Rate Control in Smart District Heating Systems Using Deep Reinforcement Learning |
| Authors | Tinghao Zhang, Jing Luo, Ping Chen, Jie Liu |
| Abstract | At high latitudes, many cities adopt a centralized heating system to improve the energy generation efficiency and to reduce pollution. In multi-tier systems, so-called district heating, there are a few efficient approaches for the flow rate control during the heating process. In this paper, we describe the theoretical methods to solve this problem by deep reinforcement learning and propose a cloud-based heating control system for implementation. A real-world case study shows the effectiveness and practicability of the proposed system controlled by humans, and the simulated experiments for deep reinforcement learning show about 1985.01 gigajoules of heat quantity and 42276.45 tons of water are saved per hour compared with manual control. |
| Tasks | |
| Published | 2019-12-01 |
| URL | https://arxiv.org/abs/1912.05313v1 |
| https://arxiv.org/pdf/1912.05313v1.pdf | |
| PWC | https://paperswithcode.com/paper/flow-rate-control-in-smart-district-heating |
| Repo | |
| Framework | |
On the Convergence of SARAH and Beyond
| Title | On the Convergence of SARAH and Beyond |
| Authors | Bingcong Li, Meng Ma, Georgios B. Giannakis |
| Abstract | The main theme of this work is a unifying algorithm, \textbf{L}oop\textbf{L}ess \textbf{S}ARAH (L2S) for problems formulated as summation of $n$ individual loss functions. L2S broadens a recently developed variance reduction method known as SARAH. To find an $\epsilon$-accurate solution, L2S enjoys a complexity of ${\cal O}\big( (n+\kappa) \ln (1/\epsilon)\big)$ for strongly convex problems. For convex problems, when adopting an $n$-dependent step size, the complexity of L2S is ${\cal O}(n+ \sqrt{n}/\epsilon)$; while for more frequently adopted $n$-independent step size, the complexity is ${\cal O}(n+ n/\epsilon)$. Distinct from SARAH, our theoretical findings support an $n$-independent step size in convex problems without extra assumptions. For nonconvex problems, the complexity of L2S is ${\cal O}(n+ \sqrt{n}/\epsilon)$. Our numerical tests on neural networks suggest that L2S can have better generalization properties than SARAH. Along with L2S, our side results include the linear convergence of the last iteration for SARAH in strongly convex problems. |
| Tasks | |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02351v2 |
| https://arxiv.org/pdf/1906.02351v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-convergence-of-sarah-and-beyond |
| Repo | |
| Framework | |
Semi-supervised Learning with Graphs: Covariance Based Superpixels For Hyperspectral Image Classification
| Title | Semi-supervised Learning with Graphs: Covariance Based Superpixels For Hyperspectral Image Classification |
| Authors | Philip Sellars, Angelica Aviles-Rivero, Nicolas Papadakis, David Coomes, Anita Faul, Carola-Bibane Schönlieb |
| Abstract | In this paper, we present a graph-based semi-supervised framework for hyperspectral image classification. We first introduce a novel superpixel algorithm based on the spectral covariance matrix representation of pixels to provide a better representation of our data. We then construct a superpixel graph, based on carefully considered feature vectors, before performing classification. We demonstrate, through a set of experimental results using two benchmarking datasets, that our approach outperforms three state-of-the-art classification frameworks, especially when an extremely small amount of labelled data is used. |
| Tasks | Hyperspectral Image Classification, Image Classification |
| Published | 2019-01-14 |
| URL | https://arxiv.org/abs/1901.04240v4 |
| https://arxiv.org/pdf/1901.04240v4.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-with-graphs |
| Repo | |
| Framework | |
Stereo-based Multi-motion Visual Odometry for Mobile Robots
| Title | Stereo-based Multi-motion Visual Odometry for Mobile Robots |
| Authors | Qing Zhao, Bin Luo, Yun Zhang |
| Abstract | With the development of computer vision, visual odometry is adopted by more and more mobile robots. However, we found that not only its own pose, but the poses of other moving objects are also crucial for the decision of the robot. In addition, the visual odometry will be greatly disturbed when a significant moving object appears. In this letter, a stereo-based multi-motion visual odometry method is proposed to acquire the poses of the robot and other moving objects. In order to obtain the poses simultaneously, a continuous motion segmentation module and a coordinate conversion module are applied to the traditional visual odometry pipeline. As a result, poses of all moving objects can be acquired and transformed into the ground coordinate system. The experimental results show that the proposed multi-motion visual odometry can effectively eliminate the influence of moving objects on the visual odometry, as well as achieve 10 cm in position and 3{\deg} in orientation RMSE (Root Mean Square Error) of each moving object. |
| Tasks | Motion Segmentation, Visual Odometry |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06607v1 |
| https://arxiv.org/pdf/1910.06607v1.pdf | |
| PWC | https://paperswithcode.com/paper/stereo-based-multi-motion-visual-odometry-for |
| Repo | |
| Framework | |
Defining Admissible Rewards for High Confidence Policy Evaluation
| Title | Defining Admissible Rewards for High Confidence Policy Evaluation |
| Authors | Niranjani Prasad, Barbara E Engelhardt, Finale Doshi-Velez |
| Abstract | A key impediment to reinforcement learning (RL) in real applications with limited, batch data is defining a reward function that reflects what we implicitly know about reasonable behaviour for a task and allows for robust off-policy evaluation. In this work, we develop a method to identify an admissible set of reward functions for policies that (a) do not diverge too far from past behaviour, and (b) can be evaluated with high confidence, given only a collection of past trajectories. Together, these ensure that we propose policies that we trust to be implemented in high-risk settings. We demonstrate our approach to reward design on synthetic domains as well as in a critical care context, for a reward that consolidates clinical objectives to learn a policy for weaning patients from mechanical ventilation. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.13167v1 |
| https://arxiv.org/pdf/1905.13167v1.pdf | |
| PWC | https://paperswithcode.com/paper/defining-admissible-rewards-for-high |
| Repo | |
| Framework | |
Reachability and Differential based Heuristics for Solving Markov Decision Processes
| Title | Reachability and Differential based Heuristics for Solving Markov Decision Processes |
| Authors | Shoubhik Debnath, Lantao Liu, Gaurav Sukhatme |
| Abstract | The solution convergence of Markov Decision Processes (MDPs) can be accelerated by prioritized sweeping of states ranked by their potential impacts to other states. In this paper, we present new heuristics to speed up the solution convergence of MDPs. First, we quantify the level of reachability of every state using the Mean First Passage Time (MFPT) and show that such reachability characterization very well assesses the importance of states which is used for effective state prioritization. Then, we introduce the notion of backup differentials as an extension to the prioritized sweeping mechanism, in order to evaluate the impacts of states at an even finer scale. Finally, we extend the state prioritization to the temporal process, where only partial sweeping can be performed during certain intermediate value iteration stages. To validate our design, we have performed numerical evaluations by comparing the proposed new heuristics with corresponding classic baseline mechanisms. The evaluation results showed that our reachability based framework and its differential variants have outperformed the state-of-the-art solutions in terms of both practical runtime and number of iterations. |
| Tasks | |
| Published | 2019-01-03 |
| URL | http://arxiv.org/abs/1901.00921v1 |
| http://arxiv.org/pdf/1901.00921v1.pdf | |
| PWC | https://paperswithcode.com/paper/reachability-and-differential-based |
| Repo | |
| Framework | |
Semi-supervised Learning with Contrastive Predicative Coding
| Title | Semi-supervised Learning with Contrastive Predicative Coding |
| Authors | Jiaxing Wang, Yin Zheng, Xiaoshuang Chen, Junzhou Huang, Jian Cheng |
| Abstract | Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, many of them have thus far been either inflexible, inefficient or non-scalable. This paper explores recently developed contrastive predictive coding technique to improve discriminative power of deep learning models when a large portion of labels are absent. Two models, cpc-SSL and a class conditional variant~(ccpc-SSL) are presented. They effectively exploit the unlabeled data by extracting shared information between different parts of the (high-dimensional) data. The proposed approaches are inductive, and scale well to very large datasets like ImageNet, making them good candidates in real-world large scale applications. |
| Tasks | |
| Published | 2019-05-25 |
| URL | https://arxiv.org/abs/1905.10514v1 |
| https://arxiv.org/pdf/1905.10514v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-with-contrastive |
| Repo | |
| Framework | |
CeliacNet: Celiac Disease Severity Diagnosis on Duodenal Histopathological Images Using Deep Residual Networks
| Title | CeliacNet: Celiac Disease Severity Diagnosis on Duodenal Histopathological Images Using Deep Residual Networks |
| Authors | Rasoul Sali, Lubaina Ehsan, Kamran Kowsari, Marium Khan, Christopher A. Moskaluk, Sana Syed, Donald E. Brown |
| Abstract | Celiac Disease (CD) is a chronic autoimmune disease that affects the small intestine in genetically predisposed children and adults. Gluten exposure triggers an inflammatory cascade which leads to compromised intestinal barrier function. If this enteropathy is unrecognized, this can lead to anemia, decreased bone density, and, in longstanding cases, intestinal cancer. The prevalence of the disorder is 1% in the United States. An intestinal (duodenal) biopsy is considered the “gold standard” for diagnosis. The mild CD might go unnoticed due to non-specific clinical symptoms or mild histologic features. In our current work, we trained a model based on deep residual networks to diagnose CD severity using a histological scoring system called the modified Marsh score. The proposed model was evaluated using an independent set of 120 whole slide images from 15 CD patients and achieved an AUC greater than 0.96 in all classes. These results demonstrate the diagnostic power of the proposed model for CD severity classification using histological images. |
| Tasks | |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.03084v1 |
| https://arxiv.org/pdf/1910.03084v1.pdf | |
| PWC | https://paperswithcode.com/paper/celiacnet-celiac-disease-severity-diagnosis |
| Repo | |
| Framework | |
Learning Occlusion-Aware View Synthesis for Light Fields
| Title | Learning Occlusion-Aware View Synthesis for Light Fields |
| Authors | Julia Navarro, Neus Sabater |
| Abstract | In this work, we present a novel learning-based approach to synthesize new views of a light field image. In particular, given the four corner views of a light field, the presented method estimates any in-between view. We use three sequential convolutional neural networks for feature extraction, scene geometry estimation and view selection. Compared to state-of-the-art approaches, in order to handle occlusions we propose to estimate a different disparity map per view. Jointly with the view selection network, this strategy shows to be the most important to have proper reconstructions near object boundaries. Ablation studies and comparison against the state of the art on Lytro light fields show the superior performance of the proposed method. Furthermore, the method is adapted and tested on light fields with wide baselines acquired with a camera array and, in spite of having to deal with large occluded areas, the proposed approach yields very promising results. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11271v1 |
| https://arxiv.org/pdf/1905.11271v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-occlusion-aware-view-synthesis-for |
| Repo | |
| Framework | |
Subspace clustering without knowing the number of clusters: A parameter free approach
| Title | Subspace clustering without knowing the number of clusters: A parameter free approach |
| Authors | Vishnu Menon, Gokularam M, Sheetal Kalyani |
| Abstract | Subspace clustering, the task of clustering high dimensional data when the data points come from a union of subspaces is one of the fundamental tasks in unsupervised machine learning. Most of the existing algorithms for this task require prior knowledge of the number of clusters along with few additional parameters which need to be set or tuned apriori according to the type of data to be clustered. In this work, a parameter free method for subspace clustering is proposed, where the data points are clustered on the basis of the difference in statistical distribution of the angles subtended by the data points within a subspace and those by points belonging to different subspaces. Given an initial fine clustering, the proposed algorithm merges the clusters until a final clustering is obtained. This, unlike many existing methods, does not require the number of clusters apriori. Also, the proposed algorithm does not involve the use of an unknown parameter or tuning for one. %through cross validation. A parameter free method for producing a fine initial clustering is also discussed, making the whole process of subspace clustering parameter free. The comparison of proposed algorithm’s performance with that of the existing state-of-the-art techniques in synthetic and real data sets, shows the significance of the proposed method. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04406v2 |
| https://arxiv.org/pdf/1909.04406v2.pdf | |
| PWC | https://paperswithcode.com/paper/subspace-clustering-without-knowing-the |
| Repo | |
| Framework | |
Forward-Backward Splitting for Optimal Transport based Problems
| Title | Forward-Backward Splitting for Optimal Transport based Problems |
| Authors | Guillermo Ortiz-Jimenez, Mireille El Gheche, Effrosyni Simou, Hermina Petric Maretic, Pascal Frossard |
| Abstract | Optimal transport aims to estimate a transportation plan that minimizes a displacement cost. This is realized by optimizing the scalar product between the sought plan and the given cost, over the space of doubly stochastic matrices. When the entropy regularization is added to the problem, the transportation plan can be efficiently computed with the Sinkhorn algorithm. Thanks to this breakthrough, optimal transport has been progressively extended to machine learning and statistical inference by introducing additional application-specific terms in the problem formulation. It is however challenging to design efficient optimization algorithms for optimal transport based extensions. To overcome this limitation, we devise a general forward-backward splitting algorithm based on Bregman distances for solving a wide range of optimization problems involving a differentiable function with Lipschitz-continuous gradient and a doubly stochastic constraint. We illustrate the efficiency of our approach in the context of continuous domain adaptation. Experiments show that the proposed method leads to a significant improvement in terms of speed and performance with respect to the state of the art for domain adaptation on a continually rotating distribution coming from the standard two moon dataset. |
| Tasks | Domain Adaptation |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.11448v3 |
| https://arxiv.org/pdf/1909.11448v3.pdf | |
| PWC | https://paperswithcode.com/paper/cdot-continuous-domain-adaptation-using |
| Repo | |
| Framework | |
An Analytical Workflow for Clustering Forensic Images
| Title | An Analytical Workflow for Clustering Forensic Images |
| Authors | Sara Mousavi, Dylan Lee, Tatianna Griffin, Dawnie Steadman, Audris Mockus |
| Abstract | Large collections of images, if curated, drastically contribute to the quality of research in many domains. Unsupervised clustering is an intuitive, yet effective step towards curating such datasets. In this work, we present a workflow for unsupervisedly clustering a large collection of forensic images. The workflow utilizes classic clustering on deep feature representation of the images in addition to domain-related data to group them together. Our manual evaluation shows a purity of 89% for the resulted clusters. |
| Tasks | |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/2001.05845v1 |
| https://arxiv.org/pdf/2001.05845v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-analytical-workflow-for-clustering |
| Repo | |
| Framework | |
