Paper Group ANR 439
Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model. On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don’t Worry About Its Nonsmooth Loss Function. Unsupervised word segmentation and lexicon discovery using acoustic word embeddings. Generalized Exponential Concentration Inequality for Rényi Div …
Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model
| Title | Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model |
| Authors | Qixiang Ye, Tianliang Zhang, Qiang Qiu, Baochang Zhang, Jie Chen, Guillermo Sapiro |
| Abstract | In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human’ annotation involved. The self-learning approach is deployed as progressive steps of object discovery, object enforcement, and label propagation. In the learning procedure, object locations in each frame are treated as latent variables that are solved with a progressive latent model (PLM). Compared with conventional latent models, the proposed PLM incorporates a spatial regularization term to reduce ambiguities in object proposals and to enforce object localization, and also a graph-based label propagation to discover harder instances in adjacent frames. With the difference of convex (DC) objective functions, PLM can be efficiently optimized with a concave-convex programming and thus guaranteeing the stability of self-learning. Extensive experiments demonstrate that even without annotation the proposed self-learning approach outperforms weakly supervised learning approaches, while achieving comparable performance with transfer learning and fully supervised approaches. |
| Tasks | Object Localization, Pedestrian Detection, Transfer Learning |
| Published | 2016-11-22 |
| URL | http://arxiv.org/abs/1611.07544v1 |
| http://arxiv.org/pdf/1611.07544v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-learning-scene-specific-pedestrian |
| Repo | |
| Framework | |
On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don’t Worry About Its Nonsmooth Loss Function
| Title | On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don’t Worry About Its Nonsmooth Loss Function |
| Authors | Xingguo Li, Haoming Jiang, Jarvis Haupt, Raman Arora, Han Liu, Mingyi Hong, Tuo Zhao |
| Abstract | Many machine learning techniques sacrifice convenient computational structures to gain estimation robustness and modeling flexibility. However, by exploring the modeling structures, we find these “sacrifices” do not always require more computational efforts. To shed light on such a “free-lunch” phenomenon, we study the square-root-Lasso (SQRT-Lasso) type regression problem. Specifically, we show that the nonsmooth loss functions of SQRT-Lasso type regression ease tuning effort and gain adaptivity to inhomogeneous noise, but is not necessarily more challenging than Lasso in computation. We can directly apply proximal algorithms (e.g. proximal gradient descent, proximal Newton, and proximal Quasi-Newton algorithms) without worrying the nonsmoothness of the loss function. Theoretically, we prove that the proximal algorithms combined with the pathwise optimization scheme enjoy fast convergence guarantees with high probability. Numerical results are provided to support our theory. |
| Tasks | |
| Published | 2016-05-25 |
| URL | http://arxiv.org/abs/1605.07950v6 |
| http://arxiv.org/pdf/1605.07950v6.pdf | |
| PWC | https://paperswithcode.com/paper/on-fast-convergence-of-proximal-algorithms |
| Repo | |
| Framework | |
Unsupervised word segmentation and lexicon discovery using acoustic word embeddings
| Title | Unsupervised word segmentation and lexicon discovery using acoustic word embeddings |
| Authors | Herman Kamper, Aren Jansen, Sharon Goldwater |
| Abstract | In settings where only unlabelled speech data is available, speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. A similar problem is faced when modelling infant language acquisition. In these cases, categorical linguistic structure needs to be discovered directly from speech audio. We present a novel unsupervised Bayesian model that segments unlabelled speech and clusters the segments into hypothesized word groupings. The result is a complete unsupervised tokenization of the input speech in terms of discovered word types. In our approach, a potential word segment (of arbitrary length) is embedded in a fixed-dimensional acoustic vector space. The model, implemented as a Gibbs sampler, then builds a whole-word acoustic model in this space while jointly performing segmentation. We report word error rates in a small-vocabulary connected digit recognition task by mapping the unsupervised decoded output to ground truth transcriptions. The model achieves around 20% error rate, outperforming a previous HMM-based system by about 10% absolute. Moreover, in contrast to the baseline, our model does not require a pre-specified vocabulary size. |
| Tasks | Language Acquisition, Language Modelling, Tokenization, Word Embeddings |
| Published | 2016-03-09 |
| URL | http://arxiv.org/abs/1603.02845v1 |
| http://arxiv.org/pdf/1603.02845v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-word-segmentation-and-lexicon |
| Repo | |
| Framework | |
Generalized Exponential Concentration Inequality for Rényi Divergence Estimation
| Title | Generalized Exponential Concentration Inequality for Rényi Divergence Estimation |
| Authors | Shashank Singh, Barnabás Póczos |
| Abstract | Estimating divergences in a consistent way is of great importance in many machine learning tasks. Although this is a fundamental problem in nonparametric statistics, to the best of our knowledge there has been no finite sample exponential inequality convergence bound derived for any divergence estimators. The main contribution of our work is to provide such a bound for an estimator of R'enyi-$\alpha$ divergence for a smooth H"older class of densities on the $d$-dimensional unit cube $[0, 1]^d$. We also illustrate our theoretical results with a numerical experiment. |
| Tasks | |
| Published | 2016-03-28 |
| URL | http://arxiv.org/abs/1603.08589v1 |
| http://arxiv.org/pdf/1603.08589v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-exponential-concentration |
| Repo | |
| Framework | |
Unsupervised Domain Adaptation Using Approximate Label Matching
| Title | Unsupervised Domain Adaptation Using Approximate Label Matching |
| Authors | Jordan T. Ash, Robert E. Schapire, Barbara E. Engelhardt |
| Abstract | Domain adaptation addresses the problem created when training data is generated by a so-called source distribution, but test data is generated by a significantly different target distribution. In this work, we present approximate label matching (ALM), a new unsupervised domain adaptation technique that creates and leverages a rough labeling on the test samples, then uses these noisy labels to learn a transformation that aligns the source and target samples. We show that the transformation estimated by ALM has favorable properties compared to transformations estimated by other methods, which do not use any kind of target labeling. Our model is regularized by requiring that a classifier trained to discriminate source from transformed target samples cannot distinguish between the two. We experiment with ALM on simulated and real data, and show that it outperforms techniques commonly used in the field. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2016-02-16 |
| URL | http://arxiv.org/abs/1602.04889v3 |
| http://arxiv.org/pdf/1602.04889v3.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-using |
| Repo | |
| Framework | |
Node-Adapt, Path-Adapt and Tree-Adapt:Model-Transfer Domain Adaptation for Random Forest
| Title | Node-Adapt, Path-Adapt and Tree-Adapt:Model-Transfer Domain Adaptation for Random Forest |
| Authors | Azadeh S. Mozafari, David Vazquez, Mansour Jamzad, Antonio M. Lopez |
| Abstract | Random Forest (RF) is a successful paradigm for learning classifiers due to its ability to learn from large feature spaces and seamlessly integrate multi-class classification, as well as the achieved accuracy and processing efficiency. However, as many other classifiers, RF requires domain adaptation (DA) provided that there is a mismatch between the training (source) and testing (target) domains which provokes classification degradation. Consequently, different RF-DA methods have been proposed, which not only require target-domain samples but revisiting the source-domain ones, too. As novelty, we propose three inherently different methods (Node-Adapt, Path-Adapt and Tree-Adapt) that only require the learned source-domain RF and a relatively few target-domain samples for DA, i.e. source-domain samples do not need to be available. To assess the performance of our proposals we focus on image-based object detection, using the pedestrian detection problem as challenging proof-of-concept. Moreover, we use the RF with expert nodes because it is a competitive patch-based pedestrian model. We test our Node-, Path- and Tree-Adapt methods in standard benchmarks, showing that DA is largely achieved. |
| Tasks | Domain Adaptation, Object Detection, Pedestrian Detection |
| Published | 2016-11-09 |
| URL | http://arxiv.org/abs/1611.02886v1 |
| http://arxiv.org/pdf/1611.02886v1.pdf | |
| PWC | https://paperswithcode.com/paper/node-adapt-path-adapt-and-tree-adaptmodel |
| Repo | |
| Framework | |
Reduced Memory Region Based Deep Convolutional Neural Network Detection
| Title | Reduced Memory Region Based Deep Convolutional Neural Network Detection |
| Authors | Denis Tome’, Luca Bondi, Emanuele Plebani, Luca Baroffio, Danilo Pau, Stefano Tubaro |
| Abstract | Accurate pedestrian detection has a primary role in automotive safety: for example, by issuing warnings to the driver or acting actively on car’s brakes, it helps decreasing the probability of injuries and human fatalities. In order to achieve very high accuracy, recent pedestrian detectors have been based on Convolutional Neural Networks (CNN). Unfortunately, such approaches require vast amounts of computational power and memory, preventing efficient implementations on embedded systems. This work proposes a CNN-based detector, adapting a general-purpose convolutional network to the task at hand. By thoroughly analyzing and optimizing each step of the detection pipeline, we develop an architecture that outperforms methods based on traditional image features and achieves an accuracy close to the state-of-the-art while having low computational complexity. Furthermore, the model is compressed in order to fit the tight constrains of low power devices with a limited amount of embedded memory available. This paper makes two main contributions: (1) it proves that a region based deep neural network can be finely tuned to achieve adequate accuracy for pedestrian detection (2) it achieves a very low memory usage without reducing detection accuracy on the Caltech Pedestrian dataset. |
| Tasks | Pedestrian Detection |
| Published | 2016-09-08 |
| URL | http://arxiv.org/abs/1609.02500v1 |
| http://arxiv.org/pdf/1609.02500v1.pdf | |
| PWC | https://paperswithcode.com/paper/reduced-memory-region-based-deep |
| Repo | |
| Framework | |
Formal analysis of HTM Spatial Pooler performance under predefined operation conditions
| Title | Formal analysis of HTM Spatial Pooler performance under predefined operation conditions |
| Authors | M. Pietron, M. Wielgosz, K. Wiatr |
| Abstract | This paper introduces mathematical formalism for Spatial (SP) of Hierarchical Temporal Memory (HTM) with a spacial consideration for its hardware implementation. Performance of HTM network and its ability to learn and adjust to a problem at hand is governed by a large set of parameters. Most of parameters are codependent which makes creating efficient HTM-based solutions challenging. It requires profound knowledge of the settings and their impact on the performance of system. Consequently, this paper introduced a set of formulas which are to facilitate the design process by enhancing tedious trial-and-error method with a tool for choosing initial parameters which enable quick learning convergence. This is especially important in hardware implementations which are constrained by the limited resources of a platform. The authors focused especially on a formalism of Spatial Pooler and derive at the formulas for quality and convergence of the model. This may be considered as recipes for designing efficient HTM models for given input patterns. |
| Tasks | |
| Published | 2016-07-04 |
| URL | http://arxiv.org/abs/1607.00791v1 |
| http://arxiv.org/pdf/1607.00791v1.pdf | |
| PWC | https://paperswithcode.com/paper/formal-analysis-of-htm-spatial-pooler |
| Repo | |
| Framework | |
A Formal Solution to the Grain of Truth Problem
| Title | A Formal Solution to the Grain of Truth Problem |
| Authors | Jan Leike, Jessica Taylor, Benya Fallenstein |
| Abstract | A Bayesian agent acting in a multi-agent environment learns to predict the other agents’ policies if its prior assigns positive probability to them (in other words, its prior contains a \emph{grain of truth}). Finding a reasonably large class of policies that contains the Bayes-optimal policies with respect to this class is known as the \emph{grain of truth problem}. Only small classes are known to have a grain of truth and the literature contains several related impossibility results. In this paper we present a formal and general solution to the full grain of truth problem: we construct a class of policies that contains all computable policies as well as Bayes-optimal policies for every lower semicomputable prior over the class. When the environment is unknown, Bayes-optimal agents may fail to act optimally even asymptotically. However, agents based on Thompson sampling converge to play {\epsilon}-Nash equilibria in arbitrary unknown computable multi-agent environments. While these results are purely theoretical, we show that they can be computationally approximated arbitrarily closely. |
| Tasks | |
| Published | 2016-09-16 |
| URL | http://arxiv.org/abs/1609.05058v1 |
| http://arxiv.org/pdf/1609.05058v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-formal-solution-to-the-grain-of-truth |
| Repo | |
| Framework | |
Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation
| Title | Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation |
| Authors | Yu-An Chung, Hsuan-Tien Lin |
| Abstract | While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies, it is important to note that many real-world applications demand vary- ing costs for different types of misclassification errors, thus requiring cost-sensitive classification algorithms. Current models of deep neural networks for cost-sensitive classification are restricted to some specific network structures and limited depth. In this paper, we propose a novel framework that can be applied to deep neural networks with any structure to facilitate their learning of meaningful representations for cost-sensitive classification problems. Furthermore, the framework allows end- to-end training of deeper networks directly. The framework is designed by augmenting auxiliary neurons to the output of each hidden layer for layer-wise cost estimation, and including the total estimation loss within the optimization objective. Experimental results on public benchmark visual data sets with two cost information settings demonstrate that the proposed frame- work outperforms state-of-the-art cost-sensitive deep learning models. |
| Tasks | Object Recognition |
| Published | 2016-11-16 |
| URL | http://arxiv.org/abs/1611.05134v1 |
| http://arxiv.org/pdf/1611.05134v1.pdf | |
| PWC | https://paperswithcode.com/paper/cost-sensitive-deep-learning-with-layer-wise |
| Repo | |
| Framework | |
Tensor Decomposition for Signal Processing and Machine Learning
| Title | Tensor Decomposition for Signal Processing and Machine Learning |
| Authors | Nicholas D. Sidiropoulos, Lieven De Lathauwer, Xiao Fu, Kejun Huang, Evangelos E. Papalexakis, Christos Faloutsos |
| Abstract | Tensors or {\em multi-way arrays} are functions of three or more indices $(i,j,k,\cdots)$ – similar to matrices (two-way arrays), which are functions of two indices $(r,c)$ for (row,column). Tensors have a rich history, stretching over almost a century, and touching upon numerous disciplines; but they have only recently become ubiquitous in signal and data analytics at the confluence of signal processing, statistics, data mining and machine learning. This overview article aims to provide a good starting point for researchers and practitioners interested in learning about and working with tensors. As such, it focuses on fundamentals and motivation (using various application examples), aiming to strike an appropriate balance of breadth {\em and depth} that will enable someone having taken first graduate courses in matrix algebra and probability to get started doing research and/or developing tensor algorithms and software. Some background in applied optimization is useful but not strictly required. The material covered includes tensor rank and rank decomposition; basic tensor factorization models and their relationships and properties (including fairly good coverage of identifiability); broad coverage of algorithms ranging from alternating optimization to stochastic gradient; statistical performance analysis; and applications ranging from source separation to collaborative filtering, mixture and topic modeling, classification, and multilinear subspace learning. |
| Tasks | |
| Published | 2016-07-06 |
| URL | http://arxiv.org/abs/1607.01668v2 |
| http://arxiv.org/pdf/1607.01668v2.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-decomposition-for-signal-processing |
| Repo | |
| Framework | |
Discovering Neuronal Cell Types and Their Gene Expression Profiles Using a Spatial Point Process Mixture Model
| Title | Discovering Neuronal Cell Types and Their Gene Expression Profiles Using a Spatial Point Process Mixture Model |
| Authors | Furong Huang, Animashree Anandkumar, Christian Borgs, Jennifer Chayes, Ernest Fraenkel, Michael Hawrylycz, Ed Lein, Alessandro Ingrosso, Srinivas Turaga |
| Abstract | Cataloging the neuronal cell types that comprise circuitry of individual brain regions is a major goal of modern neuroscience and the BRAIN initiative. Single-cell RNA sequencing can now be used to measure the gene expression profiles of individual neurons and to categorize neurons based on their gene expression profiles. While the single-cell techniques are extremely powerful and hold great promise, they are currently still labor intensive, have a high cost per cell, and, most importantly, do not provide information on spatial distribution of cell types in specific regions of the brain. We propose a complementary approach that uses computational methods to infer the cell types and their gene expression profiles through analysis of brain-wide single-cell resolution in situ hybridization (ISH) imagery contained in the Allen Brain Atlas (ABA). We measure the spatial distribution of neurons labeled in the ISH image for each gene and model it as a spatial point process mixture, whose mixture weights are given by the cell types which express that gene. By fitting a point process mixture model jointly to the ISH images, we infer both the spatial point process distribution for each cell type and their gene expression profile. We validate our predictions of cell type-specific gene expression profiles using single cell RNA sequencing data, recently published for the mouse somatosensory cortex. Jointly with the gene expression profiles, cell features such as cell size, orientation, intensity and local density level are inferred per cell type. |
| Tasks | |
| Published | 2016-02-04 |
| URL | http://arxiv.org/abs/1602.01889v2 |
| http://arxiv.org/pdf/1602.01889v2.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-neuronal-cell-types-and-their |
| Repo | |
| Framework | |
Latent Skill Embedding for Personalized Lesson Sequence Recommendation
| Title | Latent Skill Embedding for Personalized Lesson Sequence Recommendation |
| Authors | Siddharth Reddy, Igor Labutov, Thorsten Joachims |
| Abstract | Students in online courses generate large amounts of data that can be used to personalize the learning process and improve quality of education. In this paper, we present the Latent Skill Embedding (LSE), a probabilistic model of students and educational content that can be used to recommend personalized sequences of lessons with the goal of helping students prepare for specific assessments. Akin to collaborative filtering for recommender systems, the algorithm does not require students or content to be described by features, but it learns a representation using access traces. We formulate this problem as a regularized maximum-likelihood embedding of students, lessons, and assessments from historical student-content interactions. An empirical evaluation on large-scale data from Knewton, an adaptive learning technology company, shows that this approach predicts assessment results competitively with benchmark models and is able to discriminate between lesson sequences that lead to mastery and failure. |
| Tasks | Recommendation Systems |
| Published | 2016-02-23 |
| URL | http://arxiv.org/abs/1602.07029v1 |
| http://arxiv.org/pdf/1602.07029v1.pdf | |
| PWC | https://paperswithcode.com/paper/latent-skill-embedding-for-personalized |
| Repo | |
| Framework | |
Evaluation and selection of Medical Tourism sites: A rough AHP based MABAC approach
| Title | Evaluation and selection of Medical Tourism sites: A rough AHP based MABAC approach |
| Authors | Jagannath Roy, Kajal Chatterjee, Abhirup Bandhopadhyay, Samarjit Kar |
| Abstract | In this paper, a novel multiple criteria decision making (MCDM) methodology is presented for assessing and prioritizing medical tourism destinations in uncertain environment. A systematic evaluation and assessment method is proposed by integrating rough number based AHP (Analytic Hierarchy Process) and rough number based MABAC (Multi-Attributive Border Approximation area Comparison). Rough number is used to aggregate individual judgments and preferences to deal with vagueness in decision making due to limited data. Rough AHP analyzes the relative importance of criteria based on their preferences given by experts. Rough MABAC evaluates the alternative sites based on the criteria weights. The proposed methodology is explained through a case study considering different cities for healthcare service in India. The validity of the obtained ranking for the given decision making problem is established by testing criteria proposed by Wang and Triantaphyllou (2008) along with further analysis and discussion. |
| Tasks | Decision Making |
| Published | 2016-06-29 |
| URL | http://arxiv.org/abs/1606.08962v2 |
| http://arxiv.org/pdf/1606.08962v2.pdf | |
| PWC | https://paperswithcode.com/paper/evaluation-and-selection-of-medical-tourism |
| Repo | |
| Framework | |
Less-forgetting Learning in Deep Neural Networks
| Title | Less-forgetting Learning in Deep Neural Networks |
| Authors | Heechul Jung, Jeongwoo Ju, Minju Jung, Junmo Kim |
| Abstract | A catastrophic forgetting problem makes deep neural networks forget the previously learned information, when learning data collected in new environments, such as by different sensors or in different light conditions. This paper presents a new method for alleviating the catastrophic forgetting problem. Unlike previous research, our method does not use any information from the source domain. Surprisingly, our method is very effective to forget less of the information in the source domain, and we show the effectiveness of our method using several experiments. Furthermore, we observed that the forgetting problem occurs between mini-batches when performing general training processes using stochastic gradient descent methods, and this problem is one of the factors that degrades generalization performance of the network. We also try to solve this problem using the proposed method. Finally, we show our less-forgetting learning method is also helpful to improve the performance of deep neural networks in terms of recognition rates. |
| Tasks | |
| Published | 2016-07-01 |
| URL | http://arxiv.org/abs/1607.00122v1 |
| http://arxiv.org/pdf/1607.00122v1.pdf | |
| PWC | https://paperswithcode.com/paper/less-forgetting-learning-in-deep-neural |
| Repo | |
| Framework | |
