Paper Group ANR 382
Computerized Tomography with Total Variation and with Shearlets. The SP theory of intelligence and the representation and processing of knowledge in the brain. Asymptotic sequential Rademacher complexity of a finite function class. Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments. Component-Based Distri …
Computerized Tomography with Total Variation and with Shearlets
| Title | Computerized Tomography with Total Variation and with Shearlets |
| Authors | Edgar Garduño, Gabor T. Herman |
| Abstract | To reduce the x-ray dose in computerized tomography (CT), many constrained optimization approaches have been proposed aiming at minimizing a regularizing function that measures lack of consistency with some prior knowledge about the object that is being imaged, subject to a (predetermined) level of consistency with the detected attenuation of x-rays. Proponents of the shearlet transform in the regularizing function claim that the reconstructions so obtained are better than those produced using TV for texture preservation (but may be worse for noise reduction). In this paper we report results related to this claim. In our reported experiments using simulated CT data collection of the head, reconstructions whose shearlet transform has a small $\ell_1$-norm are not more efficacious than reconstructions that have a small TV value. Our experiments for making such comparisons use the recently-developed superiorization methodology for both regularizing functions. Superiorization is an automated procedure for turning an iterative algorithm for producing images that satisfy a primary criterion (such as consistency with the observed measurements) into its superiorized version that will produce results that, according to the primary criterion are as good as those produced by the original algorithm, but in addition are superior to them according to a secondary (regularizing) criterion. The method presented for superiorization involving the $\ell_1$-norm of the shearlet transform is novel and is quite general: It can be used for any regularizing function that is defined as the $\ell_1$-norm of a transform specified by the application of a matrix. Because in the previous literature the split Bregman algorithm is used for similar purposes, a section is included comparing the results of the superiorization algorithm with the split Bregman algorithm. |
| Tasks | |
| Published | 2016-08-23 |
| URL | http://arxiv.org/abs/1608.06668v1 |
| http://arxiv.org/pdf/1608.06668v1.pdf | |
| PWC | https://paperswithcode.com/paper/computerized-tomography-with-total-variation |
| Repo | |
| Framework | |
The SP theory of intelligence and the representation and processing of knowledge in the brain
| Title | The SP theory of intelligence and the representation and processing of knowledge in the brain |
| Authors | J Gerard Wolff |
| Abstract | The “SP theory of intelligence”, with its realisation in the “SP computer model”, aims to simplify and integrate observations and concepts across AI-related fields, with information compression as a unifying theme. This paper describes how abstract structures and processes in the theory may be realised in terms of neurons, their interconnections, and the transmission of signals between neurons. This part of the SP theory – “SP-neural” – is a tentative and partial model for the representation and processing of knowledge in the brain. In the SP theory (apart from SP-neural), all kinds of knowledge are represented with “patterns”, where a pattern is an array of atomic symbols in one or two dimensions. In SP-neural, the concept of a “pattern” is realised as an array of neurons called a “pattern assembly”, similar to Hebb’s concept of a “cell assembly” but with important differences. Central to the processing of information in the SP system is the powerful concept of “multiple alignment”, borrowed and adapted from bioinformatics. Processes such as pattern recognition, reasoning and problem solving are achieved via the building of multiple alignments, while unsupervised learning – significantly different from the “Hebbian” kinds of learning – is achieved by creating patterns from sensory information and also by creating patterns from multiple alignments in which there is a partial match between one pattern and another. Short-lived neural structures equivalent to multiple alignments will be created via an inter-play of excitatory and inhibitory neural signals. The paper discusses several associated issues, with relevant empirical evidence. |
| Tasks | |
| Published | 2016-04-19 |
| URL | http://arxiv.org/abs/1604.05535v2 |
| http://arxiv.org/pdf/1604.05535v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-sp-theory-of-intelligence-and-the |
| Repo | |
| Framework | |
Asymptotic sequential Rademacher complexity of a finite function class
| Title | Asymptotic sequential Rademacher complexity of a finite function class |
| Authors | Dmitry B. Rokhlin |
| Abstract | For a finite function class we describe the large sample limit of the sequential Rademacher complexity in terms of the viscosity solution of a $G$-heat equation. In the language of Peng’s sublinear expectation theory, the same quantity equals to the expected value of the largest order statistics of a multidimensional $G$-normal random variable. We illustrate this result by deriving upper and lower bounds for the asymptotic sequential Rademacher complexity. |
| Tasks | |
| Published | 2016-05-11 |
| URL | http://arxiv.org/abs/1605.03843v1 |
| http://arxiv.org/pdf/1605.03843v1.pdf | |
| PWC | https://paperswithcode.com/paper/asymptotic-sequential-rademacher-complexity |
| Repo | |
| Framework | |
Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments
| Title | Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments |
| Authors | Jingwei Zhang, Jost Tobias Springenberg, Joschka Boedecker, Wolfram Burgard |
| Abstract | In this paper we consider the problem of robot navigation in simple maze-like environments where the robot has to rely on its onboard sensors to perform the navigation task. In particular, we are interested in solutions to this problem that do not require localization, mapping or planning. Additionally, we require that our solution can quickly adapt to new situations (e.g., changing navigation goals and environments). To meet these criteria we frame this problem as a sequence of related reinforcement learning tasks. We propose a successor feature based deep reinforcement learning algorithm that can learn to transfer knowledge from previously mastered navigation tasks to new problem instances. Our algorithm substantially decreases the required learning time after the first task instance has been solved, which makes it easily adaptable to changing environments. We validate our method in both simulated and real robot experiments with a Robotino and compare it to a set of baseline methods including classical planning-based navigation. |
| Tasks | Robot Navigation |
| Published | 2016-12-16 |
| URL | http://arxiv.org/abs/1612.05533v3 |
| http://arxiv.org/pdf/1612.05533v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-with-successor |
| Repo | |
| Framework | |
Component-Based Distributed Framework for Coherent and Real-Time Video Dehazing
| Title | Component-Based Distributed Framework for Coherent and Real-Time Video Dehazing |
| Authors | Meihua Wang, Jiaming Mai, Yun Liang, Tom Z. J. Fu, Zhenjie Zhang, Ruichu Cai |
| Abstract | Traditional dehazing techniques, as a well studied topic in image processing, are now widely used to eliminate the haze effects from individual images. However, even the state-of-the-art dehazing algorithms may not provide sufficient support to video analytics, as a crucial pre-processing step for video-based decision making systems (e.g., robot navigation), due to the limitations of these algorithms on poor result coherence and low processing efficiency. This paper presents a new framework, particularly designed for video dehazing, to output coherent results in real time, with two novel techniques. Firstly, we decompose the dehazing algorithms into three generic components, namely transmission map estimator, atmospheric light estimator and haze-free image generator. They can be simultaneously processed by multiple threads in the distributed system, such that the processing efficiency is optimized by automatic CPU resource allocation based on the workloads. Secondly, a cross-frame normalization scheme is proposed to enhance the coherence among consecutive frames, by sharing the parameters of atmospheric light from consecutive frames in the distributed computation platform. The combination of these techniques enables our framework to generate highly consistent and accurate dehazing results in real-time, by using only 3 PCs connected by Ethernet. |
| Tasks | Decision Making, Robot Navigation |
| Published | 2016-09-07 |
| URL | http://arxiv.org/abs/1609.02035v2 |
| http://arxiv.org/pdf/1609.02035v2.pdf | |
| PWC | https://paperswithcode.com/paper/component-based-distributed-framework-for |
| Repo | |
| Framework | |
The Generalized Reparameterization Gradient
| Title | The Generalized Reparameterization Gradient |
| Authors | Francisco J. R. Ruiz, Michalis K. Titsias, David M. Blei |
| Abstract | The reparameterization gradient has become a widely used method to obtain Monte Carlo gradients to optimize the variational objective. However, this technique does not easily apply to commonly used distributions such as beta or gamma without further approximations, and most practical applications of the reparameterization gradient fit Gaussian distributions. In this paper, we introduce the generalized reparameterization gradient, a method that extends the reparameterization gradient to a wider class of variational distributions. Generalized reparameterizations use invertible transformations of the latent variables which lead to transformed distributions that weakly depend on the variational parameters. This results in new Monte Carlo gradients that combine reparameterization gradients and score function gradients. We demonstrate our approach on variational inference for two complex probabilistic models. The generalized reparameterization is effective: even a single sample from the variational distribution is enough to obtain a low-variance gradient. |
| Tasks | |
| Published | 2016-10-07 |
| URL | http://arxiv.org/abs/1610.02287v3 |
| http://arxiv.org/pdf/1610.02287v3.pdf | |
| PWC | https://paperswithcode.com/paper/the-generalized-reparameterization-gradient |
| Repo | |
| Framework | |
Multi-Model Hypothesize-and-Verify Approach for Incremental Loop Closure Verification
| Title | Multi-Model Hypothesize-and-Verify Approach for Incremental Loop Closure Verification |
| Authors | Kanji Tanaka |
| Abstract | Loop closure detection, which is the task of identifying locations revisited by a robot in a sequence of odometry and perceptual observations, is typically formulated as a visual place recognition (VPR) task. However, even state-of-the-art VPR techniques generate a considerable number of false positives as a result of confusing visual features and perceptual aliasing. In this paper, we propose a robust incremental framework for loop closure detection, termed incremental loop closure verification. Our approach reformulates the problem of loop closure detection as an instance of a multi-model hypothesize-and-verify framework, in which multiple loop closure hypotheses are generated and verified in terms of the consistency between loop closure hypotheses and VPR constraints at multiple viewpoints along the robot’s trajectory. Furthermore, we consider the general incremental setting of loop closure detection, in which the system must update both the set of VPR constraints and that of loop closure hypotheses when new constraints or hypotheses arrive during robot navigation. Experimental results using a stereo SLAM system and DCNN features and visual odometry validate effectiveness of the proposed approach. |
| Tasks | Loop Closure Detection, Robot Navigation, Visual Odometry, Visual Place Recognition |
| Published | 2016-08-06 |
| URL | http://arxiv.org/abs/1608.02052v1 |
| http://arxiv.org/pdf/1608.02052v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-model-hypothesize-and-verify-approach |
| Repo | |
| Framework | |
Mirrored Light Field Video Camera Adapter
| Title | Mirrored Light Field Video Camera Adapter |
| Authors | Dorian Tsai, Donald G. Dansereau, Steve Martin, Peter Corke |
| Abstract | This paper proposes the design of a custom mirror-based light field camera adapter that is cheap, simple in construction, and accessible. Mirrors of different shape and orientation reflect the scene into an upwards-facing camera to create an array of virtual cameras with overlapping field of view at specified depths, and deliver video frame rate light fields. We describe the design, construction, decoding and calibration processes of our mirror-based light field camera adapter in preparation for an open-source release to benefit the robotic vision community. |
| Tasks | Calibration |
| Published | 2016-12-16 |
| URL | http://arxiv.org/abs/1612.05335v1 |
| http://arxiv.org/pdf/1612.05335v1.pdf | |
| PWC | https://paperswithcode.com/paper/mirrored-light-field-video-camera-adapter |
| Repo | |
| Framework | |
Kernel Density Estimation for Dynamical Systems
| Title | Kernel Density Estimation for Dynamical Systems |
| Authors | Hanyuan Hang, Ingo Steinwart, Yunlong Feng, Johan A. K. Suykens |
| Abstract | We study the density estimation problem with observations generated by certain dynamical systems that admit a unique underlying invariant Lebesgue density. Observations drawn from dynamical systems are not independent and moreover, usual mixing concepts may not be appropriate for measuring the dependence among these observations. By employing the $\mathcal{C}$-mixing concept to measure the dependence, we conduct statistical analysis on the consistency and convergence of the kernel density estimator. Our main results are as follows: First, we show that with properly chosen bandwidth, the kernel density estimator is universally consistent under $L_1$-norm; Second, we establish convergence rates for the estimator with respect to several classes of dynamical systems under $L_1$-norm. In the analysis, the density function $f$ is only assumed to be H"{o}lder continuous which is a weak assumption in the literature of nonparametric density estimation and also more realistic in the dynamical system context. Last but not least, we prove that the same convergence rates of the estimator under $L_\infty$-norm and $L_1$-norm can be achieved when the density function is H"{o}lder continuous, compactly supported and bounded. The bandwidth selection problem of the kernel density estimator for dynamical system is also discussed in our study via numerical simulations. |
| Tasks | Density Estimation |
| Published | 2016-07-13 |
| URL | http://arxiv.org/abs/1607.03792v1 |
| http://arxiv.org/pdf/1607.03792v1.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-density-estimation-for-dynamical |
| Repo | |
| Framework | |
SNN: Stacked Neural Networks
| Title | SNN: Stacked Neural Networks |
| Authors | Milad Mohammadi, Subhasis Das |
| Abstract | It has been proven that transfer learning provides an easy way to achieve state-of-the-art accuracies on several vision tasks by training a simple classifier on top of features obtained from pre-trained neural networks. The goal of this work is to generate better features for transfer learning from multiple publicly available pre-trained neural networks. To this end, we propose a novel architecture called Stacked Neural Networks which leverages the fast training time of transfer learning while simultaneously being much more accurate. We show that using a stacked NN architecture can result in up to 8% improvements in accuracy over state-of-the-art techniques using only one pre-trained network for transfer learning. A second aim of this work is to make network fine- tuning retain the generalizability of the base network to unseen tasks. To this end, we propose a new technique called “joint fine-tuning” that is able to give accuracies comparable to finetuning the same network individually over two datasets. We also show that a jointly finetuned network generalizes better to unseen tasks when compared to a network finetuned over a single task. |
| Tasks | Transfer Learning |
| Published | 2016-05-27 |
| URL | http://arxiv.org/abs/1605.08512v1 |
| http://arxiv.org/pdf/1605.08512v1.pdf | |
| PWC | https://paperswithcode.com/paper/snn-stacked-neural-networks |
| Repo | |
| Framework | |
WS4A: a Biomedical Question and Answering System based on public Web Services and Ontologies
| Title | WS4A: a Biomedical Question and Answering System based on public Web Services and Ontologies |
| Authors | Miguel J. Rodrigues, Miguel Falé, Andre Lamurias, Francisco M. Couto |
| Abstract | This paper describes our system, dubbed WS4A (Web Services for All), that participated in the fourth edition of the BioASQ challenge (2016). We used WS4A to perform the Question and Answering (QA) task 4b, which consisted on the retrieval of relevant concepts, documents, snippets, RDF triples, exact answers and ideal answers for each given question. The novelty in our approach consists on the maximum exploitation of existing web services in each step of WS4A, such as the annotation of text, and the retrieval of metadata for each annotation. The information retrieved included concept identifiers, ontologies, ancestors, and most importantly, PubMed identifiers. The paper describes the WS4A pipeline and also presents the precision, recall and f-measure values obtained in task 4b. Our system achieved two second places in two subtasks on one of the five batches. |
| Tasks | |
| Published | 2016-09-27 |
| URL | http://arxiv.org/abs/1609.08492v2 |
| http://arxiv.org/pdf/1609.08492v2.pdf | |
| PWC | https://paperswithcode.com/paper/ws4a-a-biomedical-question-and-answering |
| Repo | |
| Framework | |
Sparsity in Dynamics of Spontaneous Subtle Emotions: Analysis & Application
| Title | Sparsity in Dynamics of Spontaneous Subtle Emotions: Analysis & Application |
| Authors | Anh Cat Le Ngo, John See, Raphael Chung-Wei Phan |
| Abstract | Spontaneous subtle emotions are expressed through micro-expressions, which are tiny, sudden and short-lived dynamics of facial muscles; thus poses a great challenge for visual recognition. The abrupt but significant dynamics for the recognition task are temporally sparse while the rest, irrelevant dynamics, are temporally redundant. In this work, we analyze and enforce sparsity constrains to learn significant temporal and spectral structures while eliminate irrelevant facial dynamics of micro-expressions, which would ease the challenge in the visual recognition of spontaneous subtle emotions. The hypothesis is confirmed through experimental results of automatic spontaneous subtle emotion recognition with several sparsity levels on CASME II and SMIC, the only two publicly available spontaneous subtle emotion databases. The overall performances of the automatic subtle emotion recognition are boosted when only significant dynamics are preserved from the original sequences. |
| Tasks | Emotion Recognition |
| Published | 2016-01-19 |
| URL | http://arxiv.org/abs/1601.04805v2 |
| http://arxiv.org/pdf/1601.04805v2.pdf | |
| PWC | https://paperswithcode.com/paper/sparsity-in-dynamics-of-spontaneous-subtle |
| Repo | |
| Framework | |
EventNet Version 1.1 Technical Report
| Title | EventNet Version 1.1 Technical Report |
| Authors | Dongang Wang, Zheng Shou, Hongyi Liu, Shih-Fu Chang |
| Abstract | EventNet is a large-scale video corpus and event ontology consisting of 500 events associated with event-specific concepts. In order to improve the quality of the current EventNet, we conduct the following steps and introduce EventNet version 1.1: (1) manually verify the correctness of event labels for all videos; (2) remove the YouTube user bias by limiting the maximum number of videos in each event from the same YouTube user as 3; (3) remove the videos which are currently not accessible online; (4) remove the video belonging to multiple event categories. After the above procedure, some events may contain only a small number of videos, and therefore we crawl more videos for those events to ensure every event will contain more than 50 videos. Finally, EventNet version 1.1 contains 67,641 videos, 500 events, and 5,028 event-specific concepts. In addition, we train a Convolutional Neural Network (CNN) model for event classification via fine-tuning AlexNet using EventNet version 1.1. Then we use the trained CNN model to extract FC7 layer feature and train binary classifiers using linear SVM for each event-specific concept. We believe this new version of EventNet will significantly facilitate research in computer vision and multimedia, and will put it online for public downloading in the future. |
| Tasks | |
| Published | 2016-05-24 |
| URL | http://arxiv.org/abs/1605.07289v2 |
| http://arxiv.org/pdf/1605.07289v2.pdf | |
| PWC | https://paperswithcode.com/paper/eventnet-version-11-technical-report |
| Repo | |
| Framework | |
A Piece of My Mind: A Sentiment Analysis Approach for Online Dispute Detection
| Title | A Piece of My Mind: A Sentiment Analysis Approach for Online Dispute Detection |
| Authors | Lu Wang, Claire Cardie |
| Abstract | We investigate the novel task of online dispute detection and propose a sentiment analysis solution to the problem: we aim to identify the sequence of sentence-level sentiments expressed during a discussion and to use them as features in a classifier that predicts the DISPUTE/NON-DISPUTE label for the discussion as a whole. We evaluate dispute detection approaches on a newly created corpus of Wikipedia Talk page disputes and find that classifiers that rely on our sentiment tagging features outperform those that do not. The best model achieves a very promising F1 score of 0.78 and an accuracy of 0.80. |
| Tasks | Sentiment Analysis |
| Published | 2016-06-17 |
| URL | http://arxiv.org/abs/1606.05704v1 |
| http://arxiv.org/pdf/1606.05704v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-piece-of-my-mind-a-sentiment-analysis |
| Repo | |
| Framework | |
Feedback Neural Network for Weakly Supervised Geo-Semantic Segmentation
| Title | Feedback Neural Network for Weakly Supervised Geo-Semantic Segmentation |
| Authors | Xianming Liu, Amy Zhang, Tobias Tiecke, Andreas Gros, Thomas S. Huang |
| Abstract | Learning from weakly-supervised data is one of the main challenges in machine learning and computer vision, especially for tasks such as image semantic segmentation where labeling is extremely expensive and subjective. In this paper, we propose a novel neural network architecture to perform weakly-supervised learning by suppressing irrelevant neuron activations. It localizes objects of interest by learning from image-level categorical labels in an end-to-end manner. We apply this algorithm to a practical challenge of transforming satellite images into a map of settlements and individual buildings. Experimental results show that the proposed algorithm achieves superior performance and efficiency when compared with various baseline models. |
| Tasks | Semantic Segmentation |
| Published | 2016-12-08 |
| URL | http://arxiv.org/abs/1612.02766v1 |
| http://arxiv.org/pdf/1612.02766v1.pdf | |
| PWC | https://paperswithcode.com/paper/feedback-neural-network-for-weakly-supervised |
| Repo | |
| Framework | |
