Paper Group ANR 231
Planning in Stochastic Environments with Goal Uncertainty. Hierarchical Bi-level Multi-Objective Evolution of Single- and Multi-layer Echo State Network Autoencoders for Data Representations. Logarithmic mathematical morphology: a new framework adaptive to illumination changes. Studio Ousia’s Quiz Bowl Question Answering System. ADMM-based Networke …
Planning in Stochastic Environments with Goal Uncertainty
| Title | Planning in Stochastic Environments with Goal Uncertainty |
| Authors | Sandhya Saisubramanian, Kyle Hollins Wray, Luis Pineda, Shlomo Zilberstein |
| Abstract | We present the Goal Uncertain Stochastic Shortest Path (GUSSP) problem — a general framework to model stochastic environments with goal uncertainty. The model is an extension of the stochastic shortest path (SSP) framework to dynamic environments in which it is impossible to determine the exact goal states ahead of plan execution. GUSSPs introduce flexibility in goal specification by allowing a belief over possible goal configurations. The partial observability is restricted to goals, facilitating the reduction to an SSP. We formally define a GUSSP and discuss its theoretical properties. We then propose an admissible heuristic that reduces the planning time of FLARES — a start-of-the-art probabilistic planner. We also propose a determinization approach for solving this class of problems. Finally, we present empirical results using a mobile robot and three other problem domains. |
| Tasks | |
| Published | 2018-10-18 |
| URL | http://arxiv.org/abs/1810.08159v1 |
| http://arxiv.org/pdf/1810.08159v1.pdf | |
| PWC | https://paperswithcode.com/paper/planning-in-stochastic-environments-with-goal |
| Repo | |
| Framework | |
Hierarchical Bi-level Multi-Objective Evolution of Single- and Multi-layer Echo State Network Autoencoders for Data Representations
| Title | Hierarchical Bi-level Multi-Objective Evolution of Single- and Multi-layer Echo State Network Autoencoders for Data Representations |
| Authors | Naima Chouikhi, Boudour Ammar, Adel M. Alimi |
| Abstract | Echo State Network (ESN) presents a distinguished kind of recurrent neural networks. It is built upon a sparse, random and large hidden infrastructure called reservoir. ESNs have succeeded in dealing with several non-linear problems such as prediction, classification, etc. Thanks to its rich dynamics, ESN is used as an Autoencoder (AE) to extract features from original data representations. ESN is not only used with its basic single layer form but also with the recently proposed Multi-Layer (ML) architecture. The well setting of ESN (basic and ML) architectures and training parameters is a crucial and hard labor task. Generally, a number of parameters (hidden neurons, sparsity rates, input scaling) is manually altered to achieve minimum learning error. However, this randomly hand crafted task, on one hand, may not guarantee best training results and on the other hand, it can raise the network’s complexity. In this paper, a hierarchical bi-level evolutionary optimization is proposed to deal with these issues. The first level includes a multi-objective architecture optimization providing maximum learning accuracy while sustaining the complexity at a reduced standard. Multi-objective Particle Swarm Optimization (MOPSO) is used to optimize ESN structure in a way to provide a trade-off between the network complexity decreasing and the accuracy increasing. A pareto-front of optimal solutions is generated by the end of the MOPSO process. These solutions present the set of candidates that succeeded in providing a compromise between different objectives (learning error and network complexity). At the second level, each of the solutions already found undergo a mono-objective weights optimization to enhance the obtained pareto-front. Empirical results ensure the effectiveness of the evolved ESN recurrent AEs (basic and ML) for noisy and noise free data. |
| Tasks | |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01016v2 |
| http://arxiv.org/pdf/1806.01016v2.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-bi-level-multi-objective |
| Repo | |
| Framework | |
Logarithmic mathematical morphology: a new framework adaptive to illumination changes
| Title | Logarithmic mathematical morphology: a new framework adaptive to illumination changes |
| Authors | Guillaume Noyel |
| Abstract | A new set of mathematical morphology (MM) operators adaptive to illumination changes caused by variation of exposure time or light intensity is defined thanks to the Logarithmic Image Processing (LIP) model. This model based on the physics of acquisition is consistent with human vision. The fundamental operators, the logarithmic-dilation and the logarithmic-erosion, are defined with the LIP-addition of a structuring function. The combination of these two adjunct operators gives morphological filters, namely the logarithmic-opening and closing, useful for pattern recognition. The mathematical relation existing between classical'' dilation and erosion and their logarithmic-versions is established facilitating their implementation. Results on simulated and real images show that logarithmic-MM is more efficient on low-contrasted information than classical’’ MM. |
| Tasks | |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.02998v3 |
| http://arxiv.org/pdf/1806.02998v3.pdf | |
| PWC | https://paperswithcode.com/paper/logarithmic-mathematical-morphology-a-new |
| Repo | |
| Framework | |
Studio Ousia’s Quiz Bowl Question Answering System
| Title | Studio Ousia’s Quiz Bowl Question Answering System |
| Authors | Ikuya Yamada, Ryuji Tamaki, Hiroyuki Shindo, Yoshiyasu Takefuji |
| Abstract | In this chapter, we describe our question answering system, which was the winning system at the Human-Computer Question Answering (HCQA) Competition at the Thirty-first Annual Conference on Neural Information Processing Systems (NIPS). The competition requires participants to address a factoid question answering task referred to as quiz bowl. To address this task, we use two novel neural network models and combine these models with conventional information retrieval models using a supervised machine learning model. Our system achieved the best performance among the systems submitted in the competition and won a match against six top human quiz experts by a wide margin. |
| Tasks | Information Retrieval, Question Answering |
| Published | 2018-03-23 |
| URL | http://arxiv.org/abs/1803.08652v1 |
| http://arxiv.org/pdf/1803.08652v1.pdf | |
| PWC | https://paperswithcode.com/paper/studio-ousias-quiz-bowl-question-answering |
| Repo | |
| Framework | |
ADMM-based Networked Stochastic Variational Inference
| Title | ADMM-based Networked Stochastic Variational Inference |
| Authors | Hamza Anwar, Quanyan Zhu |
| Abstract | Owing to the recent advances in “Big Data” modeling and prediction tasks, variational Bayesian estimation has gained popularity due to their ability to provide exact solutions to approximate posteriors. One key technique for approximate inference is stochastic variational inference (SVI). SVI poses variational inference as a stochastic optimization problem and solves it iteratively using noisy gradient estimates. It aims to handle massive data for predictive and classification tasks by applying complex Bayesian models that have observed as well as latent variables. This paper aims to decentralize it allowing parallel computation, secure learning and robustness benefits. We use Alternating Direction Method of Multipliers in a top-down setting to develop a distributed SVI algorithm such that independent learners running inference algorithms only require sharing the estimated model parameters instead of their private datasets. Our work extends the distributed SVI-ADMM algorithm that we first propose, to an ADMM-based networked SVI algorithm in which not only are the learners working distributively but they share information according to rules of a graph by which they form a network. This kind of work lies under the umbrella of `deep learning over networks’ and we verify our algorithm for a topic-modeling problem for corpus of Wikipedia articles. We illustrate the results on latent Dirichlet allocation (LDA) topic model in large document classification, compare performance with the centralized algorithm, and use numerical experiments to corroborate the analytical results. | |
| Tasks | Document Classification, Stochastic Optimization |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.10168v1 |
| http://arxiv.org/pdf/1802.10168v1.pdf | |
| PWC | https://paperswithcode.com/paper/admm-based-networked-stochastic-variational |
| Repo | |
| Framework | |
Semi-Supervised Multi-Organ Segmentation via Deep Multi-Planar Co-Training
| Title | Semi-Supervised Multi-Organ Segmentation via Deep Multi-Planar Co-Training |
| Authors | Yuyin Zhou, Yan Wang, Peng Tang, Song Bai, Wei Shen, Elliot K. Fishman, Alan L. Yuille |
| Abstract | In multi-organ segmentation of abdominal CT scans, most existing fully supervised deep learning algorithms require lots of voxel-wise annotations, which are usually difficult, expensive, and slow to obtain. In comparison, massive unlabeled 3D CT volumes are usually easily accessible. Current mainstream works to address the semi-supervised biomedical image segmentation problem are mostly graph-based. By contrast, deep network based semi-supervised learning methods have not drawn much attention in this field. In this work, we propose Deep Multi-Planar Co-Training (DMPCT), whose contributions can be divided into two folds: 1) The deep model is learned in a co-training style which can mine consensus information from multiple planes like the sagittal, coronal, and axial planes; 2) Multi-planar fusion is applied to generate more reliable pseudo-labels, which alleviates the errors occurring in the pseudo-labels and thus can help to train better segmentation networks. Experiments are done on our newly collected large dataset with 100 unlabeled cases as well as 210 labeled cases where 16 anatomical structures are manually annotated by four radiologists and confirmed by a senior expert. The results suggest that DMPCT significantly outperforms the fully supervised method by more than 4% especially when only a small set of annotations is used. |
| Tasks | Semantic Segmentation |
| Published | 2018-04-07 |
| URL | http://arxiv.org/abs/1804.02586v3 |
| http://arxiv.org/pdf/1804.02586v3.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-multi-organ-segmentation-via |
| Repo | |
| Framework | |
Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks
| Title | Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks |
| Authors | Ramin M. Hasani, Alexander Amini, Mathias Lechner, Felix Naser, Radu Grosu, Daniela Rus |
| Abstract | In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a systematic pipeline for interpreting individual hidden state dynamics within the network using response characterization methods. The ranked contribution of individual cells to the network’s output is computed by analyzing a set of interpretable metrics of their decoupled step and sinusoidal responses. As a result, our method is able to uniquely identify neurons with insightful dynamics, quantify relationships between dynamical properties and test accuracy through ablation analysis, and interpret the impact of network capacity on a network’s dynamical distribution. Finally, we demonstrate generalizability and scalability of our method by evaluating a series of different benchmark sequential datasets. |
| Tasks | |
| Published | 2018-09-11 |
| URL | http://arxiv.org/abs/1809.03864v1 |
| http://arxiv.org/pdf/1809.03864v1.pdf | |
| PWC | https://paperswithcode.com/paper/response-characterization-for-auditing-cell |
| Repo | |
| Framework | |
Extracting Tree-structures in CT data by Tracking Multiple Statistically Ranked Hypotheses
| Title | Extracting Tree-structures in CT data by Tracking Multiple Statistically Ranked Hypotheses |
| Authors | Raghavendra Selvan, Jens Petersen, Jesper H Pedersen, Marleen de Bruijne |
| Abstract | In this work, we adapt a method based on multiple hypothesis tracking (MHT) that has been shown to give state-of-the-art vessel segmentation results in interactive settings, for the purpose of extracting trees. Regularly spaced tubular templates are fit to image data forming local hypotheses. These local hypotheses are used to construct the MHT tree, which is then traversed to make segmentation decisions. However, some critical parameters in this method are scale-dependent and have an adverse effect when tracking structures of varying dimensions. We propose to use statistical ranking of local hypotheses in constructing the MHT tree, which yields a probabilistic interpretation of scores across scales and helps alleviate the scale-dependence of MHT parameters. This enables our method to track trees starting from a single seed point. Our method is evaluated on chest CT data to extract airway trees and coronary arteries. In both cases, we show that our method performs significantly better than the original MHT method. |
| Tasks | |
| Published | 2018-06-23 |
| URL | https://arxiv.org/abs/1806.08981v2 |
| https://arxiv.org/pdf/1806.08981v2.pdf | |
| PWC | https://paperswithcode.com/paper/extracting-tree-structures-in-ct-data-by |
| Repo | |
| Framework | |
Deep Group-shuffling Random Walk for Person Re-identification
| Title | Deep Group-shuffling Random Walk for Person Re-identification |
| Authors | Yantao Shen, Hongsheng Li, Tong Xiao, Shuai Yi, Dapeng Chen, Xiaogang Wang |
| Abstract | Person re-identification aims at finding a person of interest in an image gallery by comparing the probe image of this person with all the gallery images. It is generally treated as a retrieval problem, where the affinities between the probe image and gallery images (P2G affinities) are used to rank the retrieved gallery images. However, most existing methods only consider P2G affinities but ignore the affinities between all the gallery images (G2G affinity). Some frameworks incorporated G2G affinities into the testing process, which is not end-to-end trainable for deep neural networks. In this paper, we propose a novel group-shuffling random walk network for fully utilizing the affinity information between gallery images in both the training and testing processes. The proposed approach aims at end-to-end refining the P2G affinities based on G2G affinity information with a simple yet effective matrix operation, which can be integrated into deep neural networks. Feature grouping and group shuffle are also proposed to apply rich supervisions for learning better person features. The proposed approach outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets by large margins, which demonstrate the effectiveness of our approach. |
| Tasks | Person Re-Identification |
| Published | 2018-07-30 |
| URL | http://arxiv.org/abs/1807.11178v1 |
| http://arxiv.org/pdf/1807.11178v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-group-shuffling-random-walk-for-person |
| Repo | |
| Framework | |
Learning models for visual 3D localization with implicit mapping
| Title | Learning models for visual 3D localization with implicit mapping |
| Authors | Dan Rosenbaum, Frederic Besse, Fabio Viola, Danilo J. Rezende, S. M. Ali Eslami |
| Abstract | We consider learning based methods for visual localization that do not require the construction of explicit maps in the form of point clouds or voxels. The goal is to learn an implicit representation of the environment at a higher, more abstract level. We propose to use a generative approach based on Generative Query Networks (GQNs, Eslami et al. 2018), asking the following questions: 1) Can GQN capture more complex scenes than those it was originally demonstrated on? 2) Can GQN be used for localization in those scenes? To study this approach we consider procedurally generated Minecraft worlds, for which we can generate images of complex 3D scenes along with camera pose coordinates. We first show that GQNs, enhanced with a novel attention mechanism can capture the structure of 3D scenes in Minecraft, as evidenced by their samples. We then apply the models to the localization problem, comparing the results to a discriminative baseline, and comparing the ways each approach captures the task uncertainty. |
| Tasks | Visual Localization |
| Published | 2018-07-04 |
| URL | http://arxiv.org/abs/1807.03149v2 |
| http://arxiv.org/pdf/1807.03149v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-models-for-visual-3d-localization |
| Repo | |
| Framework | |
EC-Net: an Edge-aware Point set Consolidation Network
| Title | EC-Net: an Edge-aware Point set Consolidation Network |
| Authors | Lequan Yu, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng |
| Abstract | Point clouds obtained from 3D scans are typically sparse, irregular, and noisy, and required to be consolidated. In this paper, we present the first deep learning based edge-aware technique to facilitate the consolidation of point clouds. We design our network to process points grouped in local patches, and train it to learn and help consolidate points, deliberately for edges. To achieve this, we formulate a regression component to simultaneously recover 3D point coordinates and point-to-edge distances from upsampled features, and an edge-aware joint loss function to directly minimize distances from output points to 3D meshes and to edges. Compared with previous neural network based works, our consolidation is edge-aware. During the synthesis, our network can attend to the detected sharp edges and enable more accurate 3D reconstructions. Also, we trained our network on virtual scanned point clouds, demonstrated the performance of our method on both synthetic and real point clouds, presented various surface reconstruction results, and showed how our method outperforms the state-of-the-arts. |
| Tasks | |
| Published | 2018-07-16 |
| URL | http://arxiv.org/abs/1807.06010v1 |
| http://arxiv.org/pdf/1807.06010v1.pdf | |
| PWC | https://paperswithcode.com/paper/ec-net-an-edge-aware-point-set-consolidation |
| Repo | |
| Framework | |
Curriculum goal masking for continuous deep reinforcement learning
| Title | Curriculum goal masking for continuous deep reinforcement learning |
| Authors | Manfred Eppe, Sven Magg, Stefan Wermter |
| Abstract | Deep reinforcement learning has recently gained a focus on problems where policy or value functions are independent of goals. Evidence exists that the sampling of goals has a strong effect on the learning performance, but there is a lack of general mechanisms that focus on optimizing the goal sampling process. In this work, we present a simple and general goal masking method that also allows us to estimate a goal’s difficulty level and thus realize a curriculum learning approach for deep RL. Our results indicate that focusing on goals with a medium difficulty level is appropriate for deep deterministic policy gradient (DDPG) methods, while an “aim for the stars and reach the moon-strategy”, where hard goals are sampled much more often than simple goals, leads to the best learning performance in cases where DDPG is combined with for hindsight experience replay (HER). We demonstrate that the approach significantly outperforms standard goal sampling for different robotic object manipulation problems. |
| Tasks | |
| Published | 2018-09-17 |
| URL | http://arxiv.org/abs/1809.06146v2 |
| http://arxiv.org/pdf/1809.06146v2.pdf | |
| PWC | https://paperswithcode.com/paper/curriculum-goal-masking-for-continuous-deep |
| Repo | |
| Framework | |
An Enhanced Multi-Objective Biogeography-Based Optimization Algorithm for Automatic Detection of Overlapping Communities in a Social Network with Node Attributes
| Title | An Enhanced Multi-Objective Biogeography-Based Optimization Algorithm for Automatic Detection of Overlapping Communities in a Social Network with Node Attributes |
| Authors | Ali Reihanian, Mohammad-Reza Feizi-Derakhshi, Hadi S. Aghdasi |
| Abstract | Community detection is one of the most important and interesting issues in social network analysis. In recent years, simultaneous considering of nodes’ attributes and topological structures of social networks in the process of community detection has attracted the attentions of many scholars, and this consideration has been recently used in some community detection methods to increase their efficiencies and to enhance their performances in finding meaningful and relevant communities. But the problem is that most of these methods tend to find non-overlapping communities, while many real-world networks include communities that often overlap to some extent. In order to solve this problem, an evolutionary algorithm called MOBBO-OCD, which is based on multi-objective biogeography-based optimization (BBO), is proposed in this paper to automatically find overlapping communities in a social network with node attributes with synchronously considering the density of connections and the similarity of nodes’ attributes in the network. In MOBBO-OCD, an extended locus-based adjacency representation called OLAR is introduced to encode and decode overlapping communities. Based on OLAR, a rank-based migration operator along with a novel two-phase mutation strategy and a new double-point crossover are used in the evolution process of MOBBO-OCD to effectively lead the population into the evolution path. In order to assess the performance of MOBBO-OCD, a new metric called alpha_SAEM is proposed in this paper, which is able to evaluate the goodness of both overlapping and non-overlapping partitions with considering the two aspects of node attributes and linkage structure. Quantitative evaluations reveal that MOBBO-OCD achieves favorable results which are quite superior to the results of 15 relevant community detection algorithms in the literature. |
| Tasks | Community Detection |
| Published | 2018-11-06 |
| URL | http://arxiv.org/abs/1811.02309v1 |
| http://arxiv.org/pdf/1811.02309v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-enhanced-multi-objective-biogeography |
| Repo | |
| Framework | |
Unsupervised Deep Features for Remote Sensing Image Matching via Discriminator Network
| Title | Unsupervised Deep Features for Remote Sensing Image Matching via Discriminator Network |
| Authors | Mohbat Tharani, Numan Khurshid, Murtaza Taj |
| Abstract | The advent of deep perceptual networks brought about a paradigm shift in machine vision and image perception. Image apprehension lately carried out by hand-crafted features in the latent space have been replaced by deep features acquired from supervised networks for improved understanding. However, such deep networks require strict supervision with a substantial amount of the labeled data for authentic training process. These methods perform poorly in domains lacking labeled data especially in case of remote sensing image retrieval. Resolving this, we propose an unsupervised encoder-decoder feature for remote sensing image matching (RSIM). Moreover, we replace the conventional distance metrics with a deep discriminator network to identify the similarity of the image pairs. To the best of our knowledge, discriminator network has never been used before for solving RSIM problem. Results have been validated with two publicly available benchmark remote sensing image datasets. The technique has also been investigated for content-based remote sensing image retrieval (CBRSIR); one of the widely used applications of RSIM. Results demonstrate that our technique supersedes the state-of-the-art methods used for unsupervised image matching with mean average precision (mAP) of 81%, and image retrieval with an overall improvement in mAP score of about 12%. |
| Tasks | Image Retrieval |
| Published | 2018-10-15 |
| URL | http://arxiv.org/abs/1810.06470v1 |
| http://arxiv.org/pdf/1810.06470v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-deep-features-for-remote-sensing |
| Repo | |
| Framework | |
SLIM LSTMs
| Title | SLIM LSTMs |
| Authors | Fathi M. Salem |
| Abstract | Long Short-Term Memory (LSTM) Recurrent Neural networks (RNNs) rely on gating signals, each driven by a function of a weighted sum of at least 3 components: (i) one of an adaptive weight matrix multiplied by the incoming external input vector sequence, (ii) one adaptive weight matrix multiplied by the previous memory/state vector, and (iii) one adaptive bias vector. In effect, they augment the simple Recurrent Neural Networks (sRNNs) structure with the addition of a “memory cell” and the incorporation of at most 3 gating signals. The standard LSTM structure and components encompass redundancy and overly increased parameterization. In this paper, we systemically introduce variants of the LSTM RNNs, referred to as SLIM LSTMs. These variants express aggressively reduced parameterizations to achieve computational saving and/or speedup in (training) performance—while necessarily retaining (validation accuracy) performance comparable to the standard LSTM RNN. |
| Tasks | |
| Published | 2018-12-29 |
| URL | http://arxiv.org/abs/1812.11391v1 |
| http://arxiv.org/pdf/1812.11391v1.pdf | |
| PWC | https://paperswithcode.com/paper/slim-lstms |
| Repo | |
| Framework | |
