October 18, 2019

3222 words 16 mins read

Paper Group ANR 509

Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks. Modelling Point Spread Function in Fluorescence Microscopy with a Sparse Combination of Gaussian Mixture: Trade-off between Accuracy and Efficiency. mQAPViz: A divide-and-conquer multi-objective optimization algorithm to compute large data visualizations. Diversity …

Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks


Title	Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks
Authors	Felix Leibfried, Peter Vrancx
Abstract	This paper proposes a new optimization objective for value-based deep reinforcement learning. We extend conventional Deep Q-Networks (DQNs) by adding a model-learning component yielding a transcoder network. The prediction errors for the model are included in the basic DQN loss as additional regularizers. This augmented objective leads to a richer training signal that provides feedback at every time step. Moreover, because learning an environment model shares a common structure with the RL problem, we hypothesize that the resulting objective improves both sample efficiency and performance. We empirically confirm our hypothesis on a range of 20 games from the Atari benchmark attaining superior results over vanilla DQN without model-based regularization.
Tasks
Published	2018-09-06
URL	http://arxiv.org/abs/1809.01906v2
PDF	http://arxiv.org/pdf/1809.01906v2.pdf
PWC	https://paperswithcode.com/paper/model-based-regularization-for-deep
Repo
Framework

Modelling Point Spread Function in Fluorescence Microscopy with a Sparse Combination of Gaussian Mixture: Trade-off between Accuracy and Efficiency


Title	Modelling Point Spread Function in Fluorescence Microscopy with a Sparse Combination of Gaussian Mixture: Trade-off between Accuracy and Efficiency
Authors	Denis K. Samuylov, Prateek Purwar, Gábor Székely, Grégory Paul
Abstract	Deblurring is a fundamental inverse problem in bioimaging. It requires modelling the point spread function (PSF), which captures the optical distortions entailed by the image formation process. The PSF limits the spatial resolution attainable for a given microscope. However, recent applications require a higher resolution, and have prompted the development of super-resolution techniques to achieve sub-pixel accuracy. This requirement restricts the class of suitable PSF models to analog ones. In addition, deblurring is computationally intensive, hence further requiring computationally efficient models. A custom candidate fitting both requirements is the Gaussian model. However, this model cannot capture the rich tail structures found in both theoretical and empirical PSFs. In this paper, we aim at improving the reconstruction accuracy beyond the Gaussian model, while preserving its computational efficiency. We introduce a new class of analog PSF models based on Gaussian mixtures. The number of Gaussian kernels controls both the modelling accuracy and the computational efficiency of the model: the lower the number of kernels, the lower accuracy and the higher efficiency. To explore the accuracy–efficiency trade-off, we propose a variational formulation of the PSF calibration problem, where a convex sparsity-inducing penalty on the number of Gaussian kernels allows trading accuracy for efficiency. We derive an efficient algorithm based on a fully-split formulation of alternating split Bregman. We assess our framework on synthetic and real data and demonstrate a better reconstruction accuracy in both geometry and photometry in point source localisation—a fundamental inverse problem in fluorescence microscopy.
Tasks	Calibration, Deblurring, Super-Resolution
Published	2018-09-05
URL	http://arxiv.org/abs/1809.01579v2
PDF	http://arxiv.org/pdf/1809.01579v2.pdf
PWC	https://paperswithcode.com/paper/modelling-point-spread-function-in
Repo
Framework

mQAPViz: A divide-and-conquer multi-objective optimization algorithm to compute large data visualizations


Title	mQAPViz: A divide-and-conquer multi-objective optimization algorithm to compute large data visualizations
Authors	Claudio Sanhueza, Francia Jiménez, Regina Berretta, Pablo Moscato
Abstract	Algorithms for data visualizations are essential tools for transforming data into useful narratives. Unfortunately, very few visualization algorithms can handle the large datasets of many real-world scenarios. In this study, we address the visualization of these datasets as a Multi-Objective Optimization Problem. We propose mQAPViz, a divide-and-conquer multi-objective optimization algorithm to compute large-scale data visualizations. Our method employs the Multi-Objective Quadratic Assignment Problem (mQAP) as the mathematical foundation to solve the visualization task at hand. The algorithm applies advanced sampling techniques originating from the field of machine learning and efficient data structures to scale to millions of data objects. The algorithm allocates objects onto a 2D grid layout. Experimental results on real-world and large datasets demonstrate that mQAPViz is a competitive alternative to existing techniques.
Tasks
Published	2018-04-02
URL	http://arxiv.org/abs/1804.00656v3
PDF	http://arxiv.org/pdf/1804.00656v3.pdf
PWC	https://paperswithcode.com/paper/mqapviz-a-divide-and-conquer-multi-objective
Repo
Framework

Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification


Title	Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification
Authors	Shuang Li, Slawomir Bak, Peter Carr, Xiaogang Wang
Abstract	Video-based person re-identification matches video clips of people across non-overlapping cameras. Most existing methods tackle this problem by encoding each video frame in its entirety and computing an aggregate representation across all frames. In practice, people are often partially occluded, which can corrupt the extracted features. Instead, we propose a new spatiotemporal attention model that automatically discovers a diverse set of distinctive body parts. This allows useful information to be extracted from all frames without succumbing to occlusions and misalignments. The network learns multiple spatial attention models and employs a diversity regularization term to ensure multiple models do not discover the same body part. Features extracted from local image regions are organized by spatial attention model and are combined using temporal attention. As a result, the network learns latent representations of the face, torso and other body parts using the best available image patches from the entire video sequence. Extensive evaluations on three datasets show that our framework outperforms the state-of-the-art approaches by large margins on multiple metrics.
Tasks	Person Re-Identification, Video-Based Person Re-Identification
Published	2018-03-27
URL	http://arxiv.org/abs/1803.09882v1
PDF	http://arxiv.org/pdf/1803.09882v1.pdf
PWC	https://paperswithcode.com/paper/diversity-regularized-spatiotemporal
Repo
Framework

DiDA: Disentangled Synthesis for Domain Adaptation


Title	DiDA: Disentangled Synthesis for Domain Adaptation
Authors	Jinming Cao, Oren Katzir, Peng Jiang, Dani Lischinski, Danny Cohen-Or, Changhe Tu, Yangyan Li
Abstract	Unsupervised domain adaptation aims at learning a shared model for two related, but not identical, domains by leveraging supervision from a source domain to an unsupervised target domain. A number of effective domain adaptation approaches rely on the ability to extract discriminative, yet domain-invariant, latent factors which are common to both domains. Extracting latent commonality is also useful for disentanglement analysis, enabling separation between the common and the domain-specific features of both domains. In this paper, we present a method for boosting domain adaptation performance by leveraging disentanglement analysis. The key idea is that by learning to separately extract both the common and the domain-specific features, one can synthesize more target domain data with supervision, thereby boosting the domain adaptation performance. Better common feature extraction, in turn, helps further improve the disentanglement analysis and disentangled synthesis. We show that iterating between domain adaptation and disentanglement analysis can consistently improve each other on several unsupervised domain adaptation tasks, for various domain adaptation backbone models.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08019v1
PDF	http://arxiv.org/pdf/1805.08019v1.pdf
PWC	https://paperswithcode.com/paper/dida-disentangled-synthesis-for-domain
Repo
Framework

Implanting Rational Knowledge into Distributed Representation at Morpheme Level


Title	Implanting Rational Knowledge into Distributed Representation at Morpheme Level
Authors	Zi Lin, Yang Liu
Abstract	Previously, researchers paid no attention to the creation of unambiguous morpheme embeddings independent from the corpus, while such information plays an important role in expressing the exact meanings of words for parataxis languages like Chinese. In this paper, after constructing the Chinese lexical and semantic ontology based on word-formation, we propose a novel approach to implanting the structured rational knowledge into distributed representation at morpheme level, naturally avoiding heavy disambiguation in the corpus. We design a template to create the instances as pseudo-sentences merely from the pieces of knowledge of morphemes built in the lexicon. To exploit hierarchical information and tackle the data sparseness problem, the instance proliferation technique is applied based on similarity to expand the collection of pseudo-sentences. The distributed representation for morphemes can then be trained on these pseudo-sentences using word2vec. For evaluation, we validate the paradigmatic and syntagmatic relations of morpheme embeddings, and apply the obtained embeddings to word similarity measurement, achieving significant improvements over the classical models by more than 5 Spearman scores or 8 percentage points, which shows very promising prospects for adoption of the new source of knowledge.
Tasks
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10188v1
PDF	http://arxiv.org/pdf/1811.10188v1.pdf
PWC	https://paperswithcode.com/paper/implanting-rational-knowledge-into
Repo
Framework

A Deterministic Self-Organizing Map Approach and its Application on Satellite Data based Cloud Type Classification


Title	A Deterministic Self-Organizing Map Approach and its Application on Satellite Data based Cloud Type Classification
Authors	Wenbin Zhang, Jianwu Wang, Daeho Jin, Lazaros Oreopoulos, Zhibo Zhang
Abstract	A self-organizing map (SOM) is a type of competitive artificial neural network, which projects the high-dimensional input space of the training samples into a low-dimensional space with the topology relations preserved. This makes SOMs supportive of organizing and visualizing complex data sets and have been pervasively used among numerous disciplines with different applications. Notwithstanding its wide applications, the self-organizing map is perplexed by its inherent randomness, which produces dissimilar SOM patterns even when being trained on identical training samples with the same parameters every time, and thus causes usability concerns for other domain practitioners and precludes more potential users from exploring SOM based applications in a broader spectrum. Motivated by this practical concern, we propose a deterministic approach as a supplement to the standard self-organizing map. In accordance with the theoretical design, the experimental results with satellite cloud data demonstrate the effective and efficient organization as well as simplification capabilities of the proposed approach.
Tasks
Published	2018-08-24
URL	http://arxiv.org/abs/1808.08315v2
PDF	http://arxiv.org/pdf/1808.08315v2.pdf
PWC	https://paperswithcode.com/paper/a-deterministic-self-organizing-map-approach
Repo
Framework

Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video


Title	Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video
Authors	Samvit Jain, Xin Wang, Joseph Gonzalez
Abstract	We present Accel, a novel semantic video segmentation system that achieves high accuracy at low inference cost by combining the predictions of two network branches: (1) a reference branch that extracts high-detail features on a reference keyframe, and warps these features forward using frame-to-frame optical flow estimates, and (2) an update branch that computes features of adjustable quality on the current frame, performing a temporal update at each video frame. The modularity of the update branch, where feature subnetworks of varying layer depth can be inserted (e.g. ResNet-18 to ResNet-101), enables operation over a new, state-of-the-art accuracy-throughput trade-off spectrum. Over this curve, Accel models achieve both higher accuracy and faster inference times than the closest comparable single-frame segmentation networks. In general, Accel significantly outperforms previous work on efficient semantic video segmentation, correcting warping-related error that compounds on datasets with complex dynamics. Accel is end-to-end trainable and highly modular: the reference network, the optical flow network, and the update network can each be selected independently, depending on application requirements, and then jointly fine-tuned. The result is a robust, general system for fast, high-accuracy semantic segmentation on video.
Tasks	Optical Flow Estimation, Semantic Segmentation, Video Semantic Segmentation
Published	2018-07-17
URL	https://arxiv.org/abs/1807.06667v4
PDF	https://arxiv.org/pdf/1807.06667v4.pdf
PWC	https://paperswithcode.com/paper/accel-a-corrective-fusion-network-for
Repo
Framework

An Efficient Matheuristic for the Minimum-Weight Dominating Set Problem


Title	An Efficient Matheuristic for the Minimum-Weight Dominating Set Problem
Authors	Mayra Albuquerque, Thibaut Vidal
Abstract	A minimum dominating set in a graph is a minimum set of vertices such that every vertex of the graph either belongs to it, or is adjacent to one vertex of this set. This mathematical object is of high relevance in a number of applications related to social networks analysis, design of wireless networks, coding theory, and data mining, among many others. When vertex weights are given, minimizing the total weight of the dominating set gives rise to a problem variant known as the minimum weight dominating set problem. To solve this problem, we introduce a hybrid matheuristic combining a tabu search with an integer programming solver. The latter is used to solve subproblems in which only a fraction of the decision variables, selected relatively to the search history, are left free while the others are fixed. Moreover, we introduce an adaptive penalty to promote the exploration of intermediate infeasible solutions during the search, enhance the algorithm with perturbations and node elimination procedures, and exploit richer neighborhood classes. Extensive experimental analyses on a variety of instance classes demonstrate the good performance of the algorithm, and the contribution of each component in the success of the search is analyzed.
Tasks
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09809v1
PDF	http://arxiv.org/pdf/1808.09809v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-matheuristic-for-the-minimum
Repo
Framework

Deep Feature Learning of Multi-Network Topology for Node Classification


Title	Deep Feature Learning of Multi-Network Topology for Node Classification
Authors	Hansheng Xue, Jiajie Peng, Xuequn Shang
Abstract	Networks are ubiquitous structure that describes complex relationships between different entities in the real world. As a critical component of prediction task over nodes in networks, learning the feature representation of nodes has become one of the most active areas recently. Network Embedding, aiming to learn non-linear and low-dimensional feature representation based on network topology, has been proved to be helpful on tasks of network analysis, especially node classification. For many real-world systems, multiple types of relations are naturally represented by multiple networks. However, existing network embedding methods mainly focus on single network embedding and neglect the information shared among different networks. In this paper, we propose a novel multiple network embedding method based on semisupervised autoencoder, named DeepMNE, which captures complex topological structures of multi-networks and takes the correlation among multi-networks into account. We evaluate DeepMNE on the task of node classification with two real-world datasets. The experimental results demonstrate the superior performance of our method over four state-of-the-art algorithms.
Tasks	Network Embedding, Node Classification
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02394v1
PDF	http://arxiv.org/pdf/1809.02394v1.pdf
PWC	https://paperswithcode.com/paper/deep-feature-learning-of-multi-network
Repo
Framework

Unsupervised Text Style Transfer using Language Models as Discriminators


Title	Unsupervised Text Style Transfer using Language Models as Discriminators
Authors	Zichao Yang, Zhiting Hu, Chris Dyer, Eric P. Xing, Taylor Berg-Kirkpatrick
Abstract	Binary classifiers are often employed as discriminators in GAN-based unsupervised style transfer systems to ensure that transferred sentences are similar to sentences in the target domain. One difficulty with this approach is that the error signal provided by the discriminator can be unstable and is sometimes insufficient to train the generator to produce fluent language. In this paper, we propose a new technique that uses a target domain language model as the discriminator, providing richer and more stable token-level feedback during the learning process. We train the generator to minimize the negative log likelihood (NLL) of generated sentences, evaluated by the language model. By using a continuous approximation of discrete sampling under the generator, our model can be trained using back-propagation in an end- to-end fashion. Moreover, our empirical results show that when using a language model as a structured discriminator, it is possible to forgo adversarial steps during training, making the process more stable. We compare our model with previous work using convolutional neural networks (CNNs) as discriminators and show that our approach leads to improved performance on three tasks: word substitution decipherment, sentiment modification, and related language translation.
Tasks	Language Modelling, Style Transfer, Text Style Transfer
Published	2018-05-30
URL	http://arxiv.org/abs/1805.11749v3
PDF	http://arxiv.org/pdf/1805.11749v3.pdf
PWC	https://paperswithcode.com/paper/unsupervised-text-style-transfer-using
Repo
Framework

QuaSE: Accurate Text Style Transfer under Quantifiable Guidance


Title	QuaSE: Accurate Text Style Transfer under Quantifiable Guidance
Authors	Yi Liao, Lidong Bing, Piji Li, Shuming Shi, Wai Lam, Tong Zhang
Abstract	We propose the task of Quantifiable Sequence Editing (QuaSE): editing an input sequence to generate an output sequence that satisfies a given numerical outcome value measuring a certain property of the sequence, with the requirement of keeping the main content of the input sequence. For example, an input sequence could be a word sequence, such as review sentence and advertisement text. For a review sentence, the outcome could be the review rating; for an advertisement, the outcome could be the click-through rate. The major challenge in performing QuaSE is how to perceive the outcome-related wordings, and only edit them to change the outcome. In this paper, the proposed framework contains two latent factors, namely, outcome factor and content factor, disentangled from the input sentence to allow convenient editing to change the outcome and keep the content. Our framework explores the pseudo-parallel sentences by modeling their content similarity and outcome differences to enable a better disentanglement of the latent factors, which allows generating an output to better satisfy the desired outcome and keep the content. The dual reconstruction structure further enhances the capability of generating expected output by exploiting the couplings of latent factors of pseudo-parallel sentences. For evaluation, we prepared a dataset of Yelp review sentences with the ratings as outcome. Extensive experimental results are reported and discussed to elaborate the peculiarities of our framework.
Tasks	Style Transfer, Text Style Transfer
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07007v3
PDF	http://arxiv.org/pdf/1804.07007v3.pdf
PWC	https://paperswithcode.com/paper/quase-accurate-text-style-transfer-under
Repo
Framework

A State-of-the-Art of Semantic Change Computation


Title	A State-of-the-Art of Semantic Change Computation
Authors	Xuri Tang
Abstract	This paper reviews the state-of-the-art of semantic change computation, one emerging research field in computational linguistics, proposing a framework that summarizes the literature by identifying and expounding five essential components in the field: diachronic corpus, diachronic word sense characterization, change modelling, evaluation data and data visualization. Despite the potential of the field, the review shows that current studies are mainly focused on testifying hypotheses proposed in theoretical linguistics and that several core issues remain to be solved: the need for diachronic corpora of languages other than English, the need for comprehensive evaluation data for evaluation, the comparison and construction of approaches to diachronic word sense characterization and change modelling, and further exploration of data visualization techniques for hypothesis justification.
Tasks
Published	2018-01-30
URL	http://arxiv.org/abs/1801.09872v1
PDF	http://arxiv.org/pdf/1801.09872v1.pdf
PWC	https://paperswithcode.com/paper/a-state-of-the-art-of-semantic-change
Repo
Framework

Fusion Graph Convolutional Networks


Title	Fusion Graph Convolutional Networks
Authors	Priyesh Vijayan, Yash Chandak, Mitesh M. Khapra, Srinivasan Parthasarathy, Balaraman Ravindran
Abstract	Semi-supervised node classification in attributed graphs, i.e., graphs with node features, involves learning to classify unlabeled nodes given a partially labeled graph. Label predictions are made by jointly modeling the node and its’ neighborhood features. State-of-the-art models for node classification on such attributed graphs use differentiable recursive functions that enable aggregation and filtering of neighborhood information from multiple hops. In this work, we analyze the representation capacity of these models to regulate information from multiple hops independently. From our analysis, we conclude that these models despite being powerful, have limited representation capacity to capture multi-hop neighborhood information effectively. Further, we also propose a mathematically motivated, yet simple extension to existing graph convolutional networks (GCNs) which has improved representation capacity. We extensively evaluate the proposed model, F-GCN on eight popular datasets from different domains. F-GCN outperforms the state-of-the-art models for semi-supervised learning on six datasets while being extremely competitive on the other two.
Tasks	Node Classification
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12528v5
PDF	http://arxiv.org/pdf/1805.12528v5.pdf
PWC	https://paperswithcode.com/paper/fusion-graph-convolutional-networks
Repo
Framework

A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection


Title	A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection
Authors	Amena Khatun, Simon Denman, Sridha Sridharan, Clinton Fookes
Abstract	State-of-the-art person re-identification systems that employ a triplet based deep network suffer from a poor generalization capability. In this paper, we propose a four stream Siamese deep convolutional neural network for person redetection that jointly optimises verification and identification losses over a four image input group. Specifically, the proposed method overcomes the weakness of the typical triplet formulation by using groups of four images featuring two matched (i.e. the same identity) and two mismatched images. This allows us to jointly increase the interclass variations and reduce the intra-class variations in the learned feature space. The proposed approach also optimises over both the identification and verification losses, further minimising intra-class variation and maximising inter-class variation, improving overall performance. Extensive experiments on four challenging datasets, VIPeR, CUHK01, CUHK03 and PRID2011, demonstrates that the proposed approach achieves state-of-the-art performance.
Tasks	Person Re-Identification
Published	2018-12-21
URL	http://arxiv.org/abs/1812.08983v1
PDF	http://arxiv.org/pdf/1812.08983v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-four-stream-siamese-convolutional
Repo
Framework