Paper Group ANR 1223
LayoutVAE: Stochastic Scene Layout Generation From a Label Set. Legal entity recognition in an agglutinating language and document connection network for EU Legislation and EU/Hungarian Case Law. Types for Parallel Complexity in the Pi-calculus. Word Embedding Visualization Via Dictionary Learning. Faster and Safer Training by Embedding High-Level …
LayoutVAE: Stochastic Scene Layout Generation From a Label Set
| Title | LayoutVAE: Stochastic Scene Layout Generation From a Label Set |
| Authors | Akash Abdu Jyothi, Thibaut Durand, Jiawei He, Leonid Sigal, Greg Mori |
| Abstract | Recently there is an increasing interest in scene generation within the research community. However, models used for generating scene layouts from textual description largely ignore plausible visual variations within the structure dictated by the text. We propose LayoutVAE, a variational autoencoder based framework for generating stochastic scene layouts. LayoutVAE is a versatile modeling framework that allows for generating full image layouts given a label set, or per label layouts for an existing image given a new label. In addition, it is also capable of detecting unusual layouts, potentially providing a way to evaluate layout generation problem. Extensive experiments on MNIST-Layouts and challenging COCO 2017 Panoptic dataset verifies the effectiveness of our proposed framework. |
| Tasks | Scene Generation |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10719v2 |
| https://arxiv.org/pdf/1907.10719v2.pdf | |
| PWC | https://paperswithcode.com/paper/layoutvae-stochastic-scene-layout-generation |
| Repo | |
| Framework | |
Legal entity recognition in an agglutinating language and document connection network for EU Legislation and EU/Hungarian Case Law
| Title | Legal entity recognition in an agglutinating language and document connection network for EU Legislation and EU/Hungarian Case Law |
| Authors | György Görög, Péter Weisz |
| Abstract | We have developed an application aiming at federated search for EU and Hungarian legislation and jurisdiction. It now contains above 1 million documents, with daily updates. The database holds documents downloaded from the EU sources EUR-Lex and Curia Online as well as public jurisdiction documents from the Constitutional Court of Hungary and The National Office for The Judiciary. The application is termed Justeus. Justeus provides comprehensible search possibilities. Besides free text and metadata (dropdown list) searches, it features hierarchical data structures (concept hierarchy trees) of directory codes and classification as well as subject terms. Justeus collects all links of a particular document to other documents (court judgements citing other case law documents as well as legislation, national court decisions referring to EU regulation etc.) as tables and directed graph networks. Choosing a document, its relations to other documents are visualized in real time as a network. Network graphs help in identifying key documents influencing or referred by many other documents (legislative and/or jurisdictive) and sets of documents predominantly referring to each other (citation networks). |
| Tasks | |
| Published | 2019-07-29 |
| URL | https://arxiv.org/abs/1907.12280v1 |
| https://arxiv.org/pdf/1907.12280v1.pdf | |
| PWC | https://paperswithcode.com/paper/legal-entity-recognition-in-an-agglutinating |
| Repo | |
| Framework | |
Types for Parallel Complexity in the Pi-calculus
| Title | Types for Parallel Complexity in the Pi-calculus |
| Authors | Patrick Baillot, Alexis Ghyselen |
| Abstract | Type systems as a way to control or analyze programs have been largely studied in the context of functional programming languages. Some of those work allow to extract from a typing derivation for a program a complexity bound on this program. We present how to adapt this result for parallel complexity in the pi-calculus, as a model of concurrency and parallel communication. We study two notions of time complexity: the total computation time without parallelism (the work) and the computation time under maximal parallelism (the span). We define reduction relations in the pi-calculus to capture those two notions, and we present two type systems from which one can extract a complexity bound on a process. The type systems are inspired by input/output types and size types, with temporal information about communications. |
| Tasks | |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.02145v1 |
| https://arxiv.org/pdf/1910.02145v1.pdf | |
| PWC | https://paperswithcode.com/paper/types-for-parallel-complexity-in-the-pi |
| Repo | |
| Framework | |
Word Embedding Visualization Via Dictionary Learning
| Title | Word Embedding Visualization Via Dictionary Learning |
| Authors | Juexiao Zhang, Yubei Chen, Brian Cheung, Bruno A Olshausen |
| Abstract | Co-occurrence statistics based word embedding techniques have proved to be very useful in extracting the semantic and syntactic representation of words as low dimensional continuous vectors. In this work, we discovered that dictionary learning can open up these word vectors as a linear combination of more elementary word factors. We demonstrate many of the learned factors have surprisingly strong semantic or syntactic meaning corresponding to the factors previously identified manually by human inspection. Thus dictionary learning provides a powerful visualization tool for understanding word embedding representations. Furthermore, we show that the word factors can help in identifying key semantic and syntactic differences in word analogy tasks and improve upon the state-of-the-art word embedding techniques in these tasks by a large margin. |
| Tasks | Dictionary Learning |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.03833v1 |
| https://arxiv.org/pdf/1910.03833v1.pdf | |
| PWC | https://paperswithcode.com/paper/word-embedding-visualization-via-dictionary |
| Repo | |
| Framework | |
Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning
| Title | Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning |
| Authors | Haodi Zhang, Zihang Gao, Yi Zhou, Hao Zhang, Kaishun Wu, Fangzhen Lin |
| Abstract | Deep reinforcement learning has been successfully used in many dynamic decision making domains, especially those with very large state spaces. However, it is also well-known that deep reinforcement learning can be very slow and resource intensive. The resulting system is often brittle and difficult to explain. In this paper, we attempt to address some of these problems by proposing a framework of Rule-interposing Learning (RIL) that embeds high level rules into the deep reinforcement learning. With some good rules, this framework not only can accelerate the learning process, but also keep it away from catastrophic explorations, thus making the system relatively stable even during the very early stage of training. Moreover, given the rules are high level and easy to interpret, they can be easily maintained, updated and shared with other similar tasks. |
| Tasks | Decision Making |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09986v1 |
| https://arxiv.org/pdf/1910.09986v1.pdf | |
| PWC | https://paperswithcode.com/paper/faster-and-safer-training-by-embedding-high |
| Repo | |
| Framework | |
Indoor dense depth map at drone hovering
| Title | Indoor dense depth map at drone hovering |
| Authors | Arindam Saha, Soumyadip Maity, Brojeshwar Bhowmick |
| Abstract | Autonomous Micro Aerial Vehicles (MAVs) gained tremendous attention in recent years. Autonomous flight in indoor requires a dense depth map for navigable space detection which is the fundamental component for autonomous navigation. In this paper, we address the problem of reconstructing dense depth while a drone is hovering (small camera motion) in indoor scenes using already estimated cameras and sparse point cloud obtained from a vSLAM. We start by segmenting the scene based on sudden depth variation using sparse 3D points and introduce a patch-based local plane fitting via energy minimization which combines photometric consistency and co-planarity with neighbouring patches. The method also combines a plane sweep technique for image segments having almost no sparse point for initialization. Experiments show, the proposed method produces better depth for indoor in artificial lighting condition, low-textured environment compared to earlier literature in small motion. |
| Tasks | Autonomous Navigation |
| Published | 2019-04-25 |
| URL | http://arxiv.org/abs/1904.11175v1 |
| http://arxiv.org/pdf/1904.11175v1.pdf | |
| PWC | https://paperswithcode.com/paper/indoor-dense-depth-map-at-drone-hovering |
| Repo | |
| Framework | |
A Neural Network-Evolutionary Computational Framework for Remaining Useful Life Estimation of Mechanical Systems
| Title | A Neural Network-Evolutionary Computational Framework for Remaining Useful Life Estimation of Mechanical Systems |
| Authors | David Laredo, Zhaoyin Chen, Oliver Schütze, Jian-Qiao Sun |
| Abstract | This paper presents a framework for estimating the remaining useful life (RUL) of mechanical systems. The framework consists of a multi-layer perceptron and an evolutionary algorithm for optimizing the data-related parameters. The framework makes use of a strided time window to estimate the RUL for mechanical components. Tuning the data-related parameters can become a very time consuming task. The framework presented here automatically reshapes the data such that the efficiency of the model is increased. Furthermore, the complexity of the model is kept low, e.g. neural networks with few hidden layers and few neurons at each layer. Having simple models has several advantages like short training times and the capacity of being in environments with limited computational resources such as embedded systems. The proposed method is evaluated on the publicly available C-MAPSS dataset, its accuracy is compared against other state-of-the art methods for the same dataset. |
| Tasks | |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.05918v1 |
| https://arxiv.org/pdf/1905.05918v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-neural-network-evolutionary-computational |
| Repo | |
| Framework | |
Runtime Analysis of the Univariate Marginal Distribution Algorithm under Low Selective Pressure and Prior Noise
| Title | Runtime Analysis of the Univariate Marginal Distribution Algorithm under Low Selective Pressure and Prior Noise |
| Authors | Per Kristian Lehre, Phan Trung Hai Nguyen |
| Abstract | We perform a rigorous runtime analysis for the Univariate Marginal Distribution Algorithm on the LeadingOnes function, a well-known benchmark function in the theory community of evolutionary computation with a high correlation between decision variables. For a problem instance of size $n$, the currently best known upper bound on the expected runtime is $\mathcal{O}(n\lambda\log\lambda+n^2)$ (Dang and Lehre, GECCO 2015), while a lower bound necessary to understand how the algorithm copes with variable dependencies is still missing. Motivated by this, we show that the algorithm requires a $e^{\Omega(\mu)}$ runtime with high probability and in expectation if the selective pressure is low; otherwise, we obtain a lower bound of $\Omega(\frac{n\lambda}{\log(\lambda-\mu)})$ on the expected runtime. Furthermore, we for the first time consider the algorithm on the function under a prior noise model and obtain an $\mathcal{O}(n^2)$ expected runtime for the optimal parameter settings. In the end, our theoretical results are accompanied by empirical findings, not only matching with rigorous analyses but also providing new insights into the behaviour of the algorithm. |
| Tasks | |
| Published | 2019-04-19 |
| URL | http://arxiv.org/abs/1904.09239v1 |
| http://arxiv.org/pdf/1904.09239v1.pdf | |
| PWC | https://paperswithcode.com/paper/runtime-analysis-of-the-univariate-marginal |
| Repo | |
| Framework | |
Limits of Deepfake Detection: A Robust Estimation Viewpoint
| Title | Limits of Deepfake Detection: A Robust Estimation Viewpoint |
| Authors | Sakshi Agarwal, Lav R. Varshney |
| Abstract | Deepfake detection is formulated as a hypothesis testing problem to classify an image as genuine or GAN-generated. A robust statistics view of GANs is considered to bound the error probability for various GAN implementations in terms of their performance. The bounds are further simplified using a Euclidean approximation for the low error regime. Lastly, relationships between error probability and epidemic thresholds for spreading processes in networks are established. |
| Tasks | DeepFake Detection, Face Swapping |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03493v1 |
| https://arxiv.org/pdf/1905.03493v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503493 |
| Repo | |
| Framework | |
Reduced-Order Modeling of Deep Neural Networks
| Title | Reduced-Order Modeling of Deep Neural Networks |
| Authors | Talgat Daulbaev, Julia Gusak, Evgeny Ponomarev, Andrzej Cichocki, Ivan Oseledets |
| Abstract | We introduce a new method for speeding up the inference of deep neural networks. It is somewhat inspired by the reduced-order modeling techniques for dynamical systems.The cornerstone of the proposed method is the maximum volume algorithm. We demonstrate efficiency on neural networks pre-trained on different datasets. We show that in many practical cases it is possible to replace convolutional layers with much smaller fully-connected layers with a relatively small drop in accuracy. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06995v3 |
| https://arxiv.org/pdf/1910.06995v3.pdf | |
| PWC | https://paperswithcode.com/paper/reduced-order-modeling-of-deep-neural |
| Repo | |
| Framework | |
Topic-Guided Variational Autoencoders for Text Generation
| Title | Topic-Guided Variational Autoencoders for Text Generation |
| Authors | Wenlin Wang, Zhe Gan, Hongteng Xu, Ruiyi Zhang, Guoyin Wang, Dinghan Shen, Changyou Chen, Lawrence Carin |
| Abstract | We propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Gaussian prior for the latent code, our model specifies the prior as a Gaussian mixture model (GMM) parametrized by a neural topic module. Each mixture component corresponds to a latent topic, which provides guidance to generate sentences under the topic. The neural topic module and the VAE-based neural sequence module in our model are learned jointly. In particular, a sequence of invertible Householder transformations is applied to endow the approximate posterior of the latent code with high flexibility during model inference. Experimental results show that our TGVAE outperforms alternative approaches on both unconditional and conditional text generation, which can generate semantically-meaningful sentences with various topics. |
| Tasks | Text Generation |
| Published | 2019-03-17 |
| URL | http://arxiv.org/abs/1903.07137v1 |
| http://arxiv.org/pdf/1903.07137v1.pdf | |
| PWC | https://paperswithcode.com/paper/topic-guided-variational-autoencoders-for |
| Repo | |
| Framework | |
Impact of Training Dataset Size on Neural Answer Selection Models
| Title | Impact of Training Dataset Size on Neural Answer Selection Models |
| Authors | Trond Linjordet, Krisztian Balog |
| Abstract | It is held as a truism that deep neural networks require large datasets to train effective models. However, large datasets, especially with high-quality labels, can be expensive to obtain. This study sets out to investigate (i) how large a dataset must be to train well-performing models, and (ii) what impact can be shown from fractional changes to the dataset size. A practical method to investigate these questions is to train a collection of deep neural answer selection models using fractional subsets of varying sizes of an initial dataset. We observe that dataset size has a conspicuous lack of effect on the training of some of these models, bringing the underlying algorithms into question. |
| Tasks | Answer Selection |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.10496v1 |
| http://arxiv.org/pdf/1901.10496v1.pdf | |
| PWC | https://paperswithcode.com/paper/impact-of-training-dataset-size-on-neural |
| Repo | |
| Framework | |
Improving Model Robustness Using Causal Knowledge
| Title | Improving Model Robustness Using Causal Knowledge |
| Authors | Trent Kyono, Mihaela van der Schaar |
| Abstract | For decades, researchers in fields, such as the natural and social sciences, have been verifying causal relationships and investigating hypotheses that are now well-established or understood as truth. These causal mechanisms are properties of the natural world, and thus are invariant conditions regardless of the collection domain or environment. We show in this paper how prior knowledge in the form of a causal graph can be utilized to guide model selection, i.e., to identify from a set of trained networks the models that are the most robust and invariant to unseen domains. Our method incorporates prior knowledge (which can be incomplete) as a Structural Causal Model (SCM) and calculates a score based on the likelihood of the SCM given the target predictions of a candidate model and the provided input variables. We show on both publicly available and synthetic datasets that our method is able to identify more robust models in terms of generalizability to unseen out-of-distribution test examples and domains where covariates have shifted. |
| Tasks | Model Selection |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.12441v1 |
| https://arxiv.org/pdf/1911.12441v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-model-robustness-using-causal |
| Repo | |
| Framework | |
MRI Super-Resolution with Ensemble Learning and Complementary Priors
| Title | MRI Super-Resolution with Ensemble Learning and Complementary Priors |
| Authors | Qing Lyu, Hongming Shan, Ge Wang |
| Abstract | Magnetic resonance imaging (MRI) is a widely used medical imaging modality. However, due to the limitations in hardware, scan time, and throughput, it is often clinically challenging to obtain high-quality MR images. The super-resolution approach is potentially promising to improve MR image quality without any hardware upgrade. In this paper, we propose an ensemble learning and deep learning framework for MR image super-resolution. In our study, we first enlarged low resolution images using 5 commonly used super-resolution algorithms and obtained differentially enlarged image datasets with complementary priors. Then, a generative adversarial network (GAN) is trained with each dataset to generate super-resolution MR images. Finally, a convolutional neural network is used for ensemble learning that synergizes the outputs of GANs into the final MR super-resolution images. According to our results, the ensemble learning results outcome any one of GAN outputs. Compared with some state-of-the-art deep learning-based super-resolution methods, our approach is advantageous in suppressing artifacts and keeping more image details. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-07-06 |
| URL | https://arxiv.org/abs/1907.03063v1 |
| https://arxiv.org/pdf/1907.03063v1.pdf | |
| PWC | https://paperswithcode.com/paper/mri-super-resolution-with-ensemble-learning |
| Repo | |
| Framework | |
Digital filters with vanishing moments for shape analysis
| Title | Digital filters with vanishing moments for shape analysis |
| Authors | Hugh L. Kennedy |
| Abstract | Shape- and scale-selective digital-filters, with steerable finite/infinite impulse responses (FIR/IIRs) and non-recursive/recursive realizations, that are separable in both spatial dimensions and adequately isotropic, are derived. The filters are conveniently designed in the frequency domain via derivative constraints at dc, which guarantees orthogonality and monomial selectivity in the pixel domain (i.e. vanishing moments), unlike more commonly used FIR filters derived from Gaussian functions. A two-stage low-pass/high-pass architecture, for blur/derivative operations, is recommended. Expressions for the coefficients of a low-order IIR blur filter with repeated poles are provided, as a function of scale; discrete Butterworth (IIR), and colored Savitzky-Golay (FIR), blurs are also examined. Parallel software implementations on central processing units (CPUs) and graphics processing units (GPUs), for scale-selective blob-detection in aerial surveillance imagery, are analyzed. It is shown that recursive IIR filters are significantly faster than non-recursive FIR filters when detecting large objects at coarse scales, i.e. using filters with long impulse responses; however, the margin of outperformance decreases as the degree of parallelization increases. |
| Tasks | |
| Published | 2019-12-15 |
| URL | https://arxiv.org/abs/1912.07133v3 |
| https://arxiv.org/pdf/1912.07133v3.pdf | |
| PWC | https://paperswithcode.com/paper/digital-filters-with-vanishing-moments-for |
| Repo | |
| Framework | |
