Paper Group ANR 1413
Robust Deep Graph Based Learning for Binary Classification. Human Activity Recognition for Edge Devices. Learning Deterministic Policy with Target for Power Control in Wireless Networks. A Conditional Generative Model for Predicting Material Microstructures from Processing Methods. Unsupervised Generative 3D Shape Learning from Natural Images. Fuzz …
Robust Deep Graph Based Learning for Binary Classification
| Title | Robust Deep Graph Based Learning for Binary Classification |
| Authors | Minxiang Ye, Vladimir Stankovic, Lina Stankovic, Gene Cheung |
| Abstract | Convolutional neural network (CNN)-based feature learning has become state of the art, since given sufficient training data, CNN can significantly outperform traditional methods for various classification tasks. However, feature learning becomes more difficult if some training labels are noisy. With traditional regularization techniques, CNN often overfits to the noisy training labels, resulting in sub-par classification performance. In this paper, we propose a robust binary classifier, based on CNNs, to learn deep metric functions, which are then used to construct an optimal underlying graph structure used to clean noisy labels via graph Laplacian regularization (GLR). GLR is posed as a convex maximum a posteriori (MAP) problem solved via convex quadratic programming (QP). To penalize samples around the decision boundary, we propose two regularized loss functions for semi-supervised learning. The binary classification experiments on three datasets, varying in number and type of features, demonstrate that given a noisy training dataset, our proposed networks outperform several state-of-the-art classifiers, including label-noise robust support vector machine, CNNs with three different robust loss functions, model-based GLR, and dynamic graph CNN classifiers. |
| Tasks | |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03321v1 |
| https://arxiv.org/pdf/1912.03321v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-deep-graph-based-learning-for-binary |
| Repo | |
| Framework | |
Human Activity Recognition for Edge Devices
| Title | Human Activity Recognition for Edge Devices |
| Authors | Manjot Bilkhu, Hammababdullah Ayyubi |
| Abstract | Video activity Recognition has recently gained a lot of momentum with the release of massive Kinetics (400 and 600) data. Architectures such as I3D and C3D networks have shown state-of-the-art performances for activity recognition. The one major pitfall with these state-of-the-art networks is that they require a lot of compute. In this paper we explore how we can achieve comparable results to these state-of-the-art networks for devices-on-edge. We primarily explore two architectures - I3D and Temporal Segment Network. We show that comparable results can be achieved using one tenth the memory usage by changing the testing procedure. We also report our results on Resnet architecture as our backbone apart from the original Inception architecture. Specifically, we achieve 84.54% top-1 accuracy on UCF-101 dataset using only RGB frames. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07563v1 |
| http://arxiv.org/pdf/1903.07563v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-activity-recognition-for-edge-devices |
| Repo | |
| Framework | |
Learning Deterministic Policy with Target for Power Control in Wireless Networks
| Title | Learning Deterministic Policy with Target for Power Control in Wireless Networks |
| Authors | Yujiao Lu, Hancheng Lu, Liangliang Cao, Feng Wu, Daren Zhu |
| Abstract | Inter-Cell Interference Coordination (ICIC) is a promising way to improve energy efficiency in wireless networks, especially where small base stations are densely deployed. However, traditional optimization based ICIC schemes suffer from severe performance degradation with complex interference pattern. To address this issue, we propose a Deep Reinforcement Learning with Deterministic Policy and Target (DRL-DPT) framework for ICIC in wireless networks. DRL-DPT overcomes the main obstacles in applying reinforcement learning and deep learning in wireless networks, i.e. continuous state space, continuous action space and convergence. Firstly, a Deep Neural Network (DNN) is involved as the actor to obtain deterministic power control actions in continuous space. Then, to guarantee the convergence, an online training process is presented, which makes use of a dedicated reward function as the target rule and a policy gradient descent algorithm to adjust DNN weights. Experimental results show that the proposed DRL-DPT framework consistently outperforms existing schemes in terms of energy efficiency and throughput under different wireless interference scenarios. More specifically, it improves up to 15% of energy efficiency with faster convergence rate. |
| Tasks | |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.07903v1 |
| http://arxiv.org/pdf/1902.07903v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-deterministic-policy-with-target-for |
| Repo | |
| Framework | |
A Conditional Generative Model for Predicting Material Microstructures from Processing Methods
| Title | A Conditional Generative Model for Predicting Material Microstructures from Processing Methods |
| Authors | Akshay Iyer, Biswadip Dey, Arindam Dasgupta, Wei Chen, Amit Chakraborty |
| Abstract | Microstructures of a material form the bridge linking processing conditions - which can be controlled, to the material property - which is the primary interest in engineering applications. Thus a critical task in material design is establishing the processing-structure relationship, which requires domain expertise and techniques that can model the high-dimensional material microstructure. This work proposes a deep learning based approach that models the processing-structure relationship as a conditional image synthesis problem. In particular, we develop an auxiliary classifier Wasserstein GAN with gradient penalty (ACWGAN-GP) to synthesize microstructures under a given processing condition. This approach is free of feature engineering, requires modest domain knowledge and is applicable to a wide range of material systems. We demonstrate this approach using the ultra high carbon steel (UHCS) database, where each microstructure is annotated with a label describing the cooling method it was subjected to. Our results show that ACWGAN-GP can synthesize high-quality multiphase microstructures for a given cooling method. |
| Tasks | Feature Engineering, Image Generation |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.02133v1 |
| https://arxiv.org/pdf/1910.02133v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-conditional-generative-model-for-predicting |
| Repo | |
| Framework | |
Unsupervised Generative 3D Shape Learning from Natural Images
| Title | Unsupervised Generative 3D Shape Learning from Natural Images |
| Authors | Attila Szabó, Givi Meishvili, Paolo Favaro |
| Abstract | In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way. For example, we do not use any ground truth 3D or 2D annotations, stereo video, and ego-motion during the training. Our approach follows the general strategy of Generative Adversarial Networks, where an image generator network learns to create image samples that are realistic enough to fool a discriminator network into believing that they are natural images. In contrast, in our approach the image generation is split into 2 stages. In the first stage a generator network outputs 3D objects. In the second, a differentiable renderer produces an image of the 3D objects from random viewpoints. The key observation is that a realistic 3D object should yield a realistic rendering from any plausible viewpoint. Thus, by randomizing the choice of the viewpoint our proposed training forces the generator network to learn an interpretable 3D representation disentangled from the viewpoint. In this work, a 3D representation consists of a triangle mesh and a texture map that is used to color the triangle surface by using the UV-mapping technique. We provide analysis of our learning approach, expose its ambiguities and show how to overcome them. Experimentally, we demonstrate that our method can learn realistic 3D shapes of faces by using only the natural images of the FFHQ dataset. |
| Tasks | Image Generation |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00287v1 |
| https://arxiv.org/pdf/1910.00287v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-generative-3d-shape-learning-1 |
| Repo | |
| Framework | |
Fuzzy Rule Interpolation Methods and Fri Toolbox
| Title | Fuzzy Rule Interpolation Methods and Fri Toolbox |
| Authors | Maen Alzubi, Zsolt Csaba Johanyák, Szilveszter Kovács |
| Abstract | FRI methods are less popular in the practical application domain. One possible reason is the missing common framework. There are many FRI methods developed independently, having different interpolation concepts and features. One trial for setting up a common FRI framework was the MATLAB FRI Toolbox, developed by Johany'ak et. al. in 2006. The goals of this paper are divided as follows: firstly, to present a brief introduction of the FRI methods. Secondly, to introduce a brief description of the refreshed and extended version of the original FRI Toolbox. And thirdly, to use different unified numerical benchmark examples to evaluate and analyze the Fuzzy Rule Interpolation Techniques (FRI) (KH, KH Stabilized, MACI, IMUL, CRF, VKK, GM, FRIPOC, LESFRI, and SCALEMOVE), that will be classified and compared based on different features by following the abnormality and linearity conditions [15]. |
| Tasks | |
| Published | 2019-04-27 |
| URL | http://arxiv.org/abs/1904.12178v1 |
| http://arxiv.org/pdf/1904.12178v1.pdf | |
| PWC | https://paperswithcode.com/paper/fuzzy-rule-interpolation-methods-and-fri |
| Repo | |
| Framework | |
Automated Let’s Play Commentary
| Title | Automated Let’s Play Commentary |
| Authors | Shukan Shah, Matthew Guzdial, Mark O. Riedl |
| Abstract | Let’s Plays of video games represent a relatively unexplored area for experimental AI in games. In this short paper, we discuss an approach to generate automated commentary for Let’s Play videos, drawing on convolutional deep neural networks. We focus on Let’s Plays of the popular game Minecraft. We compare our approach and a prior approach and demonstrate the generation of automated, artificial commentary. |
| Tasks | |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.02195v2 |
| https://arxiv.org/pdf/1909.02195v2.pdf | |
| PWC | https://paperswithcode.com/paper/automated-lets-play-commentary |
| Repo | |
| Framework | |
On the Impact of the Cutoff Time on the Performance of Algorithm Configurators
| Title | On the Impact of the Cutoff Time on the Performance of Algorithm Configurators |
| Authors | George T. Hall, Pietro S. Oliveto, Dirk Sudholt |
| Abstract | Algorithm configurators are automated methods to optimise the parameters of an algorithm for a class of problems. We evaluate the performance of a simple random local search configurator (ParamRLS) for tuning the neighbourhood size $k$ of the RLS$_k$ algorithm. We measure performance as the expected number of configuration evaluations required to identify the optimal value for the parameter. We analyse the impact of the cutoff time $\kappa$ (the time spent evaluating a configuration for a problem instance) on the expected number of configuration evaluations required to find the optimal parameter value, where we compare configurations using either best found fitness values (ParamRLS-F) or optimisation times (ParamRLS-T). We consider tuning RLS$_k$ for a variant of the Ridge function class (Ridge*), where the performance of each parameter value does not change during the run, and for the OneMax function class, where longer runs favour smaller $k$. We rigorously prove that ParamRLS-F efficiently tunes RLS$_k$ for Ridge* for any $\kappa$ while ParamRLS-T requires at least quadratic $\kappa$. For OneMax ParamRLS-F identifies $k=1$ as optimal with linear $\kappa$ while ParamRLS-T requires a $\kappa$ of at least $\Omega(n\log n)$. For smaller $\kappa$ ParamRLS-F identifies that $k>1$ performs better while ParamRLS-T returns $k$ chosen uniformly at random. |
| Tasks | |
| Published | 2019-04-12 |
| URL | https://arxiv.org/abs/1904.06230v2 |
| https://arxiv.org/pdf/1904.06230v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-impact-of-the-cutoff-time-on-the |
| Repo | |
| Framework | |
A Mutual Information Maximization Perspective of Language Representation Learning
| Title | A Mutual Information Maximization Perspective of Language Representation Learning |
| Authors | Lingpeng Kong, Cyprien de Masson d’Autume, Wang Ling, Lei Yu, Zihang Dai, Dani Yogatama |
| Abstract | We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i.e., a sentence). Our formulation provides an alternative perspective that unifies classical word embedding models (e.g., Skip-gram) and modern contextual embeddings (e.g., BERT, XLNet). In addition to enhancing our theoretical understanding of these methods, our derivation leads to a principled framework that can be used to construct new self-supervised tasks. We provide an example by drawing inspirations from related methods based on mutual information maximization that have been successful in computer vision, and introduce a simple self-supervised objective that maximizes the mutual information between a global sentence representation and n-grams in the sentence. Our analysis offers a holistic view of representation learning methods to transfer knowledge and translate progress across multiple domains (e.g., natural language processing, computer vision, audio processing). |
| Tasks | Representation Learning |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08350v2 |
| https://arxiv.org/pdf/1910.08350v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-mutual-information-maximization-perspective-1 |
| Repo | |
| Framework | |
Analyses of Multi-collection Corpora via Compound Topic Modeling
| Title | Analyses of Multi-collection Corpora via Compound Topic Modeling |
| Authors | Clint P. George, Wei Xia, George Michailidis |
| Abstract | As electronically stored data grow in daily life, obtaining novel and relevant information becomes challenging in text mining. Thus people have sought statistical methods based on term frequency, matrix algebra, or topic modeling for text mining. Popular topic models have centered on one single text collection, which is deficient for comparative text analyses. We consider a setting where one can partition the corpus into subcollections. Each subcollection shares a common set of topics, but there exists relative variation in topic proportions among collections. Including any prior knowledge about the corpus (e.g. organization structure), we propose the compound latent Dirichlet allocation (cLDA) model, improving on previous work, encouraging generalizability, and depending less on user-input parameters. To identify the parameters of interest in cLDA, we study Markov chain Monte Carlo (MCMC) and variational inference approaches extensively, and suggest an efficient MCMC method. We evaluate cLDA qualitatively and quantitatively using both synthetic and real-world corpora. The usability study on some real-world corpora illustrates the superiority of cLDA to explore the underlying topics automatically but also model their connections and variations across multiple collections. |
| Tasks | Topic Models |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1907.01636v1 |
| https://arxiv.org/pdf/1907.01636v1.pdf | |
| PWC | https://paperswithcode.com/paper/analyses-of-multi-collection-corpora-via |
| Repo | |
| Framework | |
Reduced-Rank Local Distance Metric Learning for k-NN Classification
| Title | Reduced-Rank Local Distance Metric Learning for k-NN Classification |
| Authors | YInjie Huang, Cong Li, Michael Georgiopoulos, Georgios C. Anagnostopoulos |
| Abstract | We propose a new method for local distance metric learning based on sample similarity as side information. These local metrics, which utilize conical combinations of metric weight matrices, are learned from the pooled spatial characteristics of the data, as well as the similarity profiles between the pairs of samples, whose distances are measured. The main objective of our framework is to yield metrics, such that the resulting distances between similar samples are small and distances between dissimilar samples are above a certain threshold. For learning and inference purposes, we describe a transductive, as well as an inductive algorithm; the former approach naturally befits our framework, while the latter one is provided in the interest of faster learning. Experimental results on a collection of classification problems imply that the new methods may exhibit notable performance advantages over alternative metric learning approaches that have recently appeared in the literature. |
| Tasks | Metric Learning |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.08313v1 |
| http://arxiv.org/pdf/1902.08313v1.pdf | |
| PWC | https://paperswithcode.com/paper/reduced-rank-local-distance-metric-learning |
| Repo | |
| Framework | |
Deep learning surrogate interacting Markov chain Monte Carlo based full wave inversion scheme for properties of materials quantification
| Title | Deep learning surrogate interacting Markov chain Monte Carlo based full wave inversion scheme for properties of materials quantification |
| Authors | Reza Rashetnia, Mohammad Pour-Ghaz |
| Abstract | Full Wave Inversion (FWI) imaging scheme has many applications in engineering, geoscience and medical sciences. In this paper, a surrogate deep learning FWI approach is presented to quantify properties of materials using stress waves. Such inverse problems, in general, are ill-posed and nonconvex, especially in cases where the solutions exhibit shocks, heterogeneity, discontinuities, or large gradients. The proposed approach is proven efficient to obtain global minima responses in these cases. This approach is trained based on random sampled set of material properties and sampled trials around local minima, therefore, it requires a forward simulation can handle high heterogeneity, discontinuities and large gradients. High resolution Kurganov-Tadmor (KT) central finite volume method is used as forward wave propagation operator. Using the proposed framework, material properties of 2D media are quantified for several different situations. The results demonstrate the feasibility of the proposed method for estimating mechanical properties of materials with high accuracy using deep learning approaches. |
| Tasks | |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/2001.02050v1 |
| https://arxiv.org/pdf/2001.02050v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-surrogate-interacting-markov |
| Repo | |
| Framework | |
Guided Stereo Matching
| Title | Guided Stereo Matching |
| Authors | Matteo Poggi, Davide Pallotti, Fabio Tosi, Stefano Mattoccia |
| Abstract | Stereo is a prominent technique to infer dense depth maps from images, and deep learning further pushed forward the state-of-the-art, making end-to-end architectures unrivaled when enough data is available for training. However, deep networks suffer from significant drops in accuracy when dealing with new environments. Therefore, in this paper, we introduce Guided Stereo Matching, a novel paradigm leveraging a small amount of sparse, yet reliable depth measurements retrieved from an external source enabling to ameliorate this weakness. The additional sparse cues required by our method can be obtained with any strategy (e.g., a LiDAR) and used to enhance features linked to corresponding disparity hypotheses. Our formulation is general and fully differentiable, thus enabling to exploit the additional sparse inputs in pre-trained deep stereo networks as well as for training a new instance from scratch. Extensive experiments on three standard datasets and two state-of-the-art deep architectures show that even with a small set of sparse input cues, i) the proposed paradigm enables significant improvements to pre-trained networks. Moreover, ii) training from scratch notably increases accuracy and robustness to domain shifts. Finally, iii) it is suited and effective even with traditional stereo algorithms such as SGM. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10107v1 |
| https://arxiv.org/pdf/1905.10107v1.pdf | |
| PWC | https://paperswithcode.com/paper/guided-stereo-matching-1 |
| Repo | |
| Framework | |
A Comparison of Stereo-Matching Cost between Convolutional Neural Network and Census for Satellite Images
| Title | A Comparison of Stereo-Matching Cost between Convolutional Neural Network and Census for Satellite Images |
| Authors | Bihe Chen, Rongjun Qin, Xu Huang, Shuang Song, Xiaohu Lu |
| Abstract | Stereo dense image matching can be categorized to low-level feature based matching and deep feature based matching according to their matching cost metrics. Census has been proofed to be one of the most efficient low-level feature based matching methods, while fast Convolutional Neural Network (fst-CNN), as a deep feature based method, has small computing time and is robust for satellite images. Thus, a comparison between fst-CNN and census is critical for further studies in stereo dense image matching. This paper used cost function of fst-CNN and census to do stereo matching, then utilized semi-global matching method to obtain optimized disparity images. Those images are used to produce digital surface model to compare with ground truth points. It addresses that fstCNN performs better than census in the aspect of absolute matching accuracy, histogram of error distribution and matching completeness, but these two algorithms still performs in the same order of magnitude. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.09147v1 |
| https://arxiv.org/pdf/1905.09147v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-stereo-matching-cost-between |
| Repo | |
| Framework | |
Graph Representations for Higher-Order Logic and Theorem Proving
| Title | Graph Representations for Higher-Order Logic and Theorem Proving |
| Authors | Aditya Paliwal, Sarah Loos, Markus Rabe, Kshitij Bansal, Christian Szegedy |
| Abstract | This paper presents the first use of graph neural networks (GNNs) for higher-order proof search and demonstrates that GNNs can improve upon state-of-the-art results in this domain. Interactive, higher-order theorem provers allow for the formalization of most mathematical theories and have been shown to pose a significant challenge for deep learning. Higher-order logic is highly expressive and, even though it is well-structured with a clearly defined grammar and semantics, there still remains no well-established method to convert formulas into graph-based representations. In this paper, we consider several graphical representations of higher-order logic and evaluate them against the HOList benchmark for higher-order theorem proving. |
| Tasks | Automated Theorem Proving |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10006v2 |
| https://arxiv.org/pdf/1905.10006v2.pdf | |
| PWC | https://paperswithcode.com/paper/graph-representations-for-higher-order-logic |
| Repo | |
| Framework | |
