Paper Group ANR 1225
Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments. 3D Hand Pose Estimation in the Wild via Graph Refinement under Adversarial Learning. Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP. A literature review on current approaches and applications of fuzzy expert systems. BagNet: Berkel …
Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments
| Title | Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments |
| Authors | Yi Shi, Kemal Davaslioglu, Yalin E. Sagduyu, William C. Headley, Michael Fowler, Gilbert Green |
| Abstract | Dynamic spectrum access (DSA) benefits from detection and classification of interference sources including in-network users, out-network users, and jammers that may all coexist in a wireless network. We present a deep learning based signal (modulation) classification solution in a realistic wireless network setting, where 1) signal types may change over time; 2) some signal types may be unknown for which there is no training data; 3) signals may be spoofed such as the smart jammers replaying other signal types; and 4) different signal types may be superimposed due to the interference from concurrent transmissions. For case 1, we apply continual learning and train a Convolutional Neural Network (CNN) using an Elastic Weight Consolidation (EWC) based loss. For case 2, we detect unknown signals via outlier detection applied to the outputs of convolutional layers using Minimum Covariance Determinant (MCD) and k-means clustering methods. For case 3, we extend the CNN structure to capture phase shifts due to radio hardware effects to identify the spoofing signal sources. For case 4, we apply blind source separation using Independent Component Analysis (ICA) to separate interfering signals. We utilize the signal classification results in a distributed scheduling protocol, where in-network (secondary) users employ signal classification scores to make channel access decisions and share the spectrum with each other while avoiding interference with out-network (primary) users and jammers. Compared with benchmark TDMA-based schemes, we show that distributed scheduling constructed upon signal classification results provides major improvements to in-network user throughput and out-network user success ratio. |
| Tasks | Continual Learning, Outlier Detection |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11800v1 |
| https://arxiv.org/pdf/1909.11800v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-rf-signal-classification-in |
| Repo | |
| Framework | |
3D Hand Pose Estimation in the Wild via Graph Refinement under Adversarial Learning
| Title | 3D Hand Pose Estimation in the Wild via Graph Refinement under Adversarial Learning |
| Authors | Yiming He, Wei Hu, Siyuan Yang, Xiaochao Qu, Pengfei Wan, Zongming Guo |
| Abstract | This paper addresses the problem of 3D hand pose estimation from a monocular RGB image. While previous methods have shown their success, the structure of hands has not been exploited explicitly, which is critical in pose estimation. To this end, we propose a hand-model regularized graph refinement paradigm under an adversarial learning framework, aiming to explicitly capture structural inter-dependencies of hand joints for the learning of intrinsic patterns. We estimate an initial hand pose from a parametric hand model as a prior of hand structure, and refine the structure by learning the deformation of the prior pose via residual graph convolution. To optimize the hand structure further, we propose two bone-constrained loss functions, which characterize the morphable structure of hand poses explicitly. Also, we introduce an adversarial learning framework with a multi-source discriminator to capture structural features, which imposes the constraints onto the distribution of generated 3D hand poses for anthropomorphically valid hand poses. Extensive experiments demonstrate that our model sets the new state-of-the-art in 3D hand pose estimation from a monocular image on standard benchmarks. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01875v3 |
| https://arxiv.org/pdf/1912.01875v3.pdf | |
| PWC | https://paperswithcode.com/paper/graphposegan-3d-hand-pose-estimation-from-a |
| Repo | |
| Framework | |
Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP
| Title | Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP |
| Authors | Kefan Dong, Yuanhao Wang, Xiaoyu Chen, Liwei Wang |
| Abstract | A fundamental question in reinforcement learning is whether model-free algorithms are sample efficient. Recently, Jin et al. \cite{jin2018q} proposed a Q-learning algorithm with UCB exploration policy, and proved it has nearly optimal regret bound for finite-horizon episodic MDP. In this paper, we adapt Q-learning with UCB-exploration bonus to infinite-horizon MDP with discounted rewards \emph{without} accessing a generative model. We show that the \textit{sample complexity of exploration} of our algorithm is bounded by $\tilde{O}({\frac{SA}{\epsilon^2(1-\gamma)^7}})$. This improves the previously best known result of $\tilde{O}({\frac{SA}{\epsilon^4(1-\gamma)^8}})$ in this setting achieved by delayed Q-learning \cite{strehl2006pac}, and matches the lower bound in terms of $\epsilon$ as well as $S$ and $A$ except for logarithmic factors. |
| Tasks | Q-Learning |
| Published | 2019-01-27 |
| URL | https://arxiv.org/abs/1901.09311v2 |
| https://arxiv.org/pdf/1901.09311v2.pdf | |
| PWC | https://paperswithcode.com/paper/q-learning-with-ucb-exploration-is-sample |
| Repo | |
| Framework | |
A literature review on current approaches and applications of fuzzy expert systems
| Title | A literature review on current approaches and applications of fuzzy expert systems |
| Authors | Mina Rajabi, Saeed Hossani, Fatemeh Dehghani |
| Abstract | The main purposes of this study are to distinguish the trends of research in publication exits for the utilisations of the fuzzy expert and knowledge-based systems that is done based on the classification of studies in the last decade. The present investigation covers 60 articles from related scholastic journals, International conference proceedings and some major literature review papers. Our outcomes reveal an upward trend in the up-to-date publications number, that is evidence of growing notoriety on the various applications of fuzzy expert systems. This raise in the reports is mainly in the medical neuro-fuzzy and fuzzy expert systems. Moreover, another most critical observation is that many modern industrial applications are extended, employing knowledge-based systems by extracting the experts’ knowledge. |
| Tasks | |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08794v1 |
| https://arxiv.org/pdf/1909.08794v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-literature-review-on-current-approaches-and |
| Repo | |
| Framework | |
BagNet: Berkeley Analog Generator with Layout Optimizer Boosted with Deep Neural Networks
| Title | BagNet: Berkeley Analog Generator with Layout Optimizer Boosted with Deep Neural Networks |
| Authors | Kourosh Hakhamaneshi, Nick Werblun, Pieter Abbeel, Vladimir Stojanovic |
| Abstract | The discrepancy between post-layout and schematic simulation results continues to widen in analog design due in part to the domination of layout parasitics. This paradigm shift is forcing designers to adopt design methodologies that seamlessly integrate layout effects into the standard design flow. Hence, any simulation-based optimization framework should take into account time-consuming post-layout simulation results. This work presents a learning framework that learns to reduce the number of simulations of evolutionary-based combinatorial optimizers, using a DNN that discriminates against generated samples, before running simulations. Using this approach, the discriminator achieves at least two orders of magnitude improvement on sample efficiency for several large circuit examples including an optical link receiver layout. |
| Tasks | |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.10515v1 |
| https://arxiv.org/pdf/1907.10515v1.pdf | |
| PWC | https://paperswithcode.com/paper/bagnet-berkeley-analog-generator-with-layout |
| Repo | |
| Framework | |
Data-driven prediction of vortex-induced vibration response of marine risers subjected to three-dimensional current
| Title | Data-driven prediction of vortex-induced vibration response of marine risers subjected to three-dimensional current |
| Authors | Signe Riemer-Sørensen, Jie Wu, Halvor Lie, Svein Sævik, Sang-Woo Kim |
| Abstract | Slender marine structures such as deep-water marine risers are subjected to currents and will normally experience Vortex Induced Vibrations (VIV), which can cause fast accumulation of fatigue damage. The ocean current is often three-dimensional (3D), i.e., the direction and magnitude of the current vary throughout the water column. Today, semi-empirical tools are used by the industry to predict VIV induced fatigue on risers. The load model and hydrodynamic parameters in present VIV prediction tools are developed based on two-dimensional (2D) flow conditions, as it is challenging to consider the effect of 3D flow along the risers. Accordingly, the current profiles must be purposely made 2D during the design process, which leads to significant uncertainty in the prediction results. Further, due to the limitations in the laboratory, VIV model tests are mostly carried out under 2D flow conditions and thus little experimental data exist to document VIV response of riser subjected to varying directions of the current. However, a few experiments have been conducted with 3D current. We have used results from one of these experiments to investigate how well 1) traditional and 2) an alternative method based on a data driven prediction can describe VIV in 3D currents. Data driven modelling is particularly suited for complicated problems with many parameters and non-linear relationships. We have applied a data clustering algorithm to the experimental 3D flow data in order to identify measurable parameters that can influence responses. The riser responses are grouped based on their statistical characteristics, which relate to the direction of the flow. Furthermore we fit a random forest regression model to the measured VIV response and compare its performance with the predictions of existing VIV prediction tools (VIVANA-FD). |
| Tasks | |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.11177v1 |
| https://arxiv.org/pdf/1906.11177v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-driven-prediction-of-vortex-induced |
| Repo | |
| Framework | |
Semantic Redundancies in Image-Classification Datasets: The 10% You Don’t Need
| Title | Semantic Redundancies in Image-Classification Datasets: The 10% You Don’t Need |
| Authors | Vighnesh Birodkar, Hossein Mobahi, Samy Bengio |
| Abstract | Large datasets have been crucial to the success of deep learning models in the recent years, which keep performing better as they are trained with more labelled data. While there have been sustained efforts to make these models more data-efficient, the potential benefit of understanding the data itself, is largely untapped. Specifically, focusing on object recognition tasks, we wonder if for common benchmark datasets we can do better than random subsets of the data and find a subset that can generalize on par with the full dataset when trained on. To our knowledge, this is the first result that can find notable redundancies in CIFAR-10 and ImageNet datasets (at least 10%). Interestingly, we observe semantic correlations between required and redundant images. We hope that our findings can motivate further research into identifying additional redundancies and exploiting them for more efficient training or data-collection. |
| Tasks | Image Classification, Object Recognition |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.11409v1 |
| http://arxiv.org/pdf/1901.11409v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-redundancies-in-image-classification |
| Repo | |
| Framework | |
Signal Conditioning for Learning in the Wild
| Title | Signal Conditioning for Learning in the Wild |
| Authors | Ayon Borthakur, Thomas A. Cleland |
| Abstract | The mammalian olfactory system learns rapidly from very few examples, presented in unpredictable online sequences, and then recognizes these learned odors under conditions of substantial interference without exhibiting catastrophic forgetting. We have developed a brain-mimetic algorithm that replicates these properties, provided that sensory inputs adhere to a common statistical structure. However, in natural, unregulated environments, this constraint cannot be assured. We here present a series of signal conditioning steps, inspired by the mammalian olfactory system, that transform diverse sensory inputs into a regularized statistical structure to which the learning network can be tuned. This pre-processing enables a single instantiated network to be applied to widely diverse classification tasks and datasets - here including gas sensor data, remote sensing from spectral characteristics, and multi-label hierarchical identification of wild species - without adjusting network hyperparameters. |
| Tasks | |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05827v1 |
| https://arxiv.org/pdf/1907.05827v1.pdf | |
| PWC | https://paperswithcode.com/paper/signal-conditioning-for-learning-in-the-wild |
| Repo | |
| Framework | |
A Generalization Theory based on Independent and Task-Identically Distributed Assumption
| Title | A Generalization Theory based on Independent and Task-Identically Distributed Assumption |
| Authors | Guanhua Zheng, Jitao Sang, Houqiang Li, Jian Yu, Changsheng Xu |
| Abstract | Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories fail to interpret many generalization phenomena or guide practical learning tasks. In this paper, we propose a new Independent and Task-Identically Distributed (ITID) assumption, to consider the task properties into the data generating process. The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance. Based on the new bound, we introduce a practical invariance enhancement algorithm from the perspective of modifying data distributions. Finally, we verify the algorithm and theorems in the context of image classification task on both toy and real-world datasets. The experimental results demonstrate the reasonableness of the ITID assumption and the effectiveness of new generalization theory in improving practical generalization performance. |
| Tasks | Image Classification |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12603v1 |
| https://arxiv.org/pdf/1911.12603v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-generalization-theory-based-on-independent |
| Repo | |
| Framework | |
DeepHMap++: Combined Projection Grouping and Correspondence Learning for Full DoF Pose Estimation
| Title | DeepHMap++: Combined Projection Grouping and Correspondence Learning for Full DoF Pose Estimation |
| Authors | Mingliang Fu, Weijia Zhou |
| Abstract | In recent years, estimating the 6D pose of object instances with convolutional neural network (CNN) has received considerable attention. Depending on whether intermediate cues are used, the relevant literature can be roughly divided into two broad categories: direct methods and two stage pipelines. For the latter, intermediate cues, such as 3D object coordinates, semantic keypoints, or virtual control points instead of pose parameters are regressed by CNN in the first stage. Object pose can then be solved by correspondence constraints constructed with these intermediate cues. In this paper, we focus on the postprocessing of a two-stage pipeline and propose to combine two learning concepts for estimating object pose under challenging scenes: projection grouping on one side, and correspondence learning on the other. We firstly employ a local patch based method to predict projection heatmaps which denote the confidence distribution of projection of 3D bounding box’s corners. A projection grouping module is then proposed to remove redundant local maxima from each layer of heatmaps. Instead of directly feeding 2D-3D correspondences to the perspective-n-point (PnP) algorithm, multiple correspondence hypotheses are sampled from local maxima and its corresponding neighborhood and ranked by a correspondence-evaluation network. Finally, correspondences with higher confidence are selected to determine object pose. Extensive experiments on three public datasets demonstrate that the proposed framework outperforms several state of the art methods. |
| Tasks | Pose Estimation |
| Published | 2019-04-29 |
| URL | http://arxiv.org/abs/1904.12735v1 |
| http://arxiv.org/pdf/1904.12735v1.pdf | |
| PWC | https://paperswithcode.com/paper/deephmap-combined-projection-grouping-and |
| Repo | |
| Framework | |
Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network
| Title | Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network |
| Authors | Marc Eder, Pierre Moulon, Li Guan |
| Abstract | In this work we present a method to train a plane-aware convolutional neural network for dense depth and surface normal estimation as well as plane boundaries from a single indoor $360^\circ$ image. Using our proposed loss function, our network outperforms existing methods for single-view, indoor, omnidirectional depth estimation and provides an initial benchmark for surface normal prediction from $360^\circ$ images. Our improvements are due to the use of a novel plane-aware loss that leverages principal curvature as an indicator of planar boundaries. We also show that including geodesic coordinate maps as network priors provides a significant boost in surface normal prediction accuracy. Finally, we demonstrate how we can combine our network’s outputs to generate high quality 3D “pop-up” models of indoor scenes. |
| Tasks | 3D Reconstruction, Depth Estimation |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.00939v2 |
| https://arxiv.org/pdf/1907.00939v2.pdf | |
| PWC | https://paperswithcode.com/paper/pano-popups-indoor-3d-reconstruction-with-a |
| Repo | |
| Framework | |
A Variational Perturbative Approach to Planning in Graph-based Markov Decision Processes
| Title | A Variational Perturbative Approach to Planning in Graph-based Markov Decision Processes |
| Authors | Dominik Linzner, Heinz Koeppl |
| Abstract | Coordinating multiple interacting agents to achieve a common goal is a difficult task with huge applicability. This problem remains hard to solve, even when limiting interactions to be mediated via a static interaction-graph. We present a novel approximate solution method for multi-agent Markov decision problems on graphs, based on variational perturbation theory. We adopt the strategy of planning via inference, which has been explored in various prior works. We employ a non-trivial extension of a novel high-order variational method that allows for approximate inference in large networks and has been shown to surpass the accuracy of existing variational methods. To compare our method to two state-of-the-art methods for multi-agent planning on graphs, we apply the method different standard GMDP problems. We show that in cases, where the goal is encoded as a non-local cost function, our method performs well, while state-of-the-art methods approach the performance of random guess. In a final experiment, we demonstrate that our method brings significant improvement for synchronization tasks. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01849v1 |
| https://arxiv.org/pdf/1912.01849v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-variational-perturbative-approach-to |
| Repo | |
| Framework | |
Does Time-Delay Feedback Matter to Small Target Motion Detection Against Complex Dynamic Environments?
| Title | Does Time-Delay Feedback Matter to Small Target Motion Detection Against Complex Dynamic Environments? |
| Authors | Hongxin Wang, Huatian Wang, Jiannan Zhao, Cheng Hu, Jigen Peng, Shigang Yue |
| Abstract | Discriminating small moving objects in complex visual environments is a significant challenge for autonomous micro robots that are generally limited in computational power. Relying on well-evolved visual systems, flying insects can effortlessly detect mates and track prey in rapid pursuits, despite target sizes as small as a few pixels in the visual field. Such exquisite sensitivity for small target motion is known to be supported by a class of specialized neurons named as small target motion detectors (STMDs). The existing STMD-based models normally consist of four sequentially arranged neural layers interconnected through feedforward loops to extract motion information about small targets from raw visual inputs. However, feedback loop, another important regulatory circuit for motion perception, has not been investigated in the STMD pathway and its functional roles for small target motion detection are not clear. In this paper, we assume the existence of the feedback and propose a STMD-based visual system with feedback connection (Feedback STMD), where the system output is temporally delayed, then fed back to lower layers to mediate neural responses. We compare the properties of the visual system with and without the time-delay feedback loop, and discuss its effect on small target motion detection. The experimental results suggest that the Feedback STMD prefers fast-moving small targets, while significantly suppresses those background features moving at lower velocities. |
| Tasks | Motion Detection |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/2001.05846v1 |
| https://arxiv.org/pdf/2001.05846v1.pdf | |
| PWC | https://paperswithcode.com/paper/does-time-delay-feedback-matter-to-small |
| Repo | |
| Framework | |
Detecting Cyberbullying and Cyberaggression in Social Media
| Title | Detecting Cyberbullying and Cyberaggression in Social Media |
| Authors | Despoina Chatzakou, Ilias Leontiadis, Jeremy Blackburn, Emiliano De Cristofaro, Gianluca Stringhini, Athena Vakali, Nicolas Kourtellis |
| Abstract | Cyberbullying and cyberaggression are increasingly worrisome phenomena affecting people across all demographics. More than half of young social media users worldwide have been exposed to such prolonged and/or coordinated digital harassment. Victims can experience a wide range of emotions, with negative consequences such as embarrassment, depression, isolation from other community members, which embed the risk to lead to even more critical consequences, such as suicide attempts. In this work, we take the first concrete steps to understand the characteristics of abusive behavior in Twitter, one of today’s largest social media platforms. We analyze 1.2 million users and 2.1 million tweets, comparing users participating in discussions around seemingly normal topics like the NBA, to those more likely to be hate-related, such as the Gamergate controversy, or the gender pay inequality at the BBC station. We also explore specific manifestations of abusive behavior, i.e., cyberbullying and cyberaggression, in one of the hate-related communities (Gamergate). We present a robust methodology to distinguish bullies and aggressors from normal Twitter users by considering text, user, and network-based attributes. Using various state-of-the-art machine learning algorithms, we classify these accounts with over 90% accuracy and AUC. Finally, we discuss the current status of Twitter user accounts marked as abusive by our methodology, and study the performance of potential mechanisms that can be used by Twitter to suspend users in the future. |
| Tasks | |
| Published | 2019-07-20 |
| URL | https://arxiv.org/abs/1907.08873v1 |
| https://arxiv.org/pdf/1907.08873v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-cyberbullying-and-cyberaggression |
| Repo | |
| Framework | |
Learning to Validate the Quality of Detected Landmarks
| Title | Learning to Validate the Quality of Detected Landmarks |
| Authors | Wolfgang Fuhl, Enkelejda Kasneci |
| Abstract | We present a new loss function for the validation of image landmarks detected via Convolutional Neural Networks (CNN). The network learns to estimate how accurate its landmark estimation is. This loss function is applicable to all regression-based location estimations and allows the exclusion of unreliable landmarks from further processing. In addition, we formulate a novel batch balancing approach which weights the importance of samples based on their produced loss. This is done by computing a probability distribution mapping on an interval from which samples can be selected using a uniform random selection scheme. We conducted experiments on the 300W, AFLW, and WFLW facial landmark datasets. In the first experiments, the influence of our batch balancing approach is evaluated by comparing it against uniform sampling. In addition, we evaluated the impact of the validation loss on the landmark accuracy based on uniform sampling. The last experiments evaluate the correlation of the validation signal with the landmark accuracy. All experiments were performed for all three datasets. |
| Tasks | Head Pose Estimation, Pose Estimation |
| Published | 2019-01-29 |
| URL | https://arxiv.org/abs/1901.10143v3 |
| https://arxiv.org/pdf/1901.10143v3.pdf | |
| PWC | https://paperswithcode.com/paper/validation-loss-for-landmark-detection |
| Repo | |
| Framework | |
