Paper Group ANR 891
Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching. Machine Learning on data with sPlot background subtraction. Event-based Object Detection and Tracking for Space Situational Awareness. Semantic Graph Convolutional Network for Implicit Discourse Relation Classification. Bayesian interpretation of SGD as Ito process. Mult …
Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching
| Title | Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching |
| Authors | Jiaqi Yang, Siwen Quan, Peng Wang, Yanning Zhang |
| Abstract | Local geometric descriptors remain an essential component for 3D rigid data matching and fusion. The devise of a rotational invariant local geometric descriptor usually consists of two steps: local reference frame (LRF) construction and feature representation. Existing evaluation efforts have mainly been paid on the LRF or the overall descriptor, yet the quantitative comparison of feature representations remains unexplored. This paper fills this gap by comprehensively evaluating nine state-of-the-art local geometric feature representations. Our evaluation is on the ground that ground-truth LRFs are leveraged such that the ranking of tested feature representations are more convincing as opposed to existing studies. The experiments are deployed on six standard datasets with various application scenarios (shape retrieval, point cloud registration, and object recognition) and data modalities (LiDAR, Kinect, and Space Time) as well as perturbations including Gaussian noise, shot noise, data decimation, clutter, occlusion, and limited overlap. The evaluated terms cover the major concerns for a feature representation, e.g., distinctiveness, robustness, compactness, and efficiency. The outcomes present interesting findings that may shed new light on this community and provide complementary perspectives to existing evaluations on the topic of local geometric feature description. A summary of evaluated methods regarding their peculiarities is also presented to guide real-world applications and new descriptor crafting. |
| Tasks | Object Recognition, Point Cloud Registration |
| Published | 2019-06-29 |
| URL | https://arxiv.org/abs/1907.00233v1 |
| https://arxiv.org/pdf/1907.00233v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-local-geometric-feature |
| Repo | |
| Framework | |
Machine Learning on data with sPlot background subtraction
| Title | Machine Learning on data with sPlot background subtraction |
| Authors | Maxim Borisyak, Nikita Kazeev |
| Abstract | Data analysis in high energy physics often deals with data samples consisting of a mixture of signal and background events. The sPlot technique is a common method to subtract the contribution of the background by assigning weights to events. Part of the weights are by design negative. Negative weights lead to the divergence of some machine learning algorithms training due to absence of the lower bound in the loss function. In this paper we propose a mathematically rigorous way to train machine learning algorithms on data samples with background described by sPlot to obtain signal probabilities conditioned on observables, without encountering negative event weight at all. This allows usage of any out-of-the-box machine learning methods on such data. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11719v5 |
| https://arxiv.org/pdf/1905.11719v5.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-on-data-with-splot |
| Repo | |
| Framework | |
Event-based Object Detection and Tracking for Space Situational Awareness
| Title | Event-based Object Detection and Tracking for Space Situational Awareness |
| Authors | Saeed Afshar, Andrew P Nicholson, Andre van Schaik, Gregory Cohen |
| Abstract | In this work, we present optical space imaging using an unconventional yet promising class of imaging devices known as neuromorphic event-based sensors. These devices, which are modeled on the human retina, do not operate with frames, but rather generate asynchronous streams of events in response to changes in log-illumination at each pixel. These devices are therefore extremely fast, do not have fixed exposure times, allow for imaging whilst the device is moving and enable low power space imaging during daytime as well as night without modification of the sensors. Recorded at multiple remote sites, we present the first event-based space imaging dataset including recordings from multiple event-based sensors from multiple providers, greatly lowering the barrier to entry for other researchers given the scarcity of such sensors and the expertise required to operate them. The dataset contains 236 separate recordings and 572 labeled resident space objects. The event-based imaging paradigm presents unique opportunities and challenges motivating the development of specialized event-based algorithms that can perform tasks such as detection and tracking in an event-based manner. Here we examine a range of such event-based algorithms for detection and tracking. The presented methods are designed specifically for space situational awareness applications and are evaluated in terms of accuracy and speed and suitability for implementation in neuromorphic hardware on remote or space-based imaging platforms. |
| Tasks | Object Detection |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.08730v1 |
| https://arxiv.org/pdf/1911.08730v1.pdf | |
| PWC | https://paperswithcode.com/paper/event-based-object-detection-and-tracking-for |
| Repo | |
| Framework | |
Semantic Graph Convolutional Network for Implicit Discourse Relation Classification
| Title | Semantic Graph Convolutional Network for Implicit Discourse Relation Classification |
| Authors | Yingxue Zhang, Ping Jian, Fandong Meng, Ruiying Geng, Wei Cheng, Jie Zhou |
| Abstract | Implicit discourse relation classification is of great importance for discourse parsing, but remains a challenging problem due to the absence of explicit discourse connectives communicating these relations. Modeling the semantic interactions between the two arguments of a relation has proven useful for detecting implicit discourse relations. However, most previous approaches model such semantic interactions from a shallow interactive level, which is inadequate on capturing enough semantic information. In this paper, we propose a novel and effective Semantic Graph Convolutional Network (SGCN) to enhance the modeling of inter-argument semantics on a deeper interaction level for implicit discourse relation classification. We first build an interaction graph over representations of the two arguments, and then automatically extract in-depth semantic interactive information through graph convolution. Experimental results on the English corpus PDTB and the Chinese corpus CDTB both demonstrate the superiority of our model to previous state-of-the-art systems. |
| Tasks | Implicit Discourse Relation Classification, Relation Classification |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09183v1 |
| https://arxiv.org/pdf/1910.09183v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-graph-convolutional-network-for |
| Repo | |
| Framework | |
Bayesian interpretation of SGD as Ito process
| Title | Bayesian interpretation of SGD as Ito process |
| Authors | Soma Yokoi, Issei Sato |
| Abstract | The current interpretation of stochastic gradient descent (SGD) as a stochastic process lacks generality in that its numerical scheme restricts continuous-time dynamics as well as the loss function and the distribution of gradient noise. We introduce a simplified scheme with milder conditions that flexibly interprets SGD as a discrete-time approximation of an Ito process. The scheme also works as a common foundation of SGD and stochastic gradient Langevin dynamics (SGLD), providing insights into their asymptotic properties. We investigate the convergence of SGD with biased gradient in terms of the equilibrium mode and the overestimation problem of the second moment of SGLD. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.09011v1 |
| https://arxiv.org/pdf/1911.09011v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-interpretation-of-sgd-as-ito-process |
| Repo | |
| Framework | |
Multi-Armed Bandits with Correlated Arms
| Title | Multi-Armed Bandits with Correlated Arms |
| Authors | Samarth Gupta, Shreyas Chaudhari, Gauri Joshi, Osman Yağan |
| Abstract | We consider a multi-armed bandit framework where the rewards obtained by pulling different arms are correlated. The correlation information is captured in terms of \textit{pseudo-rewards}, which are bounds on the rewards on the other arm given a reward realization and can capture many general correlation structures. We leverage these pseudo-rewards to design a novel approach that extends any classical bandit algorithm to the correlated multi-armed bandit setting studied in the framework. In each round, our proposed C-Bandit algorithm identifies some arms as empirically non-competitive, and avoids exploring them for that round. Through a unified regret analysis of the proposed C-Bandit algorithm, we show that C-UCB and C-TS (the correlated bandit versions of Upper-confidence-bound and Thompson sampling) pull certain arms called non-competitive arms, only O(1) times. As a result, we effectively reduce a $K$-armed bandit problem to a $C+1$-armed bandit problem, where $C$ is the number of competitive arms, as only $C$ sub-optimal arms are pulled O(log T) times. In many practical scenarios, $C$ can be zero due to which our proposed C-Bandit algorithms achieve bounded regret. In the special case where rewards are correlated through a latent random variable $X$, we give a regret lower bound that shows that bounded regret is possible only when $C = 0$. In addition to simulations, we validate the proposed algorithms via experiments on two real-world recommendation datasets, movielens and goodreads, and show that C-UCB and C-TS significantly outperform classical bandit algorithms. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.03959v2 |
| https://arxiv.org/pdf/1911.03959v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-armed-bandits-with-correlated-arms |
| Repo | |
| Framework | |
Optical Flow augmented Semantic Segmentation networks for Automated Driving
| Title | Optical Flow augmented Semantic Segmentation networks for Automated Driving |
| Authors | Hazem Rashed, Senthil Yogamani, Ahmad El-Sallab, Pavel Krizek, Mohamed El-Helw |
| Abstract | Motion is a dominant cue in automated driving systems. Optical flow is typically computed to detect moving objects and to estimate depth using triangulation. In this paper, our motivation is to leverage the existing dense optical flow to improve the performance of semantic segmentation. To provide a systematic study, we construct four different architectures which use RGB only, flow only, RGBF concatenated and two-stream RGB + flow. We evaluate these networks on two automotive datasets namely Virtual KITTI and Cityscapes using the state-of-the-art flow estimator FlowNet v2. We also make use of the ground truth optical flow in Virtual KITTI to serve as an ideal estimator and a standard Farneback optical flow algorithm to study the effect of noise. Using the flow ground truth in Virtual KITTI, two-stream architecture achieves the best results with an improvement of 4% IoU. As expected, there is a large improvement for moving objects like trucks, vans and cars with 38%, 28% and 6% increase in IoU. FlowNet produces an improvement of 2.4% in average IoU with larger improvement in the moving objects corresponding to 26%, 11% and 5% in trucks, vans and cars. In Cityscapes, flow augmentation provided an improvement for moving objects like motorcycle and train with an increase of 17% and 7% in IoU. |
| Tasks | Optical Flow Estimation, Semantic Segmentation |
| Published | 2019-01-11 |
| URL | http://arxiv.org/abs/1901.07355v1 |
| http://arxiv.org/pdf/1901.07355v1.pdf | |
| PWC | https://paperswithcode.com/paper/optical-flow-augmented-semantic-segmentation |
| Repo | |
| Framework | |
The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent
| Title | The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent |
| Authors | Karthik A. Sankararaman, Soham De, Zheng Xu, W. Ronny Huang, Tom Goldstein |
| Abstract | In this paper we study how neural network architecture affects the speed of training. We introduce a simple concept called gradient confusion to help formally analyze this. When confusion is high, stochastic gradients produced by different data samples may be negatively correlated, slowing down convergence. But when gradient confusion is low, data samples interact harmoniously, and training proceeds quickly. Through novel theoretical and experimental results, we show how the neural net architecture affects gradient confusion, and thus the efficiency of training. We show that for popular initialization techniques used in deep learning, increasing the width of neural networks leads to lower gradient confusion, and thus easier model training. On the other hand, increasing the depth of neural networks has the opposite effect. Further, when using orthogonal initialization, we show that the training dynamics early on become independent of the depth for linear neural networks, suggesting a way forward for training deep models. Finally, we observe that the combination of batch normalization and skip connections reduces gradient confusion, which helps reduce the training burden of very deep networks with Gaussian initializations. |
| Tasks | |
| Published | 2019-04-15 |
| URL | https://arxiv.org/abs/1904.06963v4 |
| https://arxiv.org/pdf/1904.06963v4.pdf | |
| PWC | https://paperswithcode.com/paper/the-impact-of-neural-network |
| Repo | |
| Framework | |
Distributed Classification of Urban Congestion Using VANET
| Title | Distributed Classification of Urban Congestion Using VANET |
| Authors | Al Mallah Ranwa, Farooq Bilal, Quintero Alejandro |
| Abstract | Vehicular Ad-hoc NETworks (VANET) can efficiently detect traffic congestion, but detection is not enough because congestion can be further classified as recurrent and non-recurrent congestion (NRC). In particular, NRC in an urban network is mainly caused by incidents, workzones, special events and adverse weather. We propose a framework for the real-time distributed classification of congestion into its components on a heterogeneous urban road network using VANET. We present models built on an understanding of the spatial and temporal causality measures and trained on synthetic data extended from a real case study of Cologne. Our performance evaluation shows a predictive accuracy of 87.63% for the deterministic Classification Tree (CT), 88.83% for the Naive Bayesian classifier (NB), 89.51% for Random Forest (RF) and 89.17% for the boosting technique. This framework can assist transportation agencies in reducing urban congestion by developing effective congestion mitigation strategies knowing the root causes of congestion. |
| Tasks | |
| Published | 2019-04-26 |
| URL | http://arxiv.org/abs/1904.12685v1 |
| http://arxiv.org/pdf/1904.12685v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-classification-of-urban |
| Repo | |
| Framework | |
Learning Efficient Convolutional Networks through Irregular Convolutional Kernels
| Title | Learning Efficient Convolutional Networks through Irregular Convolutional Kernels |
| Authors | Weiyu Guo, Jiabin Ma, Liang Wang, Yongzhen Huang |
| Abstract | As deep neural networks are increasingly used in applications suited for low-power devices, a fundamental dilemma becomes apparent: the trend is to grow models to absorb increasing data that gives rise to memory intensive; however low-power devices are designed with very limited memory that can not store large models. Parameters pruning is critical for deep model deployment on low-power devices. Existing efforts mainly focus on designing highly efficient structures or pruning redundant connections for networks. They are usually sensitive to the tasks or relay on dedicated and expensive hashing storage strategies. In this work, we introduce a novel approach for achieving a lightweight model from the views of reconstructing the structure of convolutional kernels and efficient storage. Our approach transforms a traditional square convolution kernel to line segments, and automatically learn a proper strategy for equipping these line segments to model diverse features. The experimental results indicate that our approach can massively reduce the number of parameters (pruned 69% on DenseNet-40) and calculations (pruned 59% on DenseNet-40) while maintaining acceptable performance (only lose less than 2% accuracy). |
| Tasks | |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1909.13239v1 |
| https://arxiv.org/pdf/1909.13239v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-efficient-convolutional-networks-2 |
| Repo | |
| Framework | |
Condition-Transforming Variational AutoEncoder for Conversation Response Generation
| Title | Condition-Transforming Variational AutoEncoder for Conversation Response Generation |
| Authors | Yu-Ping Ruan, Zhen-Hua Ling, Quan Liu, Zhigang Chen, Nitin Indurkhya |
| Abstract | This paper proposes a new model, called condition-transforming variational autoencoder (CTVAE), to improve the performance of conversation response generation using conditional variational autoencoders (CVAEs). In conventional CVAEs , the prior distribution of latent variable z follows a multivariate Gaussian distribution with mean and variance modulated by the input conditions. Previous work found that this distribution tends to become condition independent in practical application. In our proposed CTVAE model, the latent variable z is sampled by performing a non-lineartransformation on the combination of the input conditions and the samples from a condition-independent prior distribution N (0; I). In our objective evaluations, the CTVAE model outperforms the CVAE model on fluency metrics and surpasses a sequence-to-sequence (Seq2Seq) model on diversity metrics. In subjective preference tests, our proposed CTVAE model performs significantly better than CVAE and Seq2Seq models on generating fluency, informative and topic relevant responses. |
| Tasks | |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1904.10610v1 |
| http://arxiv.org/pdf/1904.10610v1.pdf | |
| PWC | https://paperswithcode.com/paper/condition-transforming-variational |
| Repo | |
| Framework | |
Successive Projection Algorithm Robust to Outliers
| Title | Successive Projection Algorithm Robust to Outliers |
| Authors | Nicolas Gillis |
| Abstract | The successive projection algorithm (SPA) is a fast algorithm to tackle separable nonnegative matrix factorization (NMF). Given a nonnegative data matrix $X$, SPA identifies an index set $\mathcal{K}$ such that there exists a nonnegative matrix $H$ with $X \approx X(:,\mathcal{K})H$. SPA has been successfully used as a pure-pixel search algorithm in hyperspectral unmixing and for anchor word selection in document classification. Moreover, SPA is provably robust in low-noise settings. The main drawbacks of SPA are that it is not robust to outliers and does not take the data fitting term into account when selecting the indices in $\mathcal{K}$. In this paper, we propose a new SPA variant, dubbed Robust SPA (RSPA), that is robust to outliers while still being provably robust in low-noise settings, and that takes into account the reconstruction error for selecting the indices in $\mathcal{K}$. We illustrate the effectiveness of RSPA on synthetic data sets and hyperspectral images. |
| Tasks | Document Classification, Hyperspectral Unmixing |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04109v1 |
| https://arxiv.org/pdf/1908.04109v1.pdf | |
| PWC | https://paperswithcode.com/paper/successive-projection-algorithm-robust-to |
| Repo | |
| Framework | |
Coupling Matrix Manifolds and Their Applications in Optimal Transport
| Title | Coupling Matrix Manifolds and Their Applications in Optimal Transport |
| Authors | Dai Shi, Junbin Gao, Xia Hong, S. T. Boris Choy, Zhiyong Wang |
| Abstract | Optimal transport (OT) is a powerful tool for measuring the distance between two defined probability distributions. In this paper, we develop a new manifold named the coupling matrix manifold (CMM), where each point on CMM can be regarded as the transportation plan of the OT problem. We firstly explore the Riemannian geometry of CMM with the metric expressed by the Fisher information. These geometrical features of CMM have paved the way for developing numerical Riemannian optimization algorithms such as Riemannian gradient descent and Riemannian trust-region algorithms, forming a uniform optimization method for all types of OT problems. The proposed method is then applied to solve several OT problems studied by previous literature. The results of the numerical experiments illustrate that the optimization algorithms that are based on the method proposed in this paper are comparable to the classic ones, for example, the Sinkhorn algorithm, while outperforming other state-of-the-art algorithms without considering the geometry information, especially in the case of non-entropy optimal transport. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06905v2 |
| https://arxiv.org/pdf/1911.06905v2.pdf | |
| PWC | https://paperswithcode.com/paper/coupling-matrix-manifolds-and-their |
| Repo | |
| Framework | |
Matrix cofactorization for joint spatial-spectral unmixing of hyperspectral images
| Title | Matrix cofactorization for joint spatial-spectral unmixing of hyperspectral images |
| Authors | Adrien Lagrange, Mathieu Fauvel, Stéphane May, Nicolas Dobigeon |
| Abstract | Hyperspectral unmixing aims at identifying a set of elementary spectra and the corresponding mixture coefficients for each pixel of an image. As the elementary spectra correspond to the reflectance spectra of real materials, they are often very correlated yielding an ill-conditioned problem. To enrich the model and to reduce ambiguity due to the high correlation, it is common to introduce spatial information to complement the spectral information. The most common way to introduce spatial information is to rely on a spatial regularization of the abundance maps. In this paper, instead of considering a simple but limited regularization process, spatial information is directly incorporated through the newly proposed context of spatial unmixing. Contextual features are extracted for each pixel and this additional set of observations is decomposed according to a linear model. Finally the spatial and spectral observations are unmixed jointly through a cofactorization model. In particular, this model introduces a coupling term used to identify clusters of shared spatial and spectral signatures. An evaluation of the proposed method is conducted on synthetic and real data and shows that results are accurate and also very meaningful since they describe both spatially and spectrally the various areas of the scene. |
| Tasks | Hyperspectral Unmixing |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08511v2 |
| https://arxiv.org/pdf/1907.08511v2.pdf | |
| PWC | https://paperswithcode.com/paper/matrix-cofactorization-for-joint-spatial |
| Repo | |
| Framework | |
Smoothness-Adaptive Contextual Bandits
| Title | Smoothness-Adaptive Contextual Bandits |
| Authors | Yonatan Gur, Ahmadreza Momeni, Stefan Wager |
| Abstract | We study a non-parametric multi-armed bandit problem with stochastic covariates, where a key driver of complexity is the smoothness with which the payoff functions vary with covariates. Previous studies have derived minimax-optimal algorithms in cases where it is a priori known how smooth the payoff functions are. In practice, however, advance information about the smoothness of payoff functions is typically not available, and misspecification of smoothness may severely deteriorate the performance of existing methods. In this work, we consider a framework where the smoothness is not known a priori, and study when and how algorithms may adapt to unknown smoothness. First, we establish that, in general, designing bandit algorithms that adapt to the unknown smoothness of payoff functions is impossible. We overcome this impossibility result by leveraging the notion of self-similarity, a concept from the statistics literature that is traditionally invoked to enable adaptive confidence intervals. Under a self-similarity assumption, we develop a policy for inferring the smoothness of the payoff functions using observations that are collected throughout the decision-making process, and establish that this policy matches (up to a logarithmic scale) the regret rate that is achievable when smoothness is known a priori. Finally, we extend our method to account for local notions of smoothness and show that, under reasonable assumptions, our method achieves performance characterized by the local complexity of the problem as opposed to its global complexity. |
| Tasks | Decision Making, Multi-Armed Bandits |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09714v2 |
| https://arxiv.org/pdf/1910.09714v2.pdf | |
| PWC | https://paperswithcode.com/paper/smoothness-adaptive-stochastic-bandits |
| Repo | |
| Framework | |
