Paper Group ANR 30
Spatiotemporal Camera-LiDAR Calibration: A Targetless and Structureless Approach. Detecting Adversarial Examples in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression. Predicting A Creator’s Preferences In, and From, Interactive Generative Art. Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction. …
Spatiotemporal Camera-LiDAR Calibration: A Targetless and Structureless Approach
| Title | Spatiotemporal Camera-LiDAR Calibration: A Targetless and Structureless Approach |
| Authors | Chanoh Park, Peyman Moghadam, Soohwan Kim, Sridha Sridharan, Clinton Fookes |
| Abstract | The demand for multimodal sensing systems for robotics is growing due to the increase in robustness, reliability and accuracy offered by these systems. These systems also need to be spatially and temporally co-registered to be effective. In this paper, we propose a targetless and structureless spatiotemporal camera-LiDAR calibration method. Our method combines a closed-form solution with a modified structureless bundle adjustment where the coarse-to-fine approach does not {require} an initial guess on the spatiotemporal parameters. Also, as 3D features (structure) are calculated from triangulation only, there is no need to have a calibration target or to match 2D features with the 3D point cloud which provides flexibility in the calibration process and sensor configuration. We demonstrate the accuracy and robustness of the proposed method through both simulation and real data experiments using multiple sensor payload configurations mounted to hand-held, aerial and legged robot systems. Also, qualitative results are given in the form of a colorized point cloud visualization. |
| Tasks | Calibration |
| Published | 2020-01-17 |
| URL | https://arxiv.org/abs/2001.06175v1 |
| https://arxiv.org/pdf/2001.06175v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatiotemporal-camera-lidar-calibration-a |
| Repo | |
| Framework | |
Detecting Adversarial Examples in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
| Title | Detecting Adversarial Examples in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression |
| Authors | Feiyang Cai, Jiani Li, Xenofon Koutsoukos |
| Abstract | Learning-enabled components (LECs) are widely used in cyber-physical systems (CPS) since they can handle the uncertainty and variability of the environment and increase the level of autonomy. However, it has been shown that LECs such as deep neural networks (DNN) are not robust and adversarial examples can cause the model to make a false prediction. The paper considers the problem of efficiently detecting adversarial examples in LECs used for regression in CPS. The proposed approach is based on inductive conformal prediction and uses a regression model based on variational autoencoder. The architecture allows to take into consideration both the input and the neural network prediction for detecting adversarial, and more generally, out-of-distribution examples. We demonstrate the method using an advanced emergency braking system implemented in an open source simulator for self-driving cars where a DNN is used to estimate the distance to an obstacle. The simulation results show that the method can effectively detect adversarial examples with a short detection delay. |
| Tasks | Self-Driving Cars |
| Published | 2020-03-21 |
| URL | https://arxiv.org/abs/2003.10804v1 |
| https://arxiv.org/pdf/2003.10804v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-adversarial-examples-in-learning |
| Repo | |
| Framework | |
Predicting A Creator’s Preferences In, and From, Interactive Generative Art
| Title | Predicting A Creator’s Preferences In, and From, Interactive Generative Art |
| Authors | Devi Parikh |
| Abstract | As a lay user creates an art piece using an interactive generative art tool, what, if anything, do the choices they make tell us about them and their preferences? These preferences could be in the specific generative art form (e.g., color palettes, density of the piece, thickness or curvatures of any lines in the piece); predicting them could lead to a smarter interactive tool. Or they could be preferences in other walks of life (e.g., music, fashion, food, interior design, paintings) or attributes of the person (e.g., personality type, gender, artistic inclinations); predicting them could lead to improved personalized recommendations for products or experiences. To study this research question, we collect preferences from 311 subjects, both in a specific generative art form and in other walks of life. We analyze the preferences and train machine learning models to predict a subset of preferences from the remaining. We find that preferences in the generative art form we studied cannot predict preferences in other walks of life better than chance (and vice versa). However, preferences within the generative art form are reliably predictive of each other. |
| Tasks | |
| Published | 2020-03-03 |
| URL | https://arxiv.org/abs/2003.01274v1 |
| https://arxiv.org/pdf/2003.01274v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-a-creators-preferences-in-and-from |
| Repo | |
| Framework | |
Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction
| Title | Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction |
| Authors | Bin Wen, Jie Luo, Xianglong Liu, Lei Huang |
| Abstract | Extracting graph representation of visual scenes in image is a challenging task in computer vision. Although there has been encouraging progress of scene graph generation in the past decade, we surprisingly find that the performance of existing approaches is largely limited by the strong biases, which mainly stem from (1) unconsciously assuming relations with certain semantic properties such as symmetric and (2) imbalanced annotations over different relations. To alleviate the negative effects of these biases, we proposed a new and simple architecture named Rich and Fair semantic extraction network (RiFa for short), to not only capture rich semantic properties of the relations, but also fairly predict relations with different scale of annotations. Using pseudo-siamese networks, RiFa embeds the subject and object respectively to distinguish their semantic differences and meanwhile preserve their underlying semantic properties. Then, it further predicts subject-object relations based on both the visual and semantic features of entities under certain contextual area, and fairly ranks the relation predictions for those with a few annotations. Experiments on the popular Visual Genome dataset show that RiFa achieves state-of-the-art performance under several challenging settings of scene graph task. Especially, it performs significantly better on capturing different semantic properties of relations, and obtains the best overall per relation performance. |
| Tasks | Graph Generation, Scene Graph Generation |
| Published | 2020-02-01 |
| URL | https://arxiv.org/abs/2002.00176v1 |
| https://arxiv.org/pdf/2002.00176v1.pdf | |
| PWC | https://paperswithcode.com/paper/unbiased-scene-graph-generation-via-rich-and |
| Repo | |
| Framework | |
Differentiating the Black-Box: Optimization with Local Generative Surrogates
| Title | Differentiating the Black-Box: Optimization with Local Generative Surrogates |
| Authors | Sergey Shirobokov, Vladislav Belavin, Michael Kagan, Andrey Ustyuzhanin, Atılım Güneş Baydin |
| Abstract | We propose a novel method for gradient-based optimization of black-box simulators using differentiable local surrogate models. In fields such as physics and engineering, many processes are modeled with non-differentiable simulators with intractable likelihoods. Optimization of these forward models is particularly challenging, especially when the simulator is stochastic. To address such cases, we introduce the use of deep generative models to iteratively approximate the simulator in local neighborhoods of the parameter space. We demonstrate that these local surrogates can be used to approximate the gradient of the simulator, and thus enable gradient-based optimization of simulator parameters. In cases where the dependence of the simulator on the parameter space is constrained to a low dimensional submanifold, we observe that our method attains minima faster than all baseline methods, including Bayesian optimization, numerical optimization, and REINFORCE driven approaches. |
| Tasks | |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04632v1 |
| https://arxiv.org/pdf/2002.04632v1.pdf | |
| PWC | https://paperswithcode.com/paper/differentiating-the-black-box-optimization |
| Repo | |
| Framework | |
Two-stage breast mass detection and segmentation system towards automated high-resolution full mammogram analysis
| Title | Two-stage breast mass detection and segmentation system towards automated high-resolution full mammogram analysis |
| Authors | Yutong Yan, Pierre-Henri Conze, Gwenolé Quellec, Mathieu Lamard, Béatrice Cochener, Gouenou Coatrieux |
| Abstract | Mammography is the primary imaging modality used for early detection and diagnosis of breast cancer. Mammography analysis mainly refers to the extraction of regions of interest around tumors, followed by a segmentation step, which is essential to further classification of benign or malignant tumors. Breast masses are the most important findings among breast abnormalities. However, manual delineation of masses from native mammogram is a time consuming and error-prone task. An integrated computer-aided diagnosis system to assist radiologists in automatically detecting and segmenting breast masses is therefore in urgent need. We propose a fully-automated approach that guides accurate mass segmentation from full mammograms at high resolution through a detection stage. First, mass detection is performed by an efficient deep learning approach, You-Only-Look-Once, extended by integrating multi-scale predictions to improve automatic candidate selection. Second, a convolutional encoder-decoder network using nested and dense skip connections is employed to fine-delineate candidate masses. Unlike most previous studies based on segmentation from regions, our framework handles mass segmentation from native full mammograms without user intervention. Trained on INbreast and DDSM-CBIS public datasets, the pipeline achieves an overall average Dice of 80.44% on high-resolution INbreast test images, outperforming state-of-the-art methods. Our system shows promising accuracy as an automatic full-image mass segmentation system. The comprehensive evaluation provided for both detection and segmentation stages reveals strong robustness to the diversity of size, shape and appearance of breast masses, towards better computer-aided diagnosis. |
| Tasks | |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12079v1 |
| https://arxiv.org/pdf/2002.12079v1.pdf | |
| PWC | https://paperswithcode.com/paper/two-stage-breast-mass-detection-and |
| Repo | |
| Framework | |
Mode-Assisted Unsupervised Learning of Restricted Boltzmann Machines
| Title | Mode-Assisted Unsupervised Learning of Restricted Boltzmann Machines |
| Authors | Haik Manukian, Yan Ru Pei, Sean R. B. Bearden, Massimiliano Di Ventra |
| Abstract | Restricted Boltzmann machines (RBMs) are a powerful class of generative models, but their training requires computing a gradient that, unlike supervised backpropagation on typical loss functions, is notoriously difficult even to approximate. Here, we show that properly combining standard gradient updates with an off-gradient direction, constructed from samples of the RBM ground state (mode), improves their training dramatically over traditional gradient methods. This approach, which we call mode training, promotes faster training and stability, in addition to lower converged relative entropy (KL divergence). Along with the proofs of stability and convergence of this method, we also demonstrate its efficacy on synthetic datasets where we can compute KL divergences exactly, as well as on a larger machine learning standard, MNIST. The mode training we suggest is quite versatile, as it can be applied in conjunction with any given gradient method, and is easily extended to more general energy-based neural network structures such as deep, convolutional and unrestricted Boltzmann machines. |
| Tasks | |
| Published | 2020-01-15 |
| URL | https://arxiv.org/abs/2001.05559v2 |
| https://arxiv.org/pdf/2001.05559v2.pdf | |
| PWC | https://paperswithcode.com/paper/mode-assisted-unsupervised-learning-of |
| Repo | |
| Framework | |
Constructing fast approximate eigenspaces with application to the fast graph Fourier transforms
| Title | Constructing fast approximate eigenspaces with application to the fast graph Fourier transforms |
| Authors | Cristian Rusu, Lorenzo Rosasco |
| Abstract | We investigate numerically efficient approximations of eigenspaces associated to symmetric and general matrices. The eigenspaces are factored into a fixed number of fundamental components that can be efficiently manipulated (we consider extended orthogonal Givens or scaling and shear transformations). The number of these components controls the trade-off between approximation accuracy and the computational complexity of projecting on the eigenspaces. We write minimization problems for the single fundamental components and provide closed-form solutions. Then we propose algorithms that iterative update all these components until convergence. We show results on random matrices and an application on the approximation of graph Fourier transforms for directed and undirected graphs. |
| Tasks | |
| Published | 2020-02-22 |
| URL | https://arxiv.org/abs/2002.09723v2 |
| https://arxiv.org/pdf/2002.09723v2.pdf | |
| PWC | https://paperswithcode.com/paper/constructing-fast-approximate-eigenspaces |
| Repo | |
| Framework | |
DeFINE: Delayed Feedback based Immersive Navigation Environment for Studying Goal-Directed Human Navigation
| Title | DeFINE: Delayed Feedback based Immersive Navigation Environment for Studying Goal-Directed Human Navigation |
| Authors | Kshitij Tiwari, Ville Kyrki, Allen Cheung, Naohide Yamamoto |
| Abstract | With the advent of consumer-grade products for presenting an immersive virtual environment (VE), there is a growing interest in utilizing VEs for testing human navigation behavior. However, preparing a VE still requires a high level of technical expertise in computer graphics and virtual reality, posing a significant hurdle to embracing the emerging technology. To address this issue, this paper presents Delayed Feedback based Immersive Navigation Environment (DeFINE), a framework that allows for easy creation and administration of navigation tasks within customizable VEs via intuitive graphical user interfaces and simple settings files. Importantly, DeFINE has a built-in capability to provide performance feedback to participants during an experiment, a feature that is critically missing in other similar frameworks. To demonstrate the usability of DeFINE from both experimentalists’ and participants’ perspectives, a case study was conducted in which participants navigated to a hidden goal location with feedback that differentially weighted speed and accuracy of their responses. In addition, the participants evaluated DeFINE in terms of its ease of use, required workload, and proneness to induce cybersickness. Results showed that the participants’ navigation performance was affected differently by the types of feedback they received, and they rated DeFINE highly in the evaluations, validating DeFINE’s architecture for investigating human navigation in VEs. With its rich out-of-the-box functionality and great customizability due to open-source licensing, DeFINE makes VEs significantly more accessible to many researchers. |
| Tasks | |
| Published | 2020-03-06 |
| URL | https://arxiv.org/abs/2003.03133v1 |
| https://arxiv.org/pdf/2003.03133v1.pdf | |
| PWC | https://paperswithcode.com/paper/define-delayed-feedback-based-immersive |
| Repo | |
| Framework | |
Joint Distributions for TensorFlow Probability
| Title | Joint Distributions for TensorFlow Probability |
| Authors | Dan Piponi, Dave Moore, Joshua V. Dillon |
| Abstract | A central tenet of probabilistic programming is that a model is specified exactly once in a canonical representation which is usable by inference algorithms. We describe JointDistributions, a family of declarative representations of directed graphical models in TensorFlow Probability. |
| Tasks | Probabilistic Programming |
| Published | 2020-01-22 |
| URL | https://arxiv.org/abs/2001.11819v1 |
| https://arxiv.org/pdf/2001.11819v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-distributions-for-tensorflow |
| Repo | |
| Framework | |
Stochastic Probabilistic Programs
| Title | Stochastic Probabilistic Programs |
| Authors | David Tolpin, Tomer Dobkin |
| Abstract | We introduce the notion of a stochastic probabilistic program and present a reference implementation of a probabilistic programming facility supporting specification of stochastic probabilistic programs and inference in them. Stochastic probabilistic programs allow straightforward specification and efficient inference in models with nuisance parameters, noise, and nondeterminism. We give several examples of stochastic probabilistic programs, and compare the programs with corresponding deterministic probabilistic programs in terms of model specification and inference. We conclude with discussion of open research topics and related work. |
| Tasks | Probabilistic Programming |
| Published | 2020-01-08 |
| URL | https://arxiv.org/abs/2001.02656v3 |
| https://arxiv.org/pdf/2001.02656v3.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-probabilistic-programs |
| Repo | |
| Framework | |
CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation
| Title | CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation |
| Authors | Kancharagunta Kishan Babu, Shiv Ram Dubey |
| Abstract | Image-to-image transformation is a kind of problem, where the input image from one visual representation is transformed into the output image of another visual representation. Since 2014, Generative Adversarial Networks (GANs) have facilitated a new direction to tackle this problem by introducing the generator and the discriminator networks in its architecture. Many recent works, like Pix2Pix, CycleGAN, DualGAN, PS2MAN and CSGAN handled this problem with the required generator and discriminator networks and choice of the different losses that are used in the objective functions. In spite of these works, still there is a gap to fill in terms of both the quality of the images generated that should look more realistic and as much as close to the ground truth images. In this work, we introduce a new Image-to-Image Transformation network named Cyclic Discriminative Generative Adversarial Networks (CDGAN) that fills the above mentioned gaps. The proposed CDGAN generates high quality and more realistic images by incorporating the additional discriminator networks for cycled images in addition to the original architecture of the CycleGAN. To demonstrate the performance of the proposed CDGAN, it is tested over three different baseline image-to-image transformation datasets. The quantitative metrics such as pixel-wise similarity, structural level similarity and perceptual level similarity are used to judge the performance. Moreover, the qualitative results are also analyzed and compared with the state-of-the-art methods. The proposed CDGAN method clearly outperformed all the state-of-the-art methods when compared over the three baseline Image-to-Image transformation datasets. |
| Tasks | |
| Published | 2020-01-15 |
| URL | https://arxiv.org/abs/2001.05489v1 |
| https://arxiv.org/pdf/2001.05489v1.pdf | |
| PWC | https://paperswithcode.com/paper/cdgan-cyclic-discriminative-generative |
| Repo | |
| Framework | |
Centrality Graph Convolutional Networks for Skeleton-based Action Recognition
| Title | Centrality Graph Convolutional Networks for Skeleton-based Action Recognition |
| Authors | Dong Yang, Monica Mengqi Li, Hong Fu, Jicong Fan, Howard Leung |
| Abstract | The topological structure of skeleton data plays a significant role in human action recognition. Combining the topological structure with graph convolutional networks has achieved remarkable performance. In existing methods, modeling the topological structure of skeleton data only considered the connections between the joints and bones, and directly use physical information. However, there exists an unknown problem to investigate the key joints, bones and body parts in every human action. In this paper, we propose the centrality graph convolutional networks to uncover the overlooked topological information, and best take advantage of the information to distinguish key joints, bones, and body parts. A novel centrality graph convolutional network firstly highlights the effects of the key joints and bones to bring a definite improvement. Besides, the topological information of the skeleton sequence is explored and combined to further enhance the performance in a four-channel framework. Moreover, the reconstructed graph is implemented by the adaptive methods on the training process, which further yields improvements. Our model is validated by two large-scale datasets, NTU-RGB+D and Kinetics, and outperforms the state-of-the-art methods. |
| Tasks | Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2020-03-06 |
| URL | https://arxiv.org/abs/2003.03007v1 |
| https://arxiv.org/pdf/2003.03007v1.pdf | |
| PWC | https://paperswithcode.com/paper/centrality-graph-convolutional-networks-for |
| Repo | |
| Framework | |
Shape analysis via inconsistent surface registration
| Title | Shape analysis via inconsistent surface registration |
| Authors | Gary P. T. Choi, Di Qiu, Lok Ming Lui |
| Abstract | In this work, we develop a framework for shape analysis using inconsistent surface mapping. Traditional landmark-based geometric morphometrics methods suffer from the limited degrees of freedom, while most of the more advanced non-rigid surface mapping methods rely on a strong assumption of the global consistency of two surfaces. From a practical point of view, given two anatomical surfaces with prominent feature landmarks, it is more desirable to have a method that automatically detects the most relevant parts of the two surfaces and finds the optimal landmark-matching alignment between those parts, without assuming any global 1-1 correspondence between the two surfaces. Our method is capable of solving this problem using inconsistent surface registration based on quasi-conformal theory. It further enables us to quantify the dissimilarity of two shapes using quasi-conformal distortion and differences in mean and Gaussian curvatures, thereby providing a natural way for shape classification. Experiments on Platyrrhine molars demonstrate the effectiveness of our method and shed light on the interplay between function and shape in nature. |
| Tasks | |
| Published | 2020-03-03 |
| URL | https://arxiv.org/abs/2003.01357v1 |
| https://arxiv.org/pdf/2003.01357v1.pdf | |
| PWC | https://paperswithcode.com/paper/shape-analysis-via-inconsistent-surface |
| Repo | |
| Framework | |
Weakly Supervised Instance Segmentation by Deep Community Learning
| Title | Weakly Supervised Instance Segmentation by Deep Community Learning |
| Authors | Jaedong Hwang, Seohyun Kim, Jeany Son, Bohyung Han |
| Abstract | We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks. This task is formulated as a combination of weakly supervised object detection and semantic segmentation, where individual objects of the same class are identified and segmented separately. We address this problem by designing a unified deep neural network architecture, which has a positive feedback loop of object detection with bounding box regression, instance mask generation, instance segmentation, and feature extraction. Each component of the network makes active interactions with others to improve accuracy, and the end-to-end trainability of our model makes our results more robust and reproducible. The proposed algorithm achieves state-of-the-art performance in the weakly supervised setting without any additional training such as Fast R-CNN and Mask R-CNN on the standard benchmark dataset. |
| Tasks | Instance Segmentation, Object Detection, Semantic Segmentation, Weakly-supervised instance segmentation, Weakly Supervised Object Detection |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11207v2 |
| https://arxiv.org/pdf/2001.11207v2.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-instance-segmentation-by |
| Repo | |
| Framework | |
