Paper Group ANR 1202
The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks. On the Adversarial Robustness of Neural Networks without Weight Transport. Simultaneous prediction of multiple outcomes using revised stacking algorithms. Elaboration Tolerant Representation of Markov Decision Process via Decision-Theoretic Extension of Probabilis …
The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks
| Title | The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks |
| Authors | Felix Assion, Peter Schlicht, Florens Greßner, Wiebke Günther, Fabian Hüger, Nico Schmidt, Umair Rasheed |
| Abstract | Most state-of-the-art machine learning (ML) classification systems are vulnerable to adversarial perturbations. As a consequence, adversarial robustness poses a significant challenge for the deployment of ML-based systems in safety- and security-critical environments like autonomous driving, disease detection or unmanned aerial vehicles. In the past years we have seen an impressive amount of publications presenting more and more new adversarial attacks. However, the attack research seems to be rather unstructured and new attacks often appear to be random selections from the unlimited set of possible adversarial attacks. With this publication, we present a structured analysis of the adversarial attack creation process. By detecting different building blocks of adversarial attacks, we outline the road to new sets of adversarial attacks. We call this the “attack generator”. In the pursuit of this objective, we summarize and extend existing adversarial perturbation taxonomies. The resulting taxonomy is then linked to the application context of computer vision systems for autonomous vehicles, i.e. semantic segmentation and object detection. Finally, in order to prove the usefulness of the attack generator, we investigate existing semantic segmentation attacks with respect to the detected defining components of adversarial attacks. |
| Tasks | Adversarial Attack, Autonomous Driving, Autonomous Vehicles, Object Detection, Semantic Segmentation |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.07077v1 |
| https://arxiv.org/pdf/1906.07077v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-attack-generator-a-systematic-approach |
| Repo | |
| Framework | |
On the Adversarial Robustness of Neural Networks without Weight Transport
| Title | On the Adversarial Robustness of Neural Networks without Weight Transport |
| Authors | Mohamed Akrout |
| Abstract | Neural networks trained with backpropagation, the standard algorithm of deep learning which uses weight transport, are easily fooled by existing gradient-based adversarial attacks. This class of attacks are based on certain small perturbations of the inputs to make networks misclassify them. We show that less biologically implausible deep neural networks trained with feedback alignment, which do not use weight transport, can be harder to fool, providing actual robustness. Tested on MNIST, deep neural networks trained without weight transport (1) have an adversarial accuracy of 98% compared to 0.03% for neural networks trained with backpropagation and (2) generate non-transferable adversarial examples. However, this gap decreases on CIFAR-10 but is still significant particularly for small perturbation magnitude less than 1/2. |
| Tasks | |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03560v2 |
| https://arxiv.org/pdf/1908.03560v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-adversarial-robustness-of-neural |
| Repo | |
| Framework | |
Simultaneous prediction of multiple outcomes using revised stacking algorithms
| Title | Simultaneous prediction of multiple outcomes using revised stacking algorithms |
| Authors | Li Xing, Mary Lesperance, Xuekui Zhang |
| Abstract | Motivation: HIV is difficult to treat because its virus mutates at a high rate and mutated viruses easily develop resistance to existing drugs. If the relationships between mutations and drug resistances can be determined from historical data, patients can be provided personalized treatment according to their own mutation information. The HIV Drug Resistance Database was built to investigate the relationships. Our goal is to build a model using data in this database, which simultaneously predicts the resistance of multiple drugs using mutation information from sequences of viruses for any new patient. Results: We propose two variations of a stacking algorithm which borrow information among multiple prediction tasks to improve multivariate prediction performance. The most attractive feature of our proposed methods is the flexibility with which complex multivariate prediction models can be constructed using any univariate prediction models. Using cross-validation studies, we show that our proposed methods outperform other popular multivariate prediction methods. Availability: An R package will be made available. |
| Tasks | |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.10153v1 |
| http://arxiv.org/pdf/1901.10153v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-prediction-of-multiple-outcomes |
| Repo | |
| Framework | |
Elaboration Tolerant Representation of Markov Decision Process via Decision-Theoretic Extension of Probabilistic Action Language pBC+
| Title | Elaboration Tolerant Representation of Markov Decision Process via Decision-Theoretic Extension of Probabilistic Action Language pBC+ |
| Authors | Yi Wang, Joohyung Lee |
| Abstract | We extend probabilistic action language pBC+ with the notion of utility as in decision theory. The semantics of the extended pBC+ can be defined as a shorthand notation for a decision-theoretic extension of the probabilistic answer set programming language LPMLN. Alternatively, the semantics of pBC+ can also be defined in terms of Markov Decision Process (MDP), which in turn allows for representing MDP in a succinct and elaboration tolerant way as well as to leverage an MDP solver to compute pBC+. The idea led to the design of the system pbcplus2mdp, which can find an optimal policy of a pBC+ action description using an MDP solver. |
| Tasks | |
| Published | 2019-04-01 |
| URL | http://arxiv.org/abs/1904.00512v1 |
| http://arxiv.org/pdf/1904.00512v1.pdf | |
| PWC | https://paperswithcode.com/paper/elaboration-tolerant-representation-of-markov |
| Repo | |
| Framework | |
Mean-Field Neural ODEs via Relaxed Optimal Control
| Title | Mean-Field Neural ODEs via Relaxed Optimal Control |
| Authors | Jean-François Jabir, David Šiška, Łukasz Szpruch |
| Abstract | We develop a framework for the analysis of deep neural networks and neural ODE models that are trained with stochastic gradient algorithms. We do that by identifying the connections between high-dimensional data-driven control problems, deep learning and theory of statistical sampling. In particular, we derive and study a mean-field (over-damped) Langevin algorithm for solving relaxed data-driven control problems. A key step in the analysis is to derive Pontryagin’s optimality principle for data-driven relaxed control problems. Subsequently, we study uniform-in-time propagation of chaos of time-discretised Mean-Field (overdamped) Langevin dynamics. We derive explicit convergence rate in terms of the learning rate, the number of particles/model parameters and the number of iterations of the gradient algorithm. In addition, we study the error arising when using a finite training data set and thus provide quantitive bounds on the generalisation error. Crucially, the obtained rates are dimension-independent. This is possible by exploiting the regularity of the model with respect to the measure over the parameter space (relaxed control). |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05475v1 |
| https://arxiv.org/pdf/1912.05475v1.pdf | |
| PWC | https://paperswithcode.com/paper/mean-field-neural-odes-via-relaxed-optimal |
| Repo | |
| Framework | |
Unobtrusive and Multimodal Approach for Behavioral Engagement Detection of Students
| Title | Unobtrusive and Multimodal Approach for Behavioral Engagement Detection of Students |
| Authors | Nese Alyuz, Eda Okur, Utku Genc, Sinem Aslan, Cagri Tanriover, Asli Arslan Esme |
| Abstract | We propose a multimodal approach for detection of students’ behavioral engagement states (i.e., On-Task vs. Off-Task), based on three unobtrusive modalities: Appearance, Context-Performance, and Mouse. Final behavioral engagement states are achieved by fusing modality-specific classifiers at the decision level. Various experiments were conducted on a student dataset collected in an authentic classroom. |
| Tasks | |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1901.05835v1 |
| http://arxiv.org/pdf/1901.05835v1.pdf | |
| PWC | https://paperswithcode.com/paper/unobtrusive-and-multimodal-approach-for |
| Repo | |
| Framework | |
Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds
| Title | Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds |
| Authors | Francis Engelmann, Theodora Kontogianni, Bastian Leibe |
| Abstract | In this work, we propose Dilated Point Convolutions (DPC). In a thorough ablation study, we show that the receptive field size is directly related to the performance of 3D point cloud processing tasks, including semantic segmentation and object classification. Point convolutions are widely used to efficiently process 3D data representations such as point clouds or graphs. However, we observe that the receptive field size of recent point convolutional networks is inherently limited. Our dilated point convolutions alleviate this issue, they significantly increase the receptive field size of point convolutions. Importantly, our dilation mechanism can easily be integrated into most existing point convolutional networks. To evaluate the resulting network architectures, we visualize the receptive field and report competitive scores on popular point cloud benchmarks. |
| Tasks | 3D Semantic Segmentation, Object Classification, Semantic Segmentation |
| Published | 2019-07-28 |
| URL | https://arxiv.org/abs/1907.12046v2 |
| https://arxiv.org/pdf/1907.12046v2.pdf | |
| PWC | https://paperswithcode.com/paper/dilated-point-convolutions-on-the-receptive |
| Repo | |
| Framework | |
360-Indoor: Towards Learning Real-World Objects in 360° Indoor Equirectangular Images
| Title | 360-Indoor: Towards Learning Real-World Objects in 360° Indoor Equirectangular Images |
| Authors | Shih-Han Chou, Cheng Sun, Wen-Yen Chang, Wan-Ting Hsu, Min Sun, Jianlong Fu |
| Abstract | While there are several widely used object detection datasets, current computer vision algorithms are still limited in conventional images. Such images narrow our vision in a restricted region. On the other hand, 360{\deg} images provide a thorough sight. In this paper, our goal is to provide a standard dataset to facilitate the vision and machine learning communities in 360{\deg} domain. To facilitate the research, we present a real-world 360{\deg} panoramic object detection dataset, 360-Indoor, which is a new benchmark for visual object detection and class recognition in 360{\deg} indoor images. It is achieved by gathering images of complex indoor scenes containing common objects and the intensive annotated bounding field-of-view. In addition, 360-Indoor has several distinct properties: (1) the largest category number (37 labels in total). (2) the most complete annotations on average (27 bounding boxes per image). The selected 37 objects are all common in indoor scene. With around 3k images and 90k labels in total, 360-Indoor achieves the largest dataset for detection in 360{\deg} images. In the end, extensive experiments on the state-of-the-art methods for both classification and detection are provided. We will release this dataset in the near future. |
| Tasks | Object Detection |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01712v1 |
| https://arxiv.org/pdf/1910.01712v1.pdf | |
| PWC | https://paperswithcode.com/paper/360-indoor-towards-learning-real-world |
| Repo | |
| Framework | |
Deep convolutional neural network application on rooftop detection for aerial image
| Title | Deep convolutional neural network application on rooftop detection for aerial image |
| Authors | Mengge Chen, Jonathan Li |
| Abstract | As one of the most destructive disasters in the world, earthquake causes death, injuries, destruction and enormous damage to the affected area. It is significant to detect buildings after an earthquake in response to reconstruction and damage evaluation. In this research, we proposed an automatic rooftop detection method based on the convolutional neural network (CNN) to extract buildings in the city of Christchurch and tuned hyperparameters to detect small detached houses from the aerial image. The experiment result shows that our approach can effectively and accurately detect and segment buildings and has competitive performance. |
| Tasks | |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13509v1 |
| https://arxiv.org/pdf/1910.13509v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-convolutional-neural-network-application |
| Repo | |
| Framework | |
Cardiac Segmentation of LGE MRI with Noisy Labels
| Title | Cardiac Segmentation of LGE MRI with Noisy Labels |
| Authors | Holger Roth, Wentao Zhu, Dong Yang, Ziyue Xu, Daguang Xu |
| Abstract | In this work, we attempt the segmentation of cardiac structures in late gadolinium-enhanced (LGE) magnetic resonance images (MRI) using only minimal supervision in a two-step approach. In the first step, we register a small set of five LGE cardiac magnetic resonance (CMR) images with ground truth labels to a set of 40 target LGE CMR images without annotation. Each manually annotated ground truth provides labels of the myocardium and the left ventricle (LV) and right ventricle (RV) cavities, which are used as atlases. After multi-atlas label fusion by majority voting, we possess noisy labels for each of the targeted LGE images. A second set of manual labels exists for 30 patients of the target LGE CMR images, but are annotated on different MRI sequences (bSSFP and T2-weighted). Again, we use multi-atlas label fusion with a consistency constraint to further refine our noisy labels if additional annotations in other modalities are available for a given patient. In the second step, we train a deep convolutional network for semantic segmentation on the target data while using data augmentation techniques to avoid over-fitting to the noisy labels. After inference and simple post-processing, we achieve our final segmentation for the targeted LGE CMR images, resulting in an average Dice of 0.890, 0.780, and 0.844 for LV cavity, LV myocardium, and RV cavity, respectively. |
| Tasks | Cardiac Segmentation, Data Augmentation, Semantic Segmentation |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.01242v1 |
| https://arxiv.org/pdf/1910.01242v1.pdf | |
| PWC | https://paperswithcode.com/paper/cardiac-segmentation-of-lge-mri-with-noisy |
| Repo | |
| Framework | |
Big Data Analytics for Manufacturing Internet of Things: Opportunities, Challenges and Enabling Technologies
| Title | Big Data Analytics for Manufacturing Internet of Things: Opportunities, Challenges and Enabling Technologies |
| Authors | Hong-Ning Dai, Hao Wang, Guangquan Xu, Jiafu Wan, Muhammad Imran |
| Abstract | The recent advances in information and communication technology (ICT) have promoted the evolution of conventional computer-aided manufacturing industry to smart data-driven manufacturing. Data analytics in massive manufacturing data can extract huge business values while can also result in research challenges due to the heterogeneous data types, enormous volume and real-time velocity of manufacturing data. This paper provides an overview on big data analytics in manufacturing Internet of Things (MIoT). This paper first starts with a discussion on necessities and challenges of big data analytics in manufacturing data of MIoT. Then, the enabling technologies of big data analytics of manufacturing data are surveyed and discussed. Moreover, this paper also outlines the future directions in this promising area. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://arxiv.org/abs/1909.00413v1 |
| https://arxiv.org/pdf/1909.00413v1.pdf | |
| PWC | https://paperswithcode.com/paper/big-data-analytics-for-manufacturing-internet |
| Repo | |
| Framework | |
Combining Multi-Sequence and Synthetic Images for Improved Segmentation of Late Gadolinium Enhancement Cardiac MRI
| Title | Combining Multi-Sequence and Synthetic Images for Improved Segmentation of Late Gadolinium Enhancement Cardiac MRI |
| Authors | Víctor M. Campello, Carlos Martín-Isla, Cristian Izquierdo, Steffen E. Petersen, Miguel A. González Ballester, Karim Lekadir |
| Abstract | Accurate segmentation of the cardiac boundaries in late gadolinium enhancement magnetic resonance images (LGE-MRI) is a fundamental step for accurate quantification of scar tissue. However, while there are many solutions for automatic cardiac segmentation of cine images, the presence of scar tissue can make the correct delineation of the myocardium in LGE-MRI challenging even for human experts. As part of the Multi-Sequence Cardiac MR Segmentation Challenge, we propose a solution for LGE-MRI segmentation based on two components. First, a generative adversarial network is trained for the task of modality-to-modality translation between cine and LGE-MRI sequences to obtain extra synthetic images for both modalities. Second, a deep learning model is trained for segmentation with different combinations of original, augmented and synthetic sequences. Our results based on three magnetic resonance sequences (LGE, bSSFP and T2) from 45 different patients show that the multi-sequence model training integrating synthetic images and data augmentation improves in the segmentation over conventional training with real datasets. In conclusion, the accuracy of the segmentation of LGE-MRI images can be improved by using complementary information provided by non-contrast MRI sequences. |
| Tasks | Cardiac Segmentation, Data Augmentation |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.01182v2 |
| https://arxiv.org/pdf/1909.01182v2.pdf | |
| PWC | https://paperswithcode.com/paper/combining-multi-sequence-and-synthetic-images |
| Repo | |
| Framework | |
A General Framework of Learning Multi-Vehicle Interaction Patterns from Videos
| Title | A General Framework of Learning Multi-Vehicle Interaction Patterns from Videos |
| Authors | Chengyuan Zhang, Jiacheng Zhu, Wenshuo Wang, Ding Zhao |
| Abstract | Semantic learning and understanding of multi-vehicle interaction patterns in a cluttered driving environment are essential but challenging for autonomous vehicles to make proper decisions. This paper presents a general framework to gain insights into intricate multi-vehicle interaction patterns from bird’s-eye view traffic videos. We adopt a Gaussian velocity field to describe the time-varying multi-vehicle interaction behaviors and then use deep autoencoders to learn associated latent representations for each temporal frame. Then, we utilize a hidden semi-Markov model with a hierarchical Dirichlet process as a prior to segment these sequential representations into granular components, also called traffic primitives, corresponding to interaction patterns. Experimental results demonstrate that our proposed framework can extract traffic primitives from videos, thus providing a semantic way to analyze multi-vehicle interaction patterns, even for cluttered driving scenarios that are far messier than human beings can cope with. |
| Tasks | Autonomous Vehicles |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07315v1 |
| https://arxiv.org/pdf/1907.07315v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-framework-of-learning-multi-vehicle |
| Repo | |
| Framework | |
How Case Based Reasoning Explained Neural Networks: An XAI Survey of Post-Hoc Explanation-by-Example in ANN-CBR Twins
| Title | How Case Based Reasoning Explained Neural Networks: An XAI Survey of Post-Hoc Explanation-by-Example in ANN-CBR Twins |
| Authors | Mark T Keane, Eoin M Kenny |
| Abstract | This paper surveys an approach to the XAI problem, using post-hoc explanation by example, that hinges on twinning Artificial Neural Networks (ANNs) with Case-Based Reasoning (CBR) systems, so-called ANN-CBR twins. A systematic survey of 1100+ papers was carried out to identify the fragmented literature on this topic and to trace it influence through to more recent work involving Deep Neural Networks (DNNs). The paper argues that this twin-system approach, especially using ANN-CBR twins, presents one possible coherent, generic solution to the XAI problem (and, indeed, XCBR problem). The paper concludes by road-mapping some future directions for this XAI solution involving (i) further tests of feature-weighting techniques, (iii) explorations of how explanatory cases might best be deployed (e.g., in counterfactuals, near-miss cases, a fortori cases), and (iii) the raising of the unwelcome and, much ignored, issue of human user evaluation. |
| Tasks | |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07186v1 |
| https://arxiv.org/pdf/1905.07186v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-case-based-reasoning-explained-neural |
| Repo | |
| Framework | |
Discretely-constrained deep network for weakly supervised segmentation
| Title | Discretely-constrained deep network for weakly supervised segmentation |
| Authors | Jizong Peng, Hoel Kervadec, Jose Dolz, Ismail Ben Ayed, Marco Pedersoli, Christian Desrosiers |
| Abstract | An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions. Recent efforts have focused on incorporating such constraints in the training of convolutional neural networks (CNN), however this has so far been done within a continuous optimization framework. Yet, various segmentation constraints and regularization can be modeled and optimized more efficiently in a discrete formulation. This paper proposes a method, based on the alternating direction method of multipliers (ADMM) algorithm, to train a CNN with discrete constraints and regularization priors. This method is applied to the segmentation of medical images with weak annotations, where both size constraints and boundary length regularization are enforced. Experiments on a benchmark cardiac segmentation dataset show our method to yield a performance near to full supervision. |
| Tasks | Cardiac Segmentation |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05770v1 |
| https://arxiv.org/pdf/1908.05770v1.pdf | |
| PWC | https://paperswithcode.com/paper/discretely-constrained-deep-network-for |
| Repo | |
| Framework | |
