Paper Group ANR 695
A Brief Survey on Autonomous Vehicle Possible Attacks, Exploits and Vulnerabilities. Addressing word-order Divergence in Multilingual Neural Machine Translation for extremely Low Resource Languages. Occupancy Map Prediction Using Generative and Fully Convolutional Networks for Vehicle Navigation. Discriminative Learning of Similarity and Group Equi …
A Brief Survey on Autonomous Vehicle Possible Attacks, Exploits and Vulnerabilities
Title | A Brief Survey on Autonomous Vehicle Possible Attacks, Exploits and Vulnerabilities |
Authors | Amara Dinesh Kumar, Koti Naga Renu Chebrolu, Vinayakumar R, Soman KP |
Abstract | Advanced driver assistance systems are advancing at a rapid pace and all major companies started investing in developing the autonomous vehicles. But the security and reliability is still uncertain and debatable. Imagine that a vehicle is compromised by the attackers and then what they can do. An attacker can control brake, accelerate and even steering which can lead to catastrophic consequences. This paper gives a very short and brief overview of most of the possible attacks on autonomous vehicle software and hardware and their potential implications. |
Tasks | Autonomous Vehicles |
Published | 2018-10-03 |
URL | http://arxiv.org/abs/1810.04144v1 |
http://arxiv.org/pdf/1810.04144v1.pdf | |
PWC | https://paperswithcode.com/paper/a-brief-survey-on-autonomous-vehicle-possible |
Repo | |
Framework | |
Addressing word-order Divergence in Multilingual Neural Machine Translation for extremely Low Resource Languages
Title | Addressing word-order Divergence in Multilingual Neural Machine Translation for extremely Low Resource Languages |
Authors | Rudra Murthy V, Anoop Kunchukuttan, Pushpak Bhattacharyya |
Abstract | Transfer learning approaches for Neural Machine Translation (NMT) train a NMT model on the assisting-target language pair (parent model) which is later fine-tuned for the source-target language pair of interest (child model), with the target language being the same. In many cases, the assisting language has a different word order from the source language. We show that divergent word order adversely limits the benefits from transfer learning when little to no parallel corpus between the source and target language is available. To bridge this divergence, We propose to pre-order the assisting language sentence to match the word order of the source language and train the parent model. Our experiments on many language pairs show that bridging the word order gap leads to significant improvement in the translation quality. |
Tasks | Machine Translation, Transfer Learning |
Published | 2018-11-01 |
URL | http://arxiv.org/abs/1811.00383v2 |
http://arxiv.org/pdf/1811.00383v2.pdf | |
PWC | https://paperswithcode.com/paper/addressing-word-order-divergence-in |
Repo | |
Framework | |
Occupancy Map Prediction Using Generative and Fully Convolutional Networks for Vehicle Navigation
Title | Occupancy Map Prediction Using Generative and Fully Convolutional Networks for Vehicle Navigation |
Authors | Kapil Katyal, Katie Popek, Chris Paxton, Joseph Moore, Kevin Wolfe, Philippe Burlina, Gregory D. Hager |
Abstract | Fast, collision-free motion through unknown environments remains a challenging problem for robotic systems. In these situations, the robot’s ability to reason about its future motion is often severely limited by sensor field of view (FOV). By contrast, biological systems routinely make decisions by taking into consideration what might exist beyond their FOV based on prior experience. In this paper, we present an approach for predicting occupancy map representations of sensor data for future robot motions using deep neural networks. We evaluate several deep network architectures, including purely generative and adversarial models. Testing on both simulated and real environments we demonstrated performance both qualitatively and quantitatively, with SSIM similarity measure up to 0.899. We showed that it is possible to make predictions about occupied space beyond the physical robot’s FOV from simulated training data. In the future, this method will allow robots to navigate through unknown environments in a faster, safer manner. |
Tasks | |
Published | 2018-03-06 |
URL | http://arxiv.org/abs/1803.02007v1 |
http://arxiv.org/pdf/1803.02007v1.pdf | |
PWC | https://paperswithcode.com/paper/occupancy-map-prediction-using-generative-and |
Repo | |
Framework | |
Discriminative Learning of Similarity and Group Equivariant Representations
Title | Discriminative Learning of Similarity and Group Equivariant Representations |
Authors | Shubhendu Trivedi |
Abstract | One of the most fundamental problems in machine learning is to compare examples: Given a pair of objects we want to return a value which indicates degree of (dis)similarity. Similarity is often task specific, and pre-defined distances can perform poorly, leading to work in metric learning. However, being able to learn a similarity-sensitive distance function also presupposes access to a rich, discriminative representation for the objects at hand. In this dissertation we present contributions towards both ends. In the first part of the thesis, assuming good representations for the data, we present a formulation for metric learning that makes a more direct attempt to optimize for the k-NN accuracy as compared to prior work. We also present extensions of this formulation to metric learning for kNN regression, asymmetric similarity learning and discriminative learning of Hamming distance. In the second part, we consider a situation where we are on a limited computational budget i.e. optimizing over a space of possible metrics would be infeasible, but access to a label aware distance metric is still desirable. We present a simple, and computationally inexpensive approach for estimating a well motivated metric that relies only on gradient estimates, discussing theoretical and experimental results. In the final part, we address representational issues, considering group equivariant convolutional neural networks (GCNNs). Equivariance to symmetry transformations is explicitly encoded in GCNNs; a classical CNN being the simplest example. In particular, we present a SO(3)-equivariant neural network architecture for spherical data, that operates entirely in Fourier space, while also providing a formalism for the design of fully Fourier neural networks that are equivariant to the action of any continuous compact group. |
Tasks | Metric Learning |
Published | 2018-08-30 |
URL | http://arxiv.org/abs/1808.10078v1 |
http://arxiv.org/pdf/1808.10078v1.pdf | |
PWC | https://paperswithcode.com/paper/discriminative-learning-of-similarity-and |
Repo | |
Framework | |
What Knowledge is Needed to Solve the RTE5 Textual Entailment Challenge?
Title | What Knowledge is Needed to Solve the RTE5 Textual Entailment Challenge? |
Authors | Peter Clark |
Abstract | This document gives a knowledge-oriented analysis of about 20 interesting Recognizing Textual Entailment (RTE) examples, drawn from the 2005 RTE5 competition test set. The analysis ignores shallow statistical matching techniques between T and H, and rather asks: What would it take to reasonably infer that T implies H? What world knowledge would be needed for this task? Although such knowledge-intensive techniques have not had much success in RTE evaluations, ultimately an intelligent system should be expected to know and deploy this kind of world knowledge required to perform this kind of reasoning. The selected examples are typically ones which our RTE system (called BLUE) got wrong and ones which require world knowledge to answer. In particular, the analysis covers cases where there was near-perfect lexical overlap between T and H, yet the entailment was NO, i.e., examples that most likely all current RTE systems will have got wrong. A nice example is #341 (page 26), that requires inferring from “a river floods” that “a river overflows its banks”. Seems it should be easy, right? Enjoy! |
Tasks | Natural Language Inference |
Published | 2018-06-10 |
URL | http://arxiv.org/abs/1806.03561v1 |
http://arxiv.org/pdf/1806.03561v1.pdf | |
PWC | https://paperswithcode.com/paper/what-knowledge-is-needed-to-solve-the-rte5 |
Repo | |
Framework | |
Efficient Online Hyperparameter Optimization for Kernel Ridge Regression with Applications to Traffic Time Series Prediction
Title | Efficient Online Hyperparameter Optimization for Kernel Ridge Regression with Applications to Traffic Time Series Prediction |
Authors | Hongyuan Zhan, Gabriel Gomes, Xiaoye S. Li, Kamesh Madduri, Kesheng Wu |
Abstract | Computational efficiency is an important consideration for deploying machine learning models for time series prediction in an online setting. Machine learning algorithms adjust model parameters automatically based on the data, but often require users to set additional parameters, known as hyperparameters. Hyperparameters can significantly impact prediction accuracy. Traffic measurements, typically collected online by sensors, are serially correlated. Moreover, the data distribution may change gradually. A typical adaptation strategy is periodically re-tuning the model hyperparameters, at the cost of computational burden. In this work, we present an efficient and principled online hyperparameter optimization algorithm for Kernel Ridge regression applied to traffic prediction problems. In tests with real traffic measurement data, our approach requires as little as one-seventh of the computation time of other tuning methods, while achieving better or similar prediction accuracy. |
Tasks | Hyperparameter Optimization, Time Series, Time Series Prediction, Traffic Prediction |
Published | 2018-11-01 |
URL | http://arxiv.org/abs/1811.00620v1 |
http://arxiv.org/pdf/1811.00620v1.pdf | |
PWC | https://paperswithcode.com/paper/efficient-online-hyperparameter-optimization |
Repo | |
Framework | |
Transfer Learning Enhanced Common Spatial Pattern Filtering for Brain Computer Interfaces (BCIs): Overview and a New Approach
Title | Transfer Learning Enhanced Common Spatial Pattern Filtering for Brain Computer Interfaces (BCIs): Overview and a New Approach |
Authors | He He, Dongrui Wu |
Abstract | The electroencephalogram (EEG) is the most widely used input for brain computer interfaces (BCIs), and common spatial pattern (CSP) is frequently used to spatially filter it to increase its signal-to-noise ratio. However, CSP is a supervised filter, which needs some subject-specific calibration data to design. This is time-consuming and not user-friendly. A promising approach for shortening or even completely eliminating this calibration session is transfer learning, which leverages relevant data or knowledge from other subjects or tasks. This paper reviews three existing approaches for incorporating transfer learning into CSP, and also proposes a new transfer learning enhanced CSP approach. Experiments on motor imagery classification demonstrate their effectiveness. Particularly, our proposed approach achieves the best performance when the number of target domain calibration samples is small. |
Tasks | Calibration, EEG, Transfer Learning |
Published | 2018-08-08 |
URL | http://arxiv.org/abs/1808.05853v1 |
http://arxiv.org/pdf/1808.05853v1.pdf | |
PWC | https://paperswithcode.com/paper/transfer-learning-enhanced-common-spatial |
Repo | |
Framework | |
Correlation Tracking via Robust Region Proposals
Title | Correlation Tracking via Robust Region Proposals |
Authors | Yuqi Han, Jinghong Nan, Zengshuo Zhang, Jingjing Wang, Baojun Zhao |
Abstract | Recently, correlation filter-based trackers have received extensive attention due to their simplicity and superior speed. However, such trackers perform poorly when the target undergoes occlusion, viewpoint change or other challenging attributes due to pre-defined sampling strategy. To tackle these issues, in this paper, we propose an adaptive region proposal scheme to facilitate visual tracking. To be more specific, a novel tracking monitoring indicator is advocated to forecast tracking failure. Afterwards, we incorporate detection and scale proposals respectively, to recover from model drift as well as handle aspect ratio variation. We test the proposed algorithm on several challenging sequences, which have demonstrated that the proposed tracker performs favourably against state-of-the-art trackers. |
Tasks | Visual Tracking |
Published | 2018-06-14 |
URL | http://arxiv.org/abs/1806.05530v1 |
http://arxiv.org/pdf/1806.05530v1.pdf | |
PWC | https://paperswithcode.com/paper/correlation-tracking-via-robust-region |
Repo | |
Framework | |
Computer Vision for Autonomous Vehicles
Title | Computer Vision for Autonomous Vehicles |
Authors | Rohit Gandikota |
Abstract | In this work, we try to implement Image Processing techniques in the area of autonomous vehicles, both indoor and outdoor. The challenges for both are different and the ways to tackle them vary too. We also showed deep learning makes things easier and precise. We also made base models for all the problems we tackle while building an autonomous car for Indian Institute of Space science and Technology. |
Tasks | Autonomous Vehicles |
Published | 2018-12-06 |
URL | http://arxiv.org/abs/1812.02542v1 |
http://arxiv.org/pdf/1812.02542v1.pdf | |
PWC | https://paperswithcode.com/paper/computer-vision-for-autonomous-vehicles-1 |
Repo | |
Framework | |
Multi-sensor data fusion based on a generalised belief divergence measure
Title | Multi-sensor data fusion based on a generalised belief divergence measure |
Authors | Fuyuan Xiao |
Abstract | Multi-sensor data fusion technology plays an important role in real applications. Because of the flexibility and effectiveness in modelling and processing the uncertain information regardless of prior probabilities, Dempster-Shafer evidence theory is widely applied in a variety of fields of information fusion. However, counter-intuitive results may come out when fusing the highly conflicting evidences. In order to deal with this problem, a novel method for multi-sensor data fusion based on a new generalised belief divergence measure of evidences is proposed. Firstly, the reliability weights of evidences are determined by considering the sufficiency and importance of the evidences. After that, on account of the reliability weights of evidences, a new Generalised Belief Jensen-Shannon divergence (GBJS) is designed to measure the discrepancy and conflict degree among multiple evidences, which can be utilised to measure the support degrees of evidences. Afterwards, the support degrees of evidences are used to adjust the bodies of the evidences before using the Dempster’s combination rule. Finally, an application in fault diagnosis demonstrates the validity of the proposed method. |
Tasks | |
Published | 2018-06-05 |
URL | http://arxiv.org/abs/1806.01563v1 |
http://arxiv.org/pdf/1806.01563v1.pdf | |
PWC | https://paperswithcode.com/paper/multi-sensor-data-fusion-based-on-a |
Repo | |
Framework | |
Towards Better Text Understanding and Retrieval through Kernel Entity Salience Modeling
Title | Towards Better Text Understanding and Retrieval through Kernel Entity Salience Modeling |
Authors | Chenyan Xiong, Zhengzhong Liu, Jamie Callan, Tie-Yan Liu |
Abstract | This paper presents a Kernel Entity Salience Model (KESM) that improves text understanding and retrieval by better estimating entity salience (importance) in documents. KESM represents entities by knowledge enriched distributed representations, models the interactions between entities and words by kernels, and combines the kernel scores to estimate entity salience. The whole model is learned end-to-end using entity salience labels. The salience model also improves ad hoc search accuracy, providing effective ranking features by modeling the salience of query entities in candidate documents. Our experiments on two entity salience corpora and two TREC ad hoc search datasets demonstrate the effectiveness of KESM over frequency-based and feature-based methods. We also provide examples showing how KESM conveys its text understanding ability learned from entity salience to search. |
Tasks | |
Published | 2018-05-03 |
URL | http://arxiv.org/abs/1805.01334v1 |
http://arxiv.org/pdf/1805.01334v1.pdf | |
PWC | https://paperswithcode.com/paper/towards-better-text-understanding-and |
Repo | |
Framework | |
Dense Adaptive Cascade Forest: A Self Adaptive Deep Ensemble for Classification Problems
Title | Dense Adaptive Cascade Forest: A Self Adaptive Deep Ensemble for Classification Problems |
Authors | Haiyang Wang, Yong Tang, Ziyang Jia, Fei Ye |
Abstract | Recent researches have shown that deep forest ensemble achieves a considerable increase in classification accuracy compared with the general ensemble learning methods, especially when the training set is small. In this paper, we take advantage of deep forest ensemble and introduce the Dense Adaptive Cascade Forest (daForest). Our model has a better performance than the original Cascade Forest with three major features: first, we apply SAMME.R boosting algorithm to improve the performance of the model. It guarantees the improvement as the number of layers increases. Second, our model connects each layer to the subsequent ones in a feed-forward fashion, which enhances the capability of the model to resist performance degeneration. Third, we add a hyper-parameters optimization layer before the first classification layer, making our model spend less time to set up and find the optimal hyper-parameters. Experimental results show that daForest performs significantly well, and in some cases, even outperforms neural networks and achieves state-of-the-art results. |
Tasks | |
Published | 2018-04-29 |
URL | https://arxiv.org/abs/1804.10885v5 |
https://arxiv.org/pdf/1804.10885v5.pdf | |
PWC | https://paperswithcode.com/paper/dense-adaptive-cascade-forest-a-self-adaptive |
Repo | |
Framework | |
LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images
Title | LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images |
Authors | Gregory Rogez, Philippe Weinzaepfel, Cordelia Schmid |
Abstract | We propose an end-to-end architecture for joint 2D and 3D human pose estimation in natural images. Key to our approach is the generation and scoring of a number of pose proposals per image, which allows us to predict 2D and 3D poses of multiple people simultaneously. Hence, our approach does not require an approximate localization of the humans for initialization. Our Localization-Classification-Regression architecture, named LCR-Net, contains 3 main components: 1) the pose proposal generator that suggests candidate poses at different locations in the image; 2) a classifier that scores the different pose proposals; and 3) a regressor that refines pose proposals both in 2D and 3D. All three stages share the convolutional feature layers and are trained jointly. The final pose estimation is obtained by integrating over neighboring pose hypotheses, which is shown to improve over a standard non maximum suppression algorithm. Our method recovers full-body 2D and 3D poses, hallucinating plausible body parts when the persons are partially occluded or truncated by the image boundary. Our approach significantly outperforms the state of the art in 3D pose estimation on Human3.6M, a controlled environment. Moreover, it shows promising results on real images for both single and multi-person subsets of the MPII 2D pose benchmark and demonstrates satisfying 3D pose results even for multi-person images. |
Tasks | 3D Human Pose Estimation, 3D Pose Estimation, Pose Estimation |
Published | 2018-03-01 |
URL | http://arxiv.org/abs/1803.00455v3 |
http://arxiv.org/pdf/1803.00455v3.pdf | |
PWC | https://paperswithcode.com/paper/lcr-net-multi-person-2d-and-3d-pose-detection |
Repo | |
Framework | |
Image-based Synthesis for Deep 3D Human Pose Estimation
Title | Image-based Synthesis for Deep 3D Human Pose Estimation |
Authors | Grégory Rogez, Cordelia Schmid |
Abstract | This paper addresses the problem of 3D human pose estimation in the wild. A significant challenge is the lack of training data, i.e., 2D images of humans annotated with 3D poses. Such data is necessary to train state-of-the-art CNN architectures. Here, we propose a solution to generate a large set of photorealistic synthetic images of humans with 3D pose annotations. We introduce an image-based synthesis engine that artificially augments a dataset of real images with 2D human pose annotations using 3D motion capture data. Given a candidate 3D pose, our algorithm selects for each joint an image whose 2D pose locally matches the projected 3D pose. The selected images are then combined to generate a new synthetic image by stitching local image patches in a kinematically constrained manner. The resulting images are used to train an end-to-end CNN for full-body 3D pose estimation. We cluster the training data into a large number of pose classes and tackle pose estimation as a $K$-way classification problem. Such an approach is viable only with large training sets such as ours. Our method outperforms most of the published works in terms of 3D pose estimation in controlled environments (Human3.6M) and shows promising results for real-world images (LSP). This demonstrates that CNNs trained on artificial images generalize well to real images. Compared to data generated from more classical rendering engines, our synthetic images do not require any domain adaptation or fine-tuning stage. |
Tasks | 3D Human Pose Estimation, 3D Pose Estimation, Domain Adaptation, Motion Capture, Pose Estimation |
Published | 2018-02-12 |
URL | http://arxiv.org/abs/1802.04216v1 |
http://arxiv.org/pdf/1802.04216v1.pdf | |
PWC | https://paperswithcode.com/paper/image-based-synthesis-for-deep-3d-human-pose |
Repo | |
Framework | |
Deep Information Theoretic Registration
Title | Deep Information Theoretic Registration |
Authors | Alireza Sedghi, Jie Luo, Alireza Mehrtash, Steve Pieper, Clare M. Tempany, Tina Kapur, Parvin Mousavi, William M. Wells III |
Abstract | This paper establishes an information theoretic framework for deep metric based image registration techniques. We show an exact equivalence between maximum profile likelihood and minimization of joint entropy, an important early information theoretic registration method. We further derive deep classifier-based metrics that can be used with iterated maximum likelihood to achieve Deep Information Theoretic Registration on patches rather than pixels. This alleviates a major shortcoming of previous information theoretic registration approaches, namely the implicit pixel-wise independence assumptions. Our proposed approach does not require well-registered training data; this brings previous fully supervised deep metric registration approaches to the realm of weak supervision. We evaluate our approach on several image registration tasks and show significantly better performance compared to mutual information, specifically when images have substantially different contrasts. This work enables general-purpose registration in applications where current methods are not successful. |
Tasks | Image Registration |
Published | 2018-12-31 |
URL | http://arxiv.org/abs/1901.00040v1 |
http://arxiv.org/pdf/1901.00040v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-information-theoretic-registration |
Repo | |
Framework | |