Paper Group ANR 308
Combining Subgoal Graphs with Reinforcement Learning to Build a Rational Pathfinder. Classifying magnetic resonance image modalities with convolutional neural networks. Safe learning-based optimal motion planning for automated driving. Machine learning enables long time scale molecular photodynamics simulations. Densely Connected Convolutional Netw …
Combining Subgoal Graphs with Reinforcement Learning to Build a Rational Pathfinder
| Title | Combining Subgoal Graphs with Reinforcement Learning to Build a Rational Pathfinder |
| Authors | Junjie Zeng, Long Qin, Yue Hu, Cong Hu, Quanjun Yin |
| Abstract | In this paper, we present a hierarchical path planning framework called SG-RL (subgoal graphs-reinforcement learning), to plan rational paths for agents maneuvering in continuous and uncertain environments. By “rational”, we mean (1) efficient path planning to eliminate first-move lags; (2) collision-free and smooth for agents with kinematic constraints satisfied. SG-RL works in a two-level manner. At the first level, SG-RL uses a geometric path-planning method, i.e., Simple Subgoal Graphs (SSG), to efficiently find optimal abstract paths, also called subgoal sequences. At the second level, SG-RL uses an RL method, i.e., Least-Squares Policy Iteration (LSPI), to learn near-optimal motion-planning policies which can generate kinematically feasible and collision-free trajectories between adjacent subgoals. The first advantage of the proposed method is that SSG can solve the limitations of sparse reward and local minima trap for RL agents; thus, LSPI can be used to generate paths in complex environments. The second advantage is that, when the environment changes slightly (i.e., unexpected obstacles appearing), SG-RL does not need to reconstruct subgoal graphs and replan subgoal sequences using SSG, since LSPI can deal with uncertainties by exploiting its generalization ability to handle changes in environments. Simulation experiments in representative scenarios demonstrate that, compared with existing methods, SG-RL can work well on large-scale maps with relatively low action-switching frequencies and shorter path lengths, and SG-RL can deal with small changes in environments. We further demonstrate that the design of reward functions and the types of training environments are important factors for learning feasible policies. |
| Tasks | Motion Planning, Optimal Motion Planning |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.01700v1 |
| http://arxiv.org/pdf/1811.01700v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-subgoal-graphs-with-reinforcement |
| Repo | |
| Framework | |
Classifying magnetic resonance image modalities with convolutional neural networks
| Title | Classifying magnetic resonance image modalities with convolutional neural networks |
| Authors | Samuel Remedios, Dzung L. Pham, John A. Butman, Snehashis Roy |
| Abstract | Magnetic Resonance (MR) imaging allows the acquisition of images with different contrast properties depending on the acquisition protocol and the magnetic properties of tissues. Many MR brain image processing techniques, such as tissue segmentation, require multiple MR contrasts as inputs, and each contrast is treated differently. Thus it is advantageous to automate the identification of image contrasts for various purposes, such as facilitating image processing pipelines, and managing and maintaining large databases via content-based image retrieval (CBIR). Most automated CBIR techniques focus on a two-step process: extracting features from data and classifying the image based on these features. We present a novel 3D deep convolutional neural network (CNN)-based method for MR image contrast classification. The proposed CNN automatically identifies the MR contrast of an input brain image volume. Specifically, we explored three classification problems: (1) identify T1-weighted (T1-w), T2-weighted (T2-w), and fluid-attenuated inversion recovery (FLAIR) contrasts, (2) identify pre vs post-contrast T1, (3) identify pre vs post-contrast FLAIR. A total of 3418 image volumes acquired from multiple sites and multiple scanners were used. To evaluate each task, the proposed model was trained on 2137 images and tested on the remaining 1281 images. Results showed that image volumes were correctly classified with 97.57% accuracy. |
| Tasks | Content-Based Image Retrieval, Image Retrieval |
| Published | 2018-04-16 |
| URL | http://arxiv.org/abs/1804.05764v2 |
| http://arxiv.org/pdf/1804.05764v2.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-magnetic-resonance-image |
| Repo | |
| Framework | |
Safe learning-based optimal motion planning for automated driving
| Title | Safe learning-based optimal motion planning for automated driving |
| Authors | Zlatan Ajanovic, Bakir Lacevic, Georg Stettinger, Daniel Watzenig, Martin Horn |
| Abstract | This paper presents preliminary work on learning the search heuristic for the optimal motion planning for automated driving in urban traffic. Previous work considered search-based optimal motion planning framework (SBOMP) that utilized numerical or model-based heuristics that did not consider dynamic obstacles. Optimal solution was still guaranteed since dynamic obstacles can only increase the cost. However, significant variations in the search efficiency are observed depending whether dynamic obstacles are present or not. This paper introduces machine learning (ML) based heuristic that takes into account dynamic obstacles, thus adding to the performance consistency for achieving real-time implementation. |
| Tasks | Motion Planning, Optimal Motion Planning |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.09994v2 |
| http://arxiv.org/pdf/1805.09994v2.pdf | |
| PWC | https://paperswithcode.com/paper/safe-learning-based-optimal-motion-planning |
| Repo | |
| Framework | |
Machine learning enables long time scale molecular photodynamics simulations
| Title | Machine learning enables long time scale molecular photodynamics simulations |
| Authors | Julia Westermayr, Michael Gastegger, Maximilian F. S. J. Menger, Sebastian Mai, Leticia González, Philipp Marquetand |
| Abstract | Photo-induced processes are fundamental in nature, but accurate simulations are seriously limited by the cost of the underlying quantum chemical calculations, hampering their application for long time scales. Here we introduce a method based on machine learning to overcome this bottleneck and enable accurate photodynamics on nanosecond time scales, which are otherwise out of reach with contemporary approaches. Instead of expensive quantum chemistry during molecular dynamics simulations, we use deep neural networks to learn the relationship between a molecular geometry and its high-dimensional electronic properties. As an example, the time evolution of the methylenimmonium cation for one nanosecond is used to demonstrate that machine learning algorithms can outperform standard excited-state molecular dynamics approaches in their computational efficiency while delivering the same accuracy. |
| Tasks | |
| Published | 2018-11-22 |
| URL | https://arxiv.org/abs/1811.09112v2 |
| https://arxiv.org/pdf/1811.09112v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-enables-long-time-scale |
| Repo | |
| Framework | |
Densely Connected Convolutional Networks for Speech Recognition
| Title | Densely Connected Convolutional Networks for Speech Recognition |
| Authors | Chia Yu Li, Ngoc Thang Vu |
| Abstract | This paper presents our latest investigation on Densely Connected Convolutional Networks (DenseNets) for acoustic modelling (AM) in automatic speech recognition. DenseN-ets are very deep, compact convolutional neural networks, which have demonstrated incredible improvements over the state-of-the-art results on several data sets in computer vision. Our experimental results show that DenseNet can be used for AM significantly outperforming other neural-based models such as DNNs, CNNs, VGGs. Furthermore, results on Wall Street Journal revealed that with only a half of the training data DenseNet was able to outperform other models trained with the full data set by a large margin. |
| Tasks | Acoustic Modelling, Speech Recognition |
| Published | 2018-08-10 |
| URL | http://arxiv.org/abs/1808.03570v1 |
| http://arxiv.org/pdf/1808.03570v1.pdf | |
| PWC | https://paperswithcode.com/paper/densely-connected-convolutional-networks-for |
| Repo | |
| Framework | |
A scene perception system for visually impaired based on object detection and classification using multi-modal DCNN
| Title | A scene perception system for visually impaired based on object detection and classification using multi-modal DCNN |
| Authors | Baljit Kaur, Jhilik Bhattacharya |
| Abstract | This paper represents a cost-effective scene perception system aimed towards visually impaired individual. We use an odroid system integrated with an USB camera and USB laser that can be attached on the chest. The system classifies the detected objects along with its distance from the user and provides a voice output. Experimental results provided in this paper use outdoor traffic scenes. The object detection and classification framework exploits a multi-modal fusion based faster RCNN using motion, sharpening and blurring filters for efficient feature representation. |
| Tasks | Object Detection |
| Published | 2018-05-22 |
| URL | http://arxiv.org/abs/1805.08798v1 |
| http://arxiv.org/pdf/1805.08798v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-scene-perception-system-for-visually |
| Repo | |
| Framework | |
Group-sparse SVD Models and Their Applications in Biological Data
| Title | Group-sparse SVD Models and Their Applications in Biological Data |
| Authors | Wenwen Min, Juan Liu, Shihua Zhang |
| Abstract | Sparse Singular Value Decomposition (SVD) models have been proposed for biclustering high dimensional gene expression data to identify block patterns with similar expressions. However, these models do not take into account prior group effects upon variable selection. To this end, we first propose group-sparse SVD models with group Lasso (GL1-SVD) and group L0-norm penalty (GL0-SVD) for non-overlapping group structure of variables. However, such group-sparse SVD models limit their applicability in some problems with overlapping structure. Thus, we also propose two group-sparse SVD models with overlapping group Lasso (OGL1-SVD) and overlapping group L0-norm penalty (OGL0-SVD). We first adopt an alternating iterative strategy to solve GL1-SVD based on a block coordinate descent method, and GL0-SVD based on a projection method. The key of solving OGL1-SVD is a proximal operator with overlapping group Lasso penalty. We employ an alternating direction method of multipliers (ADMM) to solve the proximal operator. Similarly, we develop an approximate method to solve OGL0-SVD. Applications of these methods and comparison with competing ones using simulated data demonstrate their effectiveness. Extensive applications of them onto several real gene expression data with gene prior group knowledge identify some biologically interpretable gene modules. |
| Tasks | |
| Published | 2018-07-28 |
| URL | http://arxiv.org/abs/1807.10956v1 |
| http://arxiv.org/pdf/1807.10956v1.pdf | |
| PWC | https://paperswithcode.com/paper/group-sparse-svd-models-and-their |
| Repo | |
| Framework | |
How to Start Training: The Effect of Initialization and Architecture
| Title | How to Start Training: The Effect of Initialization and Architecture |
| Authors | Boris Hanin, David Rolnick |
| Abstract | We identify and study two common failure modes for early training in deep ReLU nets. For each we give a rigorous proof of when it occurs and how to avoid it, for fully connected and residual architectures. The first failure mode, exploding/vanishing mean activation length, can be avoided by initializing weights from a symmetric distribution with variance 2/fan-in and, for ResNets, by correctly weighting the residual modules. We prove that the second failure mode, exponentially large variance of activation length, never occurs in residual nets once the first failure mode is avoided. In contrast, for fully connected nets, we prove that this failure mode can happen and is avoided by keeping constant the sum of the reciprocals of layer widths. We demonstrate empirically the effectiveness of our theoretical results in predicting when networks are able to start training. In particular, we note that many popular initializations fail our criteria, whereas correct initialization and architecture allows much deeper networks to be trained. |
| Tasks | |
| Published | 2018-03-05 |
| URL | http://arxiv.org/abs/1803.01719v3 |
| http://arxiv.org/pdf/1803.01719v3.pdf | |
| PWC | https://paperswithcode.com/paper/how-to-start-training-the-effect-of |
| Repo | |
| Framework | |
Ensembling Neural Networks for Digital Pathology Images Classification and Segmentation
| Title | Ensembling Neural Networks for Digital Pathology Images Classification and Segmentation |
| Authors | Gleb Makarchuk, Vladimir Kondratenko, Maxim Pisov, Artem Pimkin, Egor Krivov, Mikhail Belyaev |
| Abstract | In the last years, neural networks have proven to be a powerful framework for various image analysis problems. However, some application domains have specific limitations. Notably, digital pathology is an example of such fields due to tremendous image sizes and quite limited number of training examples available. In this paper, we adopt state-of-the-art convolutional neural networks (CNN) architectures for digital pathology images analysis. We propose to classify image patches to increase effective sample size and then to apply an ensembling technique to build prediction for the original images. To validate the developed approaches, we conducted experiments with \textit{Breast Cancer Histology Challenge} dataset and obtained 90% accuracy for the 4-class tissue classification task. |
| Tasks | |
| Published | 2018-02-03 |
| URL | http://arxiv.org/abs/1802.00947v1 |
| http://arxiv.org/pdf/1802.00947v1.pdf | |
| PWC | https://paperswithcode.com/paper/ensembling-neural-networks-for-digital |
| Repo | |
| Framework | |
SeFM: A Sequential Feature Point Matching Algorithm for Object 3D Reconstruction
| Title | SeFM: A Sequential Feature Point Matching Algorithm for Object 3D Reconstruction |
| Authors | Zhihao Fang, He Ma, Xuemin Zhu, Xutao Guo, Ruixin Zhou |
| Abstract | 3D reconstruction is a fundamental issue in many applications and the feature point matching problem is a key step while reconstructing target objects. Conventional algorithms can only find a small number of feature points from two images which is quite insufficient for reconstruction. To overcome this problem, we propose SeFM a sequential feature point matching algorithm. We first utilize the epipolar geometry to find the epipole of each image. Rotating along the epipole, we generate a set of the epipolar lines and reserve those intersecting with the input image. Next, a rough matching phase, followed by a dense matching phase, is applied to find the matching dot-pairs using dynamic programming. Furthermore, we also remove wrong matching dot-pairs by calculating the validity. Experimental results illustrate that SeFM can achieve around 1,000 to 10,000 times matching dot-pairs, depending on individual image, compared to conventional algorithms and the object reconstruction with only two images is semantically visible. Moreover, it outperforms conventional algorithms, such as SIFT and SURF, regarding precision and recall. |
| Tasks | 3D Reconstruction, Object Reconstruction |
| Published | 2018-12-07 |
| URL | https://arxiv.org/abs/1812.02925v3 |
| https://arxiv.org/pdf/1812.02925v3.pdf | |
| PWC | https://paperswithcode.com/paper/sefm-a-sequential-feature-point-matching |
| Repo | |
| Framework | |
Multi-agent Inverse Reinforcement Learning for Certain General-sum Stochastic Games
| Title | Multi-agent Inverse Reinforcement Learning for Certain General-sum Stochastic Games |
| Authors | Xiaomin Lin, Stephen C. Adams, Peter A. Beling |
| Abstract | This paper addresses the problem of multi-agent inverse reinforcement learning (MIRL) in a two-player general-sum stochastic game framework. Five variants of MIRL are considered: uCS-MIRL, advE-MIRL, cooE-MIRL, uCE-MIRL, and uNE-MIRL, each distinguished by its solution concept. Problem uCS-MIRL is a cooperative game in which the agents employ cooperative strategies that aim to maximize the total game value. In problem uCE-MIRL, agents are assumed to follow strategies that constitute a correlated equilibrium while maximizing total game value. Problem uNE-MIRL is similar to uCE-MIRL in total game value maximization, but it is assumed that the agents are playing a Nash equilibrium. Problems advE-MIRL and cooE-MIRL assume agents are playing an adversarial equilibrium and a coordination equilibrium, respectively. We propose novel approaches to address these five problems under the assumption that the game observer either knows or is able to accurate estimate the policies and solution concepts for players. For uCS-MIRL, we first develop a characteristic set of solutions ensuring that the observed bi-policy is a uCS and then apply a Bayesian inverse learning method. For uCE-MIRL, we develop a linear programming problem subject to constraints that define necessary and sufficient conditions for the observed policies to be correlated equilibria. The objective is to choose a solution that not only minimizes the total game value difference between the observed bi-policy and a local uCS, but also maximizes the scale of the solution. We apply a similar treatment to the problem of uNE-MIRL. The remaining two problems can be solved efficiently by taking advantage of solution uniqueness and setting up a convex optimization problem. Results are validated on various benchmark grid-world games. |
| Tasks | |
| Published | 2018-06-26 |
| URL | https://arxiv.org/abs/1806.09795v3 |
| https://arxiv.org/pdf/1806.09795v3.pdf | |
| PWC | https://paperswithcode.com/paper/multi-agent-inverse-reinforcement-learning-1 |
| Repo | |
| Framework | |
Denoising Distant Supervision for Relation Extraction via Instance-Level Adversarial Training
| Title | Denoising Distant Supervision for Relation Extraction via Instance-Level Adversarial Training |
| Authors | Xu Han, Zhiyuan Liu, Maosong Sun |
| Abstract | Existing neural relation extraction (NRE) models rely on distant supervision and suffer from wrong labeling problems. In this paper, we propose a novel adversarial training mechanism over instances for relation extraction to alleviate the noise issue. As compared with previous denoising methods, our proposed method can better discriminate those informative instances from noisy ones. Our method is also efficient and flexible to be applied to various NRE architectures. As shown in the experiments on a large-scale benchmark dataset in relation extraction, our denoising method can effectively filter out noisy instances and achieve significant improvements as compared with the state-of-the-art models. |
| Tasks | Denoising, Relation Extraction |
| Published | 2018-05-28 |
| URL | http://arxiv.org/abs/1805.10959v1 |
| http://arxiv.org/pdf/1805.10959v1.pdf | |
| PWC | https://paperswithcode.com/paper/denoising-distant-supervision-for-relation |
| Repo | |
| Framework | |
A Manually Annotated Chinese Corpus for Non-task-oriented Dialogue Systems
| Title | A Manually Annotated Chinese Corpus for Non-task-oriented Dialogue Systems |
| Authors | Jing Li, Yan Song, Haisong Zhang, Shuming Shi |
| Abstract | This paper presents a large-scale corpus for non-task-oriented dialogue response selection, which contains over 27K distinct prompts more than 82K responses collected from social media. To annotate this corpus, we define a 5-grade rating scheme: bad, mediocre, acceptable, good, and excellent, according to the relevance, coherence, informativeness, interestingness, and the potential to move a conversation forward. To test the validity and usefulness of the produced corpus, we compare various unsupervised and supervised models for response selection. Experimental results confirm that the proposed corpus is helpful in training response selection models. |
| Tasks | Task-Oriented Dialogue Systems |
| Published | 2018-05-15 |
| URL | http://arxiv.org/abs/1805.05542v1 |
| http://arxiv.org/pdf/1805.05542v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-manually-annotated-chinese-corpus-for-non |
| Repo | |
| Framework | |
3DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCN
| Title | 3DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCN |
| Authors | Guanghua Pan, Jun Wang, Rendong Ying, Peilin Liu |
| Abstract | Deep learning on point clouds has made a lot of progress recently. Many point cloud dedicated deep learning frameworks, such as PointNet and PointNet++, have shown advantages in accuracy and speed comparing to those using traditional 3D convolution algorithms. However, nearly all of these methods face a challenge, since the coordinates of the point cloud are decided by the coordinate system, they cannot handle the problem of 3D transform invariance properly. In this paper, we propose a general framework for point cloud learning. We achieve transform invariance by learning inner 3D geometry feature based on local graph representation, and propose a feature extraction network based on graph convolution network. Through experiments on classification and segmentation tasks, our method achieves state-of-the-art performance in rotated 3D object classification, and achieve competitive performance with the state-of-the-art in classification and segmentation tasks with fixed coordinate value. |
| Tasks | 3D Object Classification, Object Classification |
| Published | 2018-12-15 |
| URL | http://arxiv.org/abs/1812.06254v1 |
| http://arxiv.org/pdf/1812.06254v1.pdf | |
| PWC | https://paperswithcode.com/paper/3dti-net-learn-inner-transform-invariant-3d |
| Repo | |
| Framework | |
Automatic Identification of Indicators of Compromise using Neural-Based Sequence Labelling
| Title | Automatic Identification of Indicators of Compromise using Neural-Based Sequence Labelling |
| Authors | Shengping Zhou, Zi Long, Lianzhi Tan, Hao Guo |
| Abstract | Indicators of Compromise (IOCs) are artifacts observed on a network or in an operating system that can be utilized to indicate a computer intrusion and detect cyber-attacks in an early stage. Thus, they exert an important role in the field of cybersecurity. However, state-of-the-art IOCs detection systems rely heavily on hand-crafted features with expert knowledge of cybersecurity, and require a large amount of supervised training corpora to train an IOC classifier. In this paper, we propose using a neural-based sequence labelling model to identify IOCs automatically from reports on cybersecurity without expert knowledge of cybersecurity. Our work is the first to apply an end-to-end sequence labelling to the task in IOCs identification. By using an attention mechanism and several token spelling features, we find that the proposed model is capable of identifying the low frequency IOCs from long sentences contained in cybersecurity reports. Experiments show that the proposed model outperforms other sequence labelling models, achieving over 88% average F1-score. |
| Tasks | |
| Published | 2018-10-24 |
| URL | http://arxiv.org/abs/1810.10156v1 |
| http://arxiv.org/pdf/1810.10156v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-identification-of-indicators-of |
| Repo | |
| Framework | |
