PyTorchKR Papers

최신 논문

총 3,382편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1803.04474

Predicting Crime Using Spatial Features

Our study aims to build a machine learning model for crime prediction using geospatial features for different categories of crime. The reverse geocoding technique is applied to retrieve open street map (OSM) spatial data. This study also proposes finding hotpoints extracted from crime hotspots area found by Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). A spatial distance feature is then computed based on the position of different hotpoints for various types of crime and this value is used as a feature for classifiers. We test the engineered features in crime data from Royal Canadian Mounted Police of Halifax, NS. We observed a significant performance improvement in crime prediction using the new generated spatial features.

arXiv:1803.05120

Topology guaranteed segmentation of the human retina from OCT using convolutional neural networks

Optical coherence tomography (OCT) is a noninvasive imaging modality which can be used to obtain depth images of the retina. The changing layer thicknesses can thus be quantified by analyzing these OCT images, moreover these changes have been shown to correlate with disease progression in multiple sclerosis. Recent automated retinal layer segmentation tools use machine learning methods to perform pixel-wise labeling and graph methods to guarantee the layer hierarchy or topology. However, graph parameters like distance and smoothness constraints must be experimentally assigned by retinal region and pathology, thus degrading the flexibility and time efficiency of the whole framework. In this paper, we develop cascaded deep networks to provide a topologically correct segmentation of the retinal layers in a single feed forward propagation. The first network (S-Net) performs pixel-wise labeling and the second regression network (R-Net) takes the topologically unconstrained S-Net results and outputs layer thicknesses for each layer and each position. Relu activation is used as the final operation of the R-Net which guarantees non-negativity of the output layer thickness. Since the segmentation boundary position is acquired by summing up the corresponding non-negative layer thicknesses, the layer ordering (i.e., topology) of the reconstructed boundaries is guaranteed even at the fovea where the distances between boundaries can be zero. The R-Net is trained using simulated masks and thus can be generalized to provide topology guaranteed segmentation for other layered structures. This deep network has achieved comparable mean absolute boundary error (2.82 {\mu}m) to state-of-the-art graph methods (2.83 {\mu}m).

arXiv:1803.06141

Patchwise object tracking via structural local sparse appearance model

In this paper, we propose a robust visual tracking method which exploits the relationships of targets in adjacent frames using patchwise joint sparse representation. Two sets of overlapping patches with different sizes are extracted from target candidates to construct two dictionaries with consideration of joint sparse representation. By applying this representation into structural sparse appearance model, we can take two-fold advantages. First, the correlation of target patches over time is considered. Second, using this local appearance model with different patch sizes takes into account local features of target thoroughly. Furthermore, the position of candidate patches and their occlusion levels are utilized simultaneously to obtain the final likelihood of target candidates. Evaluations on recent challenging benchmark show that our tracking method outperforms the state-of-the-art trackers.

arXiv:1803.06554

Fusion of an Ensemble of Augmented Image Detectors for Robust Object Detection

A significant challenge in object detection is accurate identification of an object's position in image space, whereas one algorithm with one set of parameters is usually not enough, and the fusion of multiple algorithms and/or parameters can lead to more robust results. Herein, a new computational intelligence fusion approach based on the dynamic analysis of agreement among object detection outputs is proposed. Furthermore, we propose an online versus just in training image augmentation strategy. Experiments comparing the results both with and without fusion are presented. We demonstrate that the augmented and fused combination results are the best, with respect to higher accuracy rates and reduction of outlier influences. The approach is demonstrated in the context of cone, pedestrian and box detection for Advanced Driver Assistance Systems (ADAS) applications.

arXiv:1803.07835공식 코드 · Papers with Code

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment. To achieve this, we design a 2D representation called UV position map which records the 3D shape of a complete face in UV space, then train a simple Convolutional Neural Network to regress it from a single 2D image. We also integrate a weight mask into the loss function during training to improve the performance of the network. Our method does not rely on any prior face model, and can reconstruct full facial geometry along with semantic meaning. Meanwhile, our network is very light-weighted and spends only 9.8ms to process an image, which is extremely faster than previous works. Experiments on multiple challenging datasets show that our method surpasses other state-of-the-art methods on both reconstruction and alignment tasks by a large margin.

arXiv:1803.07624

Dynamic Filtering with Large Sampling Field for ConvNets

We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from not only the identical position but also multiple sampled neighbor regions. During sampling, residual learning is introduced to ease training and an attention mechanism is applied to fuse features from different samples. Such multiple samples enlarge the kernels' receptive fields significantly without requiring more parameters. While LS-DFN inherits the advantages of DFN, namely avoiding feature map blurring by position-wise kernels while keeping translation invariance, it also efficiently alleviates the overfitting issue caused by much more parameters than normal CNNs. Our model is efficient and can be trained end-to-end via standard back-propagation. We demonstrate the merits of our LS-DFN on both sparse and dense prediction tasks involving object detection, semantic segmentation, and flow estimation. Our results show LS-DFN enjoys stronger recognition abilities in object detection and semantic segmentation tasks on VOC benchmark and sharper responses in flow estimation on FlyingChairs dataset compared to strong baselines.

arXiv:1707.02309공식 코드 · Papers with Code

Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking

Object tracking is challenging as target objects often undergo drastic appearance changes over time. Recently, adaptive correlation filters have been successfully applied to object tracking. However, tracking algorithms relying on highly adaptive correlation filters are prone to drift due to noisy updates. Moreover, as these algorithms do not maintain long-term memory of target appearance, they cannot recover from tracking failures caused by heavy occlusion or target disappearance in the camera view. In this paper, we propose to learn multiple adaptive correlation filters with both long-term and short-term memory of target appearance for robust object tracking. First, we learn a kernelized correlation filter with an aggressive learning rate for locating target objects precisely. We take into account the appropriate size of surrounding context and the feature representations. Second, we learn a correlation filter over a feature pyramid centered at the estimated target position for predicting scale changes. Third, we learn a complementary correlation filter with a conservative learning rate to maintain long-term memory of target appearance. We use the output responses of this long-term filter to determine if tracking failure occurs. In the case of tracking failures, we apply an incrementally learned detector to recover the target position in a sliding window fashion. Extensive experimental results on large-scale benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods in terms of efficiency, accuracy, and robustness.

arXiv:1803.09789

On Chatbots Exhibiting Goal-Directed Autonomy in Dynamic Environments

Conversation interfaces (CIs), or chatbots, are a popular form of intelligent agents that engage humans in task-oriented or informal conversation. In this position paper and demonstration, we argue that chatbots working in dynamic environments, like with sensor data, can not only serve as a promising platform to research issues at the intersection of learning, reasoning, representation and execution for goal-directed autonomy; but also handle non-trivial business applications. We explore the underlying issues in the context of Water Advisor, a preliminary multi-modal conversation system that can access and explain water quality data.

arXiv:1803.10106

Event-based Face Detection and Tracking in the Blink of an Eye

We present the first purely event-based method for face detection using the high temporal resolution of an event-based camera. We will rely on a new feature that has never been used for such a task that relies on detecting eye blinks. Eye blinks are a unique natural dynamic signature of human faces that is captured well by event-based sensors that rely on relative changes of luminance. Although an eye blink can be captured with conventional cameras, we will show that the dynamics of eye blinks combined with the fact that two eyes act simultaneously allows to derive a robust methodology for face detection at a low computational cost and high temporal resolution. We show that eye blinks have a unique temporal signature over time that can be easily detected by correlating the acquired local activity with a generic temporal model of eye blinks that has been generated from a wide population of users. We furthermore show that once the face is reliably detected it is possible to apply a probabilistic framework to track the spatial position of a face for each incoming event while updating the position of trackers. Results are shown for several indoor and outdoor experiments. We will also release an annotated data set that can be used for future work on the topic.

arXiv:1804.00787

Multi-Scale Spatially-Asymmetric Recalibration for Image Classification

Convolution is spatially-symmetric, i.e., the visual features are independent of its position in the image, which limits its ability to utilize contextual cues for visual recognition. This paper addresses this issue by introducing a recalibration process, which refers to the surrounding region of each neuron, computes an importance value and multiplies it to the original neural response. Our approach is named multi-scale spatially-asymmetric recalibration (MS-SAR), which extracts visual cues from surrounding regions at multiple scales, and designs a weighting scheme which is asymmetric in the spatial domain. MS-SAR is implemented in an efficient way, so that only small fractions of extra parameters and computations are required. We apply MS-SAR to several popular building blocks, including the residual block and the densely-connected block, and demonstrate its superior performance in both CIFAR and ILSVRC2012 classification tasks.

arXiv:1804.02698

Hierarchical Modular Reinforcement Learning Method and Knowledge Acquisition of State-Action Rule for Multi-target Problem

Hierarchical Modular Reinforcement Learning (HMRL), consists of 2 layered learning where Profit Sharing works to plan a prey position in the higher layer and Q-learning method trains the state-actions to the target in the lower layer. In this paper, we expanded HMRL to multi-target problem to take the distance between targets to the consideration. The function, called `AT field', can estimate the interests for an agent according to the distance between 2 agents and the advantage/disadvantage of the other agent. Moreover, the knowledge related to state-action rules is extracted by C4.5. The action under the situation is decided by using the acquired knowledge. To verify the effectiveness of proposed method, some experimental results are reported.

arXiv:1804.03583

Classification of Point Cloud Scenes with Multiscale Voxel Deep Network

In this article we describe a new convolutional neural network (CNN) to classify 3D point clouds of urban or indoor scenes. Solutions are given to the problems encountered working on scene point clouds, and a network is described that allows for point classification using only the position of points in a multi-scale neighborhood. On the reduced-8 Semantic3D benchmark [Hackel et al., 2017], this network, ranked second, beats the state of the art of point classification methods (those not using a regularization step).

arXiv:1804.04216공식 코드 · Papers with Code

Market Making via Reinforcement Learning

Market making is a fundamental trading problem in which an agent provides liquidity by continually offering to buy and sell a security. The problem is challenging due to inventory risk, the risk of accumulating an unfavourable position and ultimately losing money. In this paper, we develop a high-fidelity simulation of limit order book markets, and use it to design a market making agent using temporal-difference reinforcement learning. We use a linear combination of tile codings as a value function approximator, and design a custom reward function that controls inventory risk. We demonstrate the effectiveness of our approach by showing that our agent outperforms both simple benchmark strategies and a recent online learning approach from the literature.

arXiv:1804.04112공식 코드 · Papers with Code

Beamformed Fingerprint Learning for Accurate Millimeter Wave Positioning

With millimeter wave wireless communications, the resulting radiation reflects on most visible objects, creating rich multipath environments, namely in urban scenarios. The radiation captured by a listening device is thus shaped by the obstacles encountered, which carry latent information regarding their relative positions. In this paper, a system to convert the received millimeter wave radiation into the device's position is proposed, making use of the aforementioned hidden information. Using deep learning techniques and a pre-established codebook of beamforming patterns transmitted by a base station, the simulations show that average estimation errors below 10 meters are achievable in realistic outdoors scenarios that contain mostly non-line-of-sight positions, paving the way for new positioning systems.

arXiv:1804.03943

VR IQA NET: Deep Virtual Reality Image Quality Assessment using Adversarial Learning

In this paper, we propose a novel virtual reality image quality assessment (VR IQA) with adversarial learning for omnidirectional images. To take into account the characteristics of the omnidirectional image, we devise deep networks including novel quality score predictor and human perception guider. The proposed quality score predictor automatically predicts the quality score of distorted image using the latent spatial and position feature. The proposed human perception guider criticizes the predicted quality score of the predictor with the human perceptual score using adversarial learning. For evaluation, we conducted extensive subjective experiments with omnidirectional image dataset. Experimental results show that the proposed VR IQA metric outperforms the 2-D IQA and the state-of-the-arts VR IQA.

arXiv:1803.02155공식 코드 · Papers with Code

Self-Attention with Relative Position Representations

Relying entirely on an attention mechanism, the Transformer introduced by Vaswani et al. (2017) achieves state-of-the-art results for machine translation. In contrast to recurrent and convolutional neural networks, it does not explicitly model relative or absolute position information in its structure. Instead, it requires adding representations of absolute positions to its inputs. In this work we present an alternative approach, extending the self-attention mechanism to efficiently consider representations of the relative positions, or distances between sequence elements. On the WMT 2014 English-to-German and English-to-French translation tasks, this approach yields improvements of 1.3 BLEU and 0.3 BLEU over absolute position representations, respectively. Notably, we observe that combining relative and absolute position representations yields no further improvement in translation quality. We describe an efficient implementation of our method and cast it as an instance of relation-aware self-attention mechanisms that can generalize to arbitrary graph-labeled inputs.

arXiv:1804.04817

Offline and Online calibration of Mobile Robot and SLAM Device for Navigation

Robot navigation technology is required to accomplish difficult tasks in various environments. In navigation, it is necessary to know the information of the external environments and the state of the robot under the environment. On the other hand, various studies have been done on SLAM technology, which is also used for navigation, but also applied to devices for Mixed Reality and the like. In this paper, we propose a robot-device calibration method for navigation with a device using SLAM technology on a robot. The calibration is performed by using the position and orientation information given by the robot and the device. In the calibration, the most efficient way of movement is clarified according to the restriction of the robot movement. Furthermore, we also show a method to dynamically correct the position and orientation of the robot so that the information of the external environment and the shape information of the robot maintain consistency in order to reduce the dynamic error occurring during navigation. Our method can be easily used for various kinds of robots and localization with sufficient precision for navigation is possible with offline calibration and online position correction. In the experiments, we confirm the parameters obtained by two types of offline calibration according to the degree of freedom of robot movement and validate the effectiveness of online correction method by plotting localized position error during robot's intense movement. Finally, we show the demonstration of navigation using SLAM device.

arXiv:1711.07971공식 코드 · Papers with Code

Non-local Neural Networks

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies. Inspired by the classical non-local means method in computer vision, our non-local operation computes the response at a position as a weighted sum of the features at all positions. This building block can be plugged into many computer vision architectures. On the task of video classification, even without any bells and whistles, our non-local models can compete or outperform current competition winners on both Kinetics and Charades datasets. In static image recognition, our non-local models improve object detection/segmentation and pose estimation on the COCO suite of tasks. Code is available at https://github.com/facebookresearch/video-nonlocal-net .

arXiv:1601.08057

On the Geometric Ergodicity of Hamiltonian Monte Carlo

We establish general conditions under which Markov chains produced by the Hamiltonian Monte Carlo method will and will not be geometrically ergodic. We consider implementations with both position-independent and position-dependent integration times. In the former case we find that the conditions for geometric ergodicity are essentially a gradient of the log-density which asymptotically points towards the centre of the space and grows no faster than linearly. In an idealised scenario in which the integration time is allowed to change in different regions of the space, we show that geometric ergodicity can be recovered for a much broader class of tail behaviours, leading to some guidelines for the choice of this free parameter in practice.

arXiv:1804.06137

SeerNet at SemEval-2018 Task 1: Domain Adaptation for Affect in Tweets

The paper describes the best performing system for the SemEval-2018 Affect in Tweets (English) sub-tasks. The system focuses on the ordinal classification and regression sub-tasks for valence and emotion. For ordinal classification valence is classified into 7 different classes ranging from -3 to 3 whereas emotion is classified into 4 different classes 0 to 3 separately for each emotion namely anger, fear, joy and sadness. The regression sub-tasks estimate the intensity of valence and each emotion. The system performs domain adaptation of 4 different models and creates an ensemble to give the final prediction. The proposed system achieved 1st position out of 75 teams which participated in the fore-mentioned sub-tasks. We outperform the baseline model by margins ranging from 49.2% to 76.4%, thus, pushing the state-of-the-art significantly.