PyTorchKR Papers

최신 논문

총 3,383편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1812.05415공식 코드 · Papers with Code

Geometrical Stem Detection from Image Data for Precision Agriculture

High efficiency in precision farming depends on accurate tools to perform weed detection and mapping of crops. This allows for precise removal of harmful weeds with a lower amount of pesticides, as well as increase of the harvest's yield by providing the farmer with valuable information. In this paper, we address the problem of fully automatic stem detection from image data for this purpose. Our approach runs on mobile agricultural robots taking RGB images. After processing the images to obtain a vegetation mask, our approach separates each plant into its individual leaves and later estimates a precise stem position. This allows an upstream mapping algorithm to add the high-resolution stem positions as a semantic aggregate to the global map of the robot, which can be used for weeding and for analyzing crop statistics. We implemented our approach and thoroughly tested it on three different datasets with vegetation masks and stem position ground truth. The experiments presented in this paper conclude that our module is able to detect leaves and estimate the stem's position at a rate of 56 Hz on a single CPU. We furthermore provide the software to the community.

arXiv:1812.02471

The Role of Normware in Trustworthy and Explainable AI

For being potentially destructive, in practice incomprehensible and for the most unintelligible, contemporary technology is setting high challenges on our society. New conception methods are urgently required. Reorganizing ideas and discussions presented in AI and related fields, this position paper aims to highlight the importance of normware--that is, computational artifacts specifying norms--with respect to these issues, and argues for its irreducibility with respect to software by making explicit its neglected ecological dimension in the decision-making cycle.

arXiv:1812.00190

Deep Learning Application in Security and Privacy -- Theory and Practice: A Position Paper

Technology is shaping our lives in a multitude of ways. This is fuelled by a technology infrastructure, both legacy and state of the art, composed of a heterogeneous group of hardware, software, services and organisations. Such infrastructure faces a diverse range of challenges to its operations that include security, privacy, resilience, and quality of services. Among these, cybersecurity and privacy are taking the centre-stage, especially since the General Data Protection Regulation (GDPR) came into effect. Traditional security and privacy techniques are overstretched and adversarial actors have evolved to design exploitation techniques that circumvent protection. With the ever-increasing complexity of technology infrastructure, security and privacy-preservation specialists have started to look for adaptable and flexible protection methods that can evolve (potentially autonomously) as the adversarial actor changes its techniques. For this, Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL) were put forward as saviours. In this paper, we look at the promises of AI, ML, and DL stated in academic and industrial literature and evaluate how realistic they are. We also put forward potential challenges a DL based security and privacy protection technique has to overcome. Finally, we conclude the paper with a discussion on what steps the DL and the security and privacy-preservation community have to take to ensure that DL is not just going to be hype, but an opportunity to build a secure, reliable, and trusted technology infrastructure on which we can rely on for so much in our lives.

arXiv:1812.01144

Back to the Future for Dialogue Research: A Position Paper

This short position paper is intended to provide a critique of current approaches to dialogue, as well as a roadmap for collaborative dialogue research. It is unapologetically opinionated, but informed by 40 years of dialogue re-search. No attempt is made to be comprehensive. The paper will discuss current research into building so-called "chatbots", slot-filling dialogue systems, and plan-based dialogue systems. For further discussion of some of these issues, please see (Allen et al., in press).

arXiv:1812.01129

Mitigating Planner Overfitting in Model-Based Reinforcement Learning

An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is optimal with respect to its model. Alternatively, it can take a more conservative stance and eschew its model in favor of optimizing its behavior solely via real-world interaction. This latter approach can be exceedingly slow to learn from experience, while the former can lead to "planner overfitting" - aspects of the agent's behavior are optimized to exploit errors in its model. This paper explores an intermediate position in which the planner seeks to avoid overfitting through a kind of regularization of the plans it considers. We present three different approaches that demonstrably mitigate planner overfitting in reinforcement-learning environments.

arXiv:1812.00155

Learning RoI Transformer for Detecting Oriented Objects in Aerial Images

Object detection in aerial images is an active yet challenging task in computer vision because of the birdview perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects. This leads to the common misalignment between the final object classification confidence and localization accuracy. Although rotated anchors have been used to tackle this problem, the design of them always multiplies the number of anchors and dramatically increases the computational complexity. In this paper, we propose a RoI Transformer to address these problems. More precisely, to improve the quality of region proposals, we first designed a Rotated RoI (RRoI) learner to transform a Horizontal Region of Interest (HRoI) into a Rotated Region of Interest (RRoI). Based on the RRoIs, we then proposed a Rotated Position Sensitive RoI Align (RPS-RoI-Align) module to extract rotation-invariant features from them for boosting subsequent classification and regression. Our RoI Transformer is with light weight and can be easily embedded into detectors for oriented object detection. A simple implementation of the RoI Transformer has achieved state-of-the-art performances on two common and challenging aerial datasets, i.e., DOTA and HRSC2016, with a neglectable reduction to detection speed. Our RoI Transformer exceeds the deformable Position Sensitive RoI pooling when oriented bounding-box annotations are available. Extensive experiments have also validated the flexibility and effectiveness of our RoI Transformer. The results demonstrate that it can be easily integrated with other detector architectures and significantly improve the performances.

arXiv:1811.12535

The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning

One of the main challenges of deep learning tools is their inability to capture model uncertainty. While Bayesian deep learning can be used to tackle the problem, Bayesian neural networks often require more time and computational power to train than deterministic networks. Our work explores whether fully Bayesian networks are needed to successfully capture model uncertainty. We vary the number and position of Bayesian layers in a network and compare their performance on active learning with the MNIST dataset. We found that we can fully capture the model uncertainty by using only a few Bayesian layers near the output of the network, combining the advantages of deterministic and Bayesian networks.

arXiv:1811.12728

Document Structure Measure for Hypernym discovery

Hypernym discovery is the problem of finding terms that have is-a relationship with a given term. We introduce a new context type, and a relatedness measure to differentiate hypernyms from other types of semantic relationships. Our Document Structure measure is based on hierarchical position of terms in a document, and their presence or otherwise in definition text. This measure quantifies the document structure using multiple attributes, and classes of weighted distance functions.

arXiv:1811.11969

Traffic Danger Recognition With Surveillance Cameras Without Training Data

We propose a traffic danger recognition model that works with arbitrary traffic surveillance cameras to identify and predict car crashes. There are too many cameras to monitor manually. Therefore, we developed a model to predict and identify car crashes from surveillance cameras based on a 3D reconstruction of the road plane and prediction of trajectories. For normal traffic, it supports real-time proactive safety checks of speeds and distances between vehicles to provide insights about possible high-risk areas. We achieve good prediction and recognition of car crashes without using any labeled training data of crashes. Experiments on the BrnoCompSpeed dataset show that our model can accurately monitor the road, with mean errors of 1.80% for distance measurement, 2.77 km/h for speed measurement, 0.24 m for car position prediction, and 2.53 km/h for speed prediction.

arXiv:1811.12354공식 코드 · Papers with Code

Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments

We study the problem of jointly reasoning about language and vision through a navigation and spatial reasoning task. We introduce the Touchdown task and dataset, where an agent must first follow navigation instructions in a real-life visual urban environment, and then identify a location described in natural language to find a hidden object at the goal position. The data contains 9,326 examples of English instructions and spatial descriptions paired with demonstrations. Empirical analysis shows the data presents an open challenge to existing methods, and qualitative linguistic analysis shows that the data displays richer use of spatial reasoning compared to related resources.

arXiv:1811.11742공식 코드 · Papers with Code

3D human pose estimation in video with temporal convolutions and semi-supervised training

In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and effective semi-supervised training method that leverages unlabeled video data. We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints. In the supervised setting, our fully-convolutional model outperforms the previous best result from the literature by 6 mm mean per-joint position error on Human3.6M, corresponding to an error reduction of 11%, and the model also shows significant improvements on HumanEva-I. Moreover, experiments with back-projection show that it comfortably outperforms previous state-of-the-art results in semi-supervised settings where labeled data is scarce. Code and models are available at https://github.com/facebookresearch/VideoPose3D

arXiv:1811.11456공식 코드 · Papers with Code

GIRNet: Interleaved Multi-Task Recurrent State Sequence Models

In several natural language tasks, labeled sequences are available in separate domains (say, languages), but the goal is to label sequences with mixed domain (such as code-switched text). Or, we may have available models for labeling whole passages (say, with sentiments), which we would like to exploit toward better position-specific label inference (say, target-dependent sentiment annotation). A key characteristic shared across such tasks is that different positions in a primary instance can benefit from different `experts' trained from auxiliary data, but labeled primary instances are scarce, and labeling the best expert for each position entails unacceptable cognitive burden. We propose GITNet, a unified position-sensitive multi-task recurrent neural network (RNN) architecture for such applications. Auxiliary and primary tasks need not share training instances. Auxiliary RNNs are trained over auxiliary instances. A primary instance is also submitted to each auxiliary RNN, but their state sequences are gated and merged into a novel composite state sequence tailored to the primary inference task. Our approach is in sharp contrast to recent multi-task networks like the cross-stitch and sluice network, which do not control state transfer at such fine granularity. We demonstrate the superiority of GIRNet using three applications: sentiment classification of code-switched passages, part-of-speech tagging of code-switched text, and target position-sensitive annotation of sentiment in monolingual passages. In all cases, we establish new state-of-the-art performance beyond recent competitive baselines.

arXiv:1811.11147

Understanding and Improving Kernel Local Descriptors

We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients. It combines two parametrizations of gradient position and direction, each parametrization provides robustness to a different type of patch mis-registration: polar parametrization for noise in the patch dominant orientation detection, Cartesian for imprecise location of the feature point. Combined with whitening of the descriptor space, that is learned with or without supervision, the performance is significantly improved. We analyze the effect of the whitening on patch similarity and demonstrate its semantic meaning. Our unsupervised variant is the best performing descriptor constructed without the need of labeled data. Despite the simplicity of the proposed descriptor, it competes well with deep learning approaches on a number of different tasks.

arXiv:1811.07123

Explicit Spatiotemporal Joint Relation Learning for Tracking Human Pose

We present a method for human pose tracking that is based on learning spatiotemporal relationships among joints. Beyond generating the heatmap of a joint in a given frame, our system also learns to predict the offset of the joint from a neighboring joint in the frame. Additionally, it is trained to predict the displacement of the joint from its position in the previous frame, in a manner that can account for possibly changing joint appearance, unlike optical flow. These relational cues in the spatial domain and temporal domain are inferred in a robust manner by attending only to relevant areas in the video frames. By explicitly learning and exploiting these joint relationships, our system achieves state-of-the-art performance on standard benchmarks for various pose tracking tasks including 3D body pose tracking in RGB video, 3D hand pose tracking in depth sequences, and 3D hand gesture tracking in RGB video.

arXiv:1811.04234

Towards Formula Translation using Recursive Neural Networks

While it has become common to perform automated translations on natural language, performing translations between different representations of mathematical formulae has thus far not been possible. We implemented the first translator for mathematical formulae based on recursive neural networks. We chose recursive neural networks because mathematical formulae inherently include a structural encoding. In our implementation, we developed new techniques and topologies for recursive tree-to-tree neural networks based on multi-variate multi-valued Long Short-Term Memory cells. We propose a novel approach for mini-batch training that utilizes clustering and tree traversal. We evaluate our translator and analyze the behavior of our proposed topologies and techniques based on a translation from generic LaTeX to the semantic LaTeX notation. We use the semantic LaTeX notation from the Digital Library for Mathematical Formulae and the Digital Repository for Mathematical Formulae at the National Institute for Standards and Technology. We find that a simple heuristics-based clustering algorithm outperforms the conventional clustering algorithms on the task of clustering binary trees of mathematical formulae with respect to their topology. Furthermore, we find a mask for the loss function, which can prevent the neural network from finding a local minimum of the loss function. Given our preliminary results, a complete translation from formula to formula is not yet possible. However, we achieved a prediction accuracy of 47.05% for predicting symbols at the correct position and an accuracy of 92.3% when ignoring the predicted position. Concluding, our work advances the field of recursive neural networks by improving the training speed and quality of training. In the future, we will work towards a complete translation allowing a machine-interpretation of LaTeX formulae.

arXiv:1811.04179공식 코드 · Papers with Code

Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction

We propose an approach for mapping natural language instructions and raw observations to continuous control of a quadcopter drone. Our model predicts interpretable position-visitation distributions indicating where the agent should go during execution and where it should stop, and uses the predicted distributions to select the actions to execute. This two-step model decomposition allows for simple and efficient training using a combination of supervised learning and imitation learning. We evaluate our approach with a realistic drone simulator, and demonstrate absolute task-completion accuracy improvements of 16.85% over two state-of-the-art instruction-following methods.

arXiv:1811.03264공식 코드 · Papers with Code

Calibration Wizard: A Guidance System for Camera Calibration Based on Modelling Geometric and Corner Uncertainty

It is well known that the accuracy of a calibration depends strongly on the choice of camera poses from which images of a calibration object are acquired. We present a system -- Calibration Wizard -- that interactively guides a user towards taking optimal calibration images. For each new image to be taken, the system computes, from all previously acquired images, the pose that leads to the globally maximum reduction of expected uncertainty on intrinsic parameters and then guides the user towards that pose. We also show how to incorporate uncertainty in corner point position in a novel principled manner, for both, calibration and computation of the next best pose. Synthetic and real-world experiments are performed to demonstrate the effectiveness of Calibration Wizard.

arXiv:1810.13118

SplineNets: Continuous Neural Decision Graphs

We present SplineNets, a practical and novel approach for using conditioning in convolutional neural networks (CNNs). SplineNets are continuous generalizations of neural decision graphs, and they can dramatically reduce runtime complexity and computation costs of CNNs, while maintaining or even increasing accuracy. Functions of SplineNets are both dynamic (i.e., conditioned on the input) and hierarchical (i.e., conditioned on the computational path). SplineNets employ a unified loss function with a desired level of smoothness over both the network and decision parameters, while allowing for sparse activation of a subset of nodes for individual samples. In particular, we embed infinitely many function weights (e.g. filters) on smooth, low dimensional manifolds parameterized by compact B-splines, which are indexed by a position parameter. Instead of sampling from a categorical distribution to pick a branch, samples choose a continuous position to pick a function weight. We further show that by maximizing the mutual information between spline positions and class labels, the network can be optimally utilized and specialized for classification tasks. Experiments show that our approach can significantly increase the accuracy of ResNets with negligible cost in speed, matching the precision of a 110 level ResNet with a 32 level SplineNet.

arXiv:1810.12552공식 코드 · Papers with Code

3D Traffic Simulation for Autonomous Vehicles in Unity and Python

Over the recent years, there has been an explosion of studies on autonomous vehicles. Many collected large amount of data from human drivers. However, compared to the tedious data collection approach, building a virtual simulation of traffic makes the autonomous vehicle research more flexible, time-saving, and scalable. Our work features a 3D simulation that takes in real time position information parsed from street cameras. The simulation can easily switch between a global bird view of the traffic and a local perspective of a car. It can also filter out certain objects in its customized camera, creating various channels for objects of different categories. This provides alternative supervised or unsupervised ways to train deep neural networks. Another advantage of the 3D simulation is its conformation to physical laws. Its naturalness to accelerate and collide prepares the system for potential deep reinforcement learning needs.

arXiv:1810.09568공식 코드 · Papers with Code

Learning Probabilistic Trajectory Models of Aircraft in Terminal Airspace from Position Data

Models for predicting aircraft motion are an important component of modern aeronautical systems. These models help aircraft plan collision avoidance maneuvers and help conduct offline performance and safety analyses. In this article, we develop a method for learning a probabilistic generative model of aircraft motion in terminal airspace, the controlled airspace surrounding a given airport. The method fits the model based on a historical dataset of radar-based position measurements of aircraft landings and takeoffs at that airport. We find that the model generates realistic trajectories, provides accurate predictions, and captures the statistical properties of aircraft trajectories. Furthermore, the model trains quickly, is compact, and allows for efficient real-time inference.