October 17, 2019

2962 words 14 mins read

Paper Group ANR 747

PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction. Finding Solutions to Generative Adversarial Privacy. Generalization Bounds for Uniformly Stable Algorithms. Neural Machine Translation for Bilingually Scarce Scenarios: A Deep Multi-task Learning Approach. Evaluating ResNeXt Model Architectur …

PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction


Title	PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction
Authors	Wei Dong, Qiuyuan Wang, Xin Wang, Hongbin Zha
Abstract	We propose a novel 3D spatial representation for data fusion and scene reconstruction. Probabilistic Signed Distance Function (Probabilistic SDF, PSDF) is proposed to depict uncertainties in the 3D space. It is modeled by a joint distribution describing SDF value and its inlier probability, reflecting input data quality and surface geometry. A hybrid data structure involving voxel, surfel, and mesh is designed to fully exploit the advantages of various prevalent 3D representations. Connected by PSDF, these components reasonably cooperate in a consistent frame- work. Given sequential depth measurements, PSDF can be incrementally refined with less ad hoc parametric Bayesian updating. Supported by PSDF and the efficient 3D data representation, high-quality surfaces can be extracted on-the-fly, and in return contribute to reliable data fu- sion using the geometry information. Experiments demonstrate that our system reconstructs scenes with higher model quality and lower redundancy, and runs faster than existing online mesh generation systems.
Tasks
Published	2018-07-29
URL	http://arxiv.org/abs/1807.11034v1
PDF	http://arxiv.org/pdf/1807.11034v1.pdf
PWC	https://paperswithcode.com/paper/psdf-fusion-probabilistic-signed-distance
Repo
Framework

Finding Solutions to Generative Adversarial Privacy


Title	Finding Solutions to Generative Adversarial Privacy
Authors	Dae Hyun Kim, Taeyoung Kong, Seungbin Jeong
Abstract	We present heuristics for solving the maximin problem induced by the generative adversarial privacy setting for linear and convolutional neural network (CNN) adversaries. In the linear adversary setting, we present a greedy algorithm for approximating the optimal solution for the privatizer, which performs better as the number of instances increases. We also provide an analysis of the algorithm to show that it not only removes the features most correlated with the private label first, but also preserves the prediction accuracy of public labels that are sufficiently independent of the features that are relevant to the private label. In the CNN adversary setting, we present a method of hiding selected information from the adversary while preserving the others through alternately optimizing the goals of the privatizer and the adversary using neural network backpropagation. We experimentally show that our method succeeds on a fixed adversary.
Tasks
Published	2018-10-04
URL	http://arxiv.org/abs/1810.02069v1
PDF	http://arxiv.org/pdf/1810.02069v1.pdf
PWC	https://paperswithcode.com/paper/finding-solutions-to-generative-adversarial
Repo
Framework

Generalization Bounds for Uniformly Stable Algorithms


Title	Generalization Bounds for Uniformly Stable Algorithms
Authors	Vitaly Feldman, Jan Vondrak
Abstract	Uniform stability of a learning algorithm is a classical notion of algorithmic stability introduced to derive high-probability bounds on the generalization error (Bousquet and Elisseeff, 2002). Specifically, for a loss function with range bounded in $[0,1]$, the generalization error of a $\gamma$-uniformly stable learning algorithm on $n$ samples is known to be within $O((\gamma +1/n) \sqrt{n \log(1/\delta)})$ of the empirical error with probability at least $1-\delta$. Unfortunately, this bound does not lead to meaningful generalization bounds in many common settings where $\gamma \geq 1/\sqrt{n}$. At the same time the bound is known to be tight only when $\gamma = O(1/n)$. We substantially improve generalization bounds for uniformly stable algorithms without making any additional assumptions. First, we show that the bound in this setting is $O(\sqrt{(\gamma + 1/n) \log(1/\delta)})$ with probability at least $1-\delta$. In addition, we prove a tight bound of $O(\gamma^2 + 1/n)$ on the second moment of the estimation error. The best previous bound on the second moment is $O(\gamma + 1/n)$. Our proofs are based on new analysis techniques and our results imply substantially stronger generalization guarantees for several well-studied algorithms.
Tasks
Published	2018-12-24
URL	http://arxiv.org/abs/1812.09859v2
PDF	http://arxiv.org/pdf/1812.09859v2.pdf
PWC	https://paperswithcode.com/paper/generalization-bounds-for-uniformly-stable
Repo
Framework

Neural Machine Translation for Bilingually Scarce Scenarios: A Deep Multi-task Learning Approach


Title	Neural Machine Translation for Bilingually Scarce Scenarios: A Deep Multi-task Learning Approach
Authors	Poorya Zaremoodi, Gholamreza Haffari
Abstract	Neural machine translation requires large amounts of parallel training text to learn a reasonable-quality translation model. This is particularly inconvenient for language pairs for which enough parallel text is not available. In this paper, we use monolingual linguistic resources in the source side to address this challenging problem based on a multi-task learning approach. More specifically, we scaffold the machine translation task on auxiliary tasks including semantic parsing, syntactic parsing, and named-entity recognition. This effectively injects semantic and/or syntactic knowledge into the translation model, which would otherwise require a large amount of training bitext. We empirically evaluate and show the effectiveness of our multi-task learning approach on three translation tasks: English-to-French, English-to-Farsi, and English-to-Vietnamese.
Tasks	Machine Translation, Multi-Task Learning, Named Entity Recognition, Semantic Parsing
Published	2018-05-11
URL	http://arxiv.org/abs/1805.04237v1
PDF	http://arxiv.org/pdf/1805.04237v1.pdf
PWC	https://paperswithcode.com/paper/neural-machine-translation-for-bilingually
Repo
Framework

Evaluating ResNeXt Model Architecture for Image Classification


Title	Evaluating ResNeXt Model Architecture for Image Classification
Authors	Saifuddin Hitawala
Abstract	In recent years, deep learning methods have been successfully applied to image classification tasks. Many such deep neural networks exist today that can easily differentiate cats from dogs. One such model is the ResNeXt model that uses a homogeneous, multi-branch architecture for image classification. This paper aims at implementing and evaluating the ResNeXt model architecture on subsets of the CIFAR-10 dataset. It also tweaks the original ResNeXt hyper-parameters such as cardinality, depth and base-width and compares the performance of the modified model with the original. Analysis of the experiments performed in this paper show that a slight decrease in depth or base-width does not affect the performance of the model much leading to comparable results.
Tasks	Image Classification
Published	2018-05-09
URL	http://arxiv.org/abs/1805.08700v1
PDF	http://arxiv.org/pdf/1805.08700v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-resnext-model-architecture-for
Repo
Framework

Visual Relationship Prediction via Label Clustering and Incorporation of Depth Information


Title	Visual Relationship Prediction via Label Clustering and Incorporation of Depth Information
Authors	Hsuan-Kung Yang, An-Chieh Cheng, Kuan-Wei Ho, Tsu-Jui Fu, Chun-Yi Lee
Abstract	In this paper, we investigate the use of an unsupervised label clustering technique and demonstrate that it enables substantial improvements in visual relationship prediction accuracy on the Person in Context (PIC) dataset. We propose to group object labels with similar patterns of relationship distribution in the dataset into fewer categories. Label clustering not only mitigates both the large classification space and class imbalance issues, but also potentially increases data samples for each clustered category. We further propose to incorporate depth information as an additional feature into the instance segmentation model. The additional depth prediction path supplements the relationship prediction model in a way that bounding boxes or segmentation masks are unable to deliver. We have rigorously evaluated the proposed techniques and performed various ablation analysis to validate the benefits of them.
Tasks	Depth Estimation, Instance Segmentation, Semantic Segmentation
Published	2018-09-09
URL	http://arxiv.org/abs/1809.02945v1
PDF	http://arxiv.org/pdf/1809.02945v1.pdf
PWC	https://paperswithcode.com/paper/visual-relationship-prediction-via-label
Repo
Framework

GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs


Title	GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
Authors	Jiani Zhang, Xingjian Shi, Junyuan Xie, Hao Ma, Irwin King, Dit-Yan Yeung
Abstract	We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head attention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to control each attention head’s importance. We demonstrate the effectiveness of GaAN on the inductive node classification problem. Moreover, with GaAN as a building block, we construct the Graph Gated Recurrent Unit (GGRU) to address the traffic speed forecasting problem. Extensive experiments on three real-world datasets show that our GaAN framework achieves state-of-the-art results on both tasks.
Tasks	Node Classification
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07294v1
PDF	http://arxiv.org/pdf/1803.07294v1.pdf
PWC	https://paperswithcode.com/paper/gaan-gated-attention-networks-for-learning-on
Repo
Framework

Hierarchical Structured Model for Fine-to-coarse Manifesto Text Analysis


Title	Hierarchical Structured Model for Fine-to-coarse Manifesto Text Analysis
Authors	Shivashankar Subramanian, Trevor Cohn, Timothy Baldwin
Abstract	Election manifestos document the intentions, motives, and views of political parties. They are often used for analysing a party’s fine-grained position on a particular issue, as well as for coarse-grained positioning of a party on the left–right spectrum. In this paper we propose a two-stage model for automatically performing both levels of analysis over manifestos. In the first step we employ a hierarchical multi-task structured deep model to predict fine- and coarse-grained positions, and in the second step we perform post-hoc calibration of coarse-grained positions using probabilistic soft logic. We empirically show that the proposed model outperforms state-of-art approaches at both granularities using manifestos from twelve countries, written in ten different languages.
Tasks	Calibration
Published	2018-05-08
URL	http://arxiv.org/abs/1805.02823v1
PDF	http://arxiv.org/pdf/1805.02823v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-structured-model-for-fine-to
Repo
Framework

Anomaly and Change Detection in Graph Streams through Constant-Curvature Manifold Embeddings


Title	Anomaly and Change Detection in Graph Streams through Constant-Curvature Manifold Embeddings
Authors	Daniele Zambon, Lorenzo Livi, Cesare Alippi
Abstract	Mapping complex input data into suitable lower dimensional manifolds is a common procedure in machine learning. This step is beneficial mainly for two reasons: (1) it reduces the data dimensionality and (2) it provides a new data representation possibly characterised by convenient geometric properties. Euclidean spaces are by far the most widely used embedding spaces, thanks to their well-understood structure and large availability of consolidated inference methods. However, recent research demonstrated that many types of complex data (e.g., those represented as graphs) are actually better described by non-Euclidean geometries. Here, we investigate how embedding graphs on constant-curvature manifolds (hyper-spherical and hyperbolic manifolds) impacts on the ability to detect changes in sequences of attributed graphs. The proposed methodology consists in embedding graphs into a geometric space and perform change detection there by means of conventional methods for numerical streams. The curvature of the space is a parameter that we learn to reproduce the geometry of the original application-dependent graph space. Preliminary experimental results show the potential capability of representing graphs by means of curved manifold, in particular for change and anomaly detection problems.
Tasks	Anomaly Detection
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01360v1
PDF	http://arxiv.org/pdf/1805.01360v1.pdf
PWC	https://paperswithcode.com/paper/anomaly-and-change-detection-in-graph-streams
Repo
Framework

Learning to Listen, Read, and Follow: Score Following as a Reinforcement Learning Game


Title	Learning to Listen, Read, and Follow: Score Following as a Reinforcement Learning Game
Authors	Matthias Dorfer, Florian Henkel, Gerhard Widmer
Abstract	Score following is the process of tracking a musical performance (audio) with respect to a known symbolic representation (a score). We start this paper by formulating score following as a multimodal Markov Decision Process, the mathematical foundation for sequential decision making. Given this formal definition, we address the score following task with state-of-the-art deep reinforcement learning (RL) algorithms such as synchronous advantage actor critic (A2C). In particular, we design multimodal RL agents that simultaneously learn to listen to music, read the scores from images of sheet music, and follow the audio along in the sheet, in an end-to-end fashion. All this behavior is learned entirely from scratch, based on a weak and potentially delayed reward signal that indicates to the agent how close it is to the correct position in the score. Besides discussing the theoretical advantages of this learning paradigm, we show in experiments that it is in fact superior compared to previously proposed methods for score following in raw sheet music images.
Tasks	Decision Making
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06391v1
PDF	http://arxiv.org/pdf/1807.06391v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-listen-read-and-follow-score
Repo
Framework

Dealing with Ambiguity in Robotic Grasping via Multiple Predictions


Title	Dealing with Ambiguity in Robotic Grasping via Multiple Predictions
Authors	Ghazal Ghazaei, Iro Laina, Christian Rupprecht, Federico Tombari, Nassir Navab, Kianoush Nazarpour
Abstract	Humans excel in grasping and manipulating objects because of their life-long experience and knowledge about the 3D shape and weight distribution of objects. However, the lack of such intuition in robots makes robotic grasping an exceptionally challenging task. There are often several equally viable options of grasping an object. However, this ambiguity is not modeled in conventional systems that estimate a single, optimal grasp position. We propose to tackle this problem by simultaneously estimating multiple grasp poses from a single RGB image of the target object. Further, we reformulate the problem of robotic grasping by replacing conventional grasp rectangles with grasp belief maps, which hold more precise location information than a rectangle and account for the uncertainty inherent to the task. We augment a fully convolutional neural network with a multiple hypothesis prediction model that predicts a set of grasp hypotheses in under 60ms, which is critical for real-time robotic applications. The grasp detection accuracy reaches over 90% for unseen objects, outperforming the current state of the art on this task.
Tasks	Robotic Grasping
Published	2018-11-02
URL	http://arxiv.org/abs/1811.00793v1
PDF	http://arxiv.org/pdf/1811.00793v1.pdf
PWC	https://paperswithcode.com/paper/dealing-with-ambiguity-in-robotic-grasping
Repo
Framework

Densely Supervised Grasp Detector (DSGD)


Title	Densely Supervised Grasp Detector (DSGD)
Authors	Umar Asif, Jianbin Tang, Stefan Harrer
Abstract	This paper presents Densely Supervised Grasp Detector (DSGD), a deep learning framework which combines CNN structures with layer-wise feature fusion and produces grasps and their confidence scores at different levels of the image hierarchy (i.e., global-, region-, and pixel-levels). % Specifically, at the global-level, DSGD uses the entire image information to predict a grasp. At the region-level, DSGD uses a region proposal network to identify salient regions in the image and predicts a grasp for each salient region. At the pixel-level, DSGD uses a fully convolutional network and predicts a grasp and its confidence at every pixel. % During inference, DSGD selects the most confident grasp as the output. This selection from hierarchically generated grasp candidates overcomes limitations of the individual models. % DSGD outperforms state-of-the-art methods on the Cornell grasp dataset in terms of grasp accuracy. % Evaluation on a multi-object dataset and real-world robotic grasping experiments show that DSGD produces highly stable grasps on a set of unseen objects in new environments. It achieves 97% grasp detection accuracy and 90% robotic grasping success rate with real-time inference speed.
Tasks	Robotic Grasping
Published	2018-10-01
URL	http://arxiv.org/abs/1810.03962v2
PDF	http://arxiv.org/pdf/1810.03962v2.pdf
PWC	https://paperswithcode.com/paper/densely-supervised-grasp-detector-dsgd
Repo
Framework

Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences


Title	Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences
Authors	Jasper van der Waa, Jurriaan van Diggelen, Karel van den Bosch, Mark Neerincx
Abstract	Machine Learning models become increasingly proficient in complex tasks. However, even for experts in the field, it can be difficult to understand what the model learned. This hampers trust and acceptance, and it obstructs the possibility to correct the model. There is therefore a need for transparency of machine learning models. The development of transparent classification models has received much attention, but there are few developments for achieving transparent Reinforcement Learning (RL) models. In this study we propose a method that enables a RL agent to explain its behavior in terms of the expected consequences of state transitions and outcomes. First, we define a translation of states and actions to a description that is easier to understand for human users. Second, we developed a procedure that enables the agent to obtain the consequences of a single action, as well as its entire policy. The method calculates contrasts between the consequences of a policy derived from a user query, and of the learned policy of the agent. Third, a format for generating explanations was constructed. A pilot survey study was conducted to explore preferences of users for different explanation properties. Results indicate that human users tend to favor explanations about policy rather than about single actions.
Tasks
Published	2018-07-23
URL	http://arxiv.org/abs/1807.08706v1
PDF	http://arxiv.org/pdf/1807.08706v1.pdf
PWC	https://paperswithcode.com/paper/contrastive-explanations-for-reinforcement
Repo
Framework

Student’s t-Generative Adversarial Networks


Title	Student’s t-Generative Adversarial Networks
Authors	Jinxuan Sun, Guoqiang Zhong, Yang Chen, Yongbin Liu, Tao Li, Zhongwen Guo
Abstract	Generative Adversarial Networks (GANs) have a great performance in image generation, but they need a large scale of data to train the entire framework, and often result in nonsensical results. We propose a new method referring to conditional GAN, which equipments the latent noise with mixture of Student’s t-distribution with attention mechanism in addition to class information. Student’s t-distribution has long tails that can provide more diversity to the latent noise. Meanwhile, the discriminator in our model implements two tasks simultaneously, judging whether the images come from the true data distribution, and identifying the class of each generated images. The parameters of the mixture model can be learned along with those of GANs. Moreover, we mathematically prove that any multivariate Student’s t-distribution can be obtained by a linear transformation of a normal multivariate Student’s t-distribution. Experiments comparing the proposed method with typical GAN, DeliGAN and DCGAN indicate that, our method has a great performance on generating diverse and legible objects with limited data.
Tasks	Image Generation
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02132v1
PDF	http://arxiv.org/pdf/1811.02132v1.pdf
PWC	https://paperswithcode.com/paper/students-t-generative-adversarial-networks
Repo
Framework

FastOrient: Lightweight Computer Vision for Wrist Control in Assistive Robotic Grasping


Title	FastOrient: Lightweight Computer Vision for Wrist Control in Assistive Robotic Grasping
Authors	Mireia Ruiz Maymo, Ali Shafti, A. Aldo Faisal
Abstract	Wearable and Assistive robotics for human grasp support are broadly either tele-operated robotic arms or act through orthotic control of a paralyzed user’s hand. Such devices require correct orientation for successful and efficient grasping. In many human-robot assistive settings, the end-user is required to explicitly control the many degrees of freedom making effective or efficient control problematic. Here we are demonstrating the off-loading of low-level control of assistive robotics and active orthotics, through automatic end-effector orientation control for grasping. This paper describes a compact algorithm implementing fast computer vision techniques to obtain the orientation of the target object to be grasped, by segmenting the images acquired with a camera positioned on top of the end-effector of the robotic device. The rotation needed that optimises grasping is directly computed from the object’s orientation. The algorithm has been evaluated in 6 different scene backgrounds and end-effector approaches to 26 different objects. 94.8% of the objects were detected in all backgrounds. Grasping of the object was achieved in 91.1% of the cases and has been evaluated with a robot simulator confirming the performance of the algorithm.
Tasks	Robotic Grasping
Published	2018-07-22
URL	http://arxiv.org/abs/1807.08275v1
PDF	http://arxiv.org/pdf/1807.08275v1.pdf
PWC	https://paperswithcode.com/paper/fastorient-lightweight-computer-vision-for
Repo
Framework