January 30, 2020

3191 words 15 mins read

Paper Group ANR 442

Unsupervised Deformable Image Registration Using Cycle-Consistent CNN. Graph-Hist: Graph Classification from Latent Feature Histograms With Application to Bot Detection. Deteção de estruturas permanentes a partir de dados de séries temporais Sentinel 1 e 2. Beyond The Wall Street Journal: Anchoring and Comparing Discourse Signals across Genres. Fus …

Unsupervised Deformable Image Registration Using Cycle-Consistent CNN


Title	Unsupervised Deformable Image Registration Using Cycle-Consistent CNN
Authors	Boah Kim, Jieun Kim, June-Goo Lee, Dong Hwan Kim, Seong Ho Park, Jong Chul Ye
Abstract	Medical image registration is one of the key processing steps for biomedical image analysis such as cancer diagnosis. Recently, deep learning based supervised and unsupervised image registration methods have been extensively studied due to its excellent performance in spite of ultra-fast computational time compared to the classical approaches. In this paper, we present a novel unsupervised medical image registration method that trains deep neural network for deformable registration of 3D volumes using a cycle-consistency. Thanks to the cycle consistency, the proposed deep neural networks can take diverse pair of image data with severe deformation for accurate registration. Experimental results using multiphase liver CT images demonstrate that our method provides very precise 3D image registration within a few seconds, resulting in more accurate cancer size estimation.
Tasks	Image Registration, Medical Image Registration
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01319v1
PDF	https://arxiv.org/pdf/1907.01319v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-deformable-image-registration
Repo
Framework

Graph-Hist: Graph Classification from Latent Feature Histograms With Application to Bot Detection


Title	Graph-Hist: Graph Classification from Latent Feature Histograms With Application to Bot Detection
Authors	Thomas Magelinski, David Beskow, Kathleen M. Carley
Abstract	Neural networks are increasingly used for graph classification in a variety of contexts. Social media is a critical application area in this space, however the characteristics of social media graphs differ from those seen in most popular benchmark datasets. Social networks tend to be large and sparse, while benchmarks are small and dense. Classically, large and sparse networks are analyzed by studying the distribution of local properties. Inspired by this, we introduce Graph-Hist: an end-to-end architecture that extracts a graph’s latent local features, bins nodes together along 1-D cross sections of the feature space, and classifies the graph based on this multi-channel histogram. We show that Graph-Hist improves state of the art performance on true social media benchmark datasets, while still performing well on other benchmarks. Finally, we demonstrate Graph-Hist’s performance by conducting bot detection in social media. While sophisticated bot and cyborg accounts increasingly evade traditional detection methods, they leave artificial artifacts in their conversational graph that are detected through graph classification. We apply Graph-Hist to classify these conversational graphs. In the process, we confirm that social media graphs are different than most baselines and that Graph-Hist outperforms existing bot-detection models.
Tasks	Graph Classification
Published	2019-10-02
URL	https://arxiv.org/abs/1910.01180v1
PDF	https://arxiv.org/pdf/1910.01180v1.pdf
PWC	https://paperswithcode.com/paper/graph-hist-graph-classification-from-latent
Repo
Framework

Deteção de estruturas permanentes a partir de dados de séries temporais Sentinel 1 e 2


Title	Deteção de estruturas permanentes a partir de dados de séries temporais Sentinel 1 e 2
Authors	André Neves, Carlos Damásio, João Pires, Fernando Birra
Abstract	Mapping structures such as settlements, roads, individual houses and any other types of artificial structures is of great importance for the analysis of urban growth, masking, image alignment and, especially in the studied use case, the definition of Fuel Management Networks (FGC), which protect buildings from forest fires. Current cartography has a low generation frequency and their resolution may not be suitable for extracting small structures such as small settlements or roads, which may lack forest fire protection. In this paper, we use time series data, extracted from Sentinel-1 and 2 constellations, over Santar'em, Ma\c{c}~ao, to explore the detection of permanent structures at a resolution of 10 by 10 meters. For this purpose, a XGBoost classification model is trained with 133 attributes extracted from the time series from all the bands, including normalized radiometric indices. The results show that the use of time series data increases the accuracy of the extraction of permanent structures when compared using only static data, using multitemporal data also increases the number of detected roads. In general, the final result has a permanent structure mapping with a higher resolution than state of the art settlement maps, small structures and roads are also more accurately represented. Regarding the use case, by using our final map for the creation of FGC it is possible to simplify and accelerate the process of delimitation of the official FGC.
Tasks	Time Series
Published	2019-12-11
URL	https://arxiv.org/abs/1912.10799v1
PDF	https://arxiv.org/pdf/1912.10799v1.pdf
PWC	https://paperswithcode.com/paper/detecao-de-estruturas-permanentes-a-partir-de
Repo
Framework

Beyond The Wall Street Journal: Anchoring and Comparing Discourse Signals across Genres


Title	Beyond The Wall Street Journal: Anchoring and Comparing Discourse Signals across Genres
Authors	Yang Liu
Abstract	Recent research on discourse relations has found that they are cued not only by discourse markers (DMs) but also by other textual signals and that signaling information is indicative of genres. While several corpora exist with discourse relation signaling information such as the Penn Discourse Treebank (PDTB, Prasad et al. 2008) and the Rhetorical Structure Theory Signalling Corpus (RST-SC, Das and Taboada 2018), they both annotate the Wall Street Journal (WSJ) section of the Penn Treebank (PTB, Marcus et al. 1993), which is limited to the news domain. Thus, this paper adapts the signal identification and anchoring scheme (Liu and Zeldes, 2019) to three more genres, examines the distribution of signaling devices across relations and genres, and provides a taxonomy of indicative signals found in this dataset.
Tasks
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00516v1
PDF	https://arxiv.org/pdf/1909.00516v1.pdf
PWC	https://paperswithcode.com/paper/beyond-the-wall-street-journal-anchoring-and-1
Repo
Framework

Fusing Body Posture with Facial Expressions for Joint Recognition of Affect in Child-Robot Interaction


Title	Fusing Body Posture with Facial Expressions for Joint Recognition of Affect in Child-Robot Interaction
Authors	Panagiotis P. Filntisis, Niki Efthymiou, Petros Koutras, Gerasimos Potamianos, Petros Maragos
Abstract	In this paper we address the problem of multi-cue affect recognition in challenging scenarios such as child-robot interaction. Towards this goal we propose a method for automatic recognition of affect that leverages body expressions alongside facial ones, as opposed to traditional methods that typically focus only on the latter. Our deep-learning based method uses hierarchical multi-label annotations and multi-stage losses, can be trained both jointly and separately, and offers us computational models for both individual modalities, as well as for the whole body emotion. We evaluate our method on a challenging child-robot interaction database of emotional expressions collected by us, as well as on the GEMEP public database of acted emotions by adults, and show that the proposed method achieves significantly better results than facial-only expression baselines.
Tasks
Published	2019-01-07
URL	https://arxiv.org/abs/1901.01805v3
PDF	https://arxiv.org/pdf/1901.01805v3.pdf
PWC	https://paperswithcode.com/paper/fusing-body-posture-with-facial-expressions
Repo
Framework

Graph Hierarchical Convolutional Recurrent Neural Network (GHCRNN) for Vehicle Condition Prediction


Title	Graph Hierarchical Convolutional Recurrent Neural Network (GHCRNN) for Vehicle Condition Prediction
Authors	Mingming Lu, Kunfang Zhang, Haiying Liu, Naixue Xiong
Abstract	The prediction of urban vehicle flow and speed can greatly facilitate people’s travel, and also can provide reasonable advice for the decision-making of relevant government departments. However, due to the spatial, temporal and hierarchy of vehicle flow and many influencing factors such as weather, it is difficult to prediction. Most of the existing research methods are to extract spatial structure information on the road network and extract time series information from the historical data. However, when extracting spatial features, these methods have higher time and space complexity, and incorporate a lot of noise. It is difficult to apply on large graphs, and only considers the influence of surrounding connected road nodes on the central node, ignoring a very important hierarchical relationship, namely, similar information of similar node features and road network structures. In response to these problems, this paper proposes the Graph Hierarchical Convolutional Recurrent Neural Network (GHCRNN) model. The model uses GCN (Graph Convolutional Networks) to extract spatial feature, GRU (Gated Recurrent Units) to extract temporal feature, and uses the learnable Pooling to extract hierarchical information, eliminate redundant information and reduce complexity. Applying this model to the vehicle flow and speed data of Shenzhen and Los Angeles has been well verified, and the time and memory consumption are effectively reduced under the compared precision.
Tasks	Decision Making, Time Series
Published	2019-03-12
URL	http://arxiv.org/abs/1903.06261v1
PDF	http://arxiv.org/pdf/1903.06261v1.pdf
PWC	https://paperswithcode.com/paper/graph-hierarchical-convolutional-recurrent
Repo
Framework

AspeRa: Aspect-based Rating Prediction Model


Title	AspeRa: Aspect-based Rating Prediction Model
Authors	Sergey I. Nikolenko, Elena Tutubalina, Valentin Malykh, Ilya Shenbin, Anton Alekseev
Abstract	We propose a novel end-to-end Aspect-based Rating Prediction model (AspeRa) that estimates user rating based on review texts for the items and at the same time discovers coherent aspects of reviews that can be used to explain predictions or profile users. The AspeRa model uses max-margin losses for joint item and user embedding learning and a dual-headed architecture; it significantly outperforms recently proposed state-of-the-art models such as DeepCoNN, HFT, NARRE, and TransRev on two real world data sets of user reviews. With qualitative examination of the aspects and quantitative evaluation of rating prediction models based on these aspects, we show how aspect embeddings can be used in a recommender system.
Tasks	Recommendation Systems
Published	2019-01-23
URL	http://arxiv.org/abs/1901.07829v1
PDF	http://arxiv.org/pdf/1901.07829v1.pdf
PWC	https://paperswithcode.com/paper/aspera-aspect-based-rating-prediction-model
Repo
Framework

Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics


Title	Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
Authors	Dawit Belayneh, Federico Carminati, Amir Farbin, Benjamin Hooberman, Gulrukh Khattak, Miaoyuan Liu, Junze Liu, Dominick Olivito, Vitória Barin Pacela, Maurizio Pierini, Alexander Schwing, Maria Spiropulu, Sofia Vallecorsa, Jean-Roch Vlimant, Wei Wei, Matt Zhang
Abstract	Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of particles produced in high-energy physics collisions. We train neural networks on shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.
Tasks
Published	2019-12-14
URL	https://arxiv.org/abs/1912.06794v3
PDF	https://arxiv.org/pdf/1912.06794v3.pdf
PWC	https://paperswithcode.com/paper/calorimetry-with-deep-learning-particle
Repo
Framework

Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?


Title	Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?
Authors	Alfred Laugros, Alice Caplier, Matthieu Ospici
Abstract	Neural Networks have been shown to be sensitive to common perturbations such as blur, Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious corruptions called adversarial examples. The adversarial examples study has recently become very popular and it sometimes even reduces the term “adversarial robustness” to the term “robustness”. Yet, we do not know to what extent the adversarial robustness is related to the global robustness. Similarly, we do not know if a robustness to various common perturbations such as translations or contrast losses for instance, could help with adversarial corruptions. We intend to study the links between the robustnesses of neural networks to both perturbations. With our experiments, we provide one of the first benchmark designed to estimate the robustness of neural networks to common perturbations. We show that increasing the robustness to carefully selected common perturbations, can make neural networks more robust to unseen common perturbations. We also prove that adversarial robustness and robustness to common perturbations are independent. Our results make us believe that neural network robustness should be addressed in a broader sense.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.02436v2
PDF	https://arxiv.org/pdf/1909.02436v2.pdf
PWC	https://paperswithcode.com/paper/are-adversarial-robustness-and-common
Repo
Framework

Iris R-CNN: Accurate Iris Segmentation in Non-cooperative Environment


Title	Iris R-CNN: Accurate Iris Segmentation in Non-cooperative Environment
Authors	Chunyang Feng, Yufeng Sun, Xin Li
Abstract	Despite the significant advances in iris segmentation, accomplishing accurate iris segmentation in non-cooperative environment remains a grand challenge. In this paper, we present a deep learning framework, referred to as Iris R-CNN, to offer superior accuracy for iris segmentation. The proposed framework is derived from Mask R-CNN, and several novel techniques are proposed to carefully explore the unique characteristics of iris. First, we propose two novel networks: (i) Double-Circle Region Proposal Network (DC-RPN), and (ii) Double-Circle Classification and Regression Network (DC-CRN) to take into account the iris and pupil circles to maximize the accuracy for iris segmentation. Second, we propose a novel normalization scheme for Regions of Interest (RoIs) to facilitate a radically new pooling operation over a double-circle region. Experimental results on two challenging iris databases, UBIRIS.v2 and MICHE, demonstrate the superior accuracy of the proposed approach over other state-of-the-art methods.
Tasks	Iris Segmentation
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10140v1
PDF	http://arxiv.org/pdf/1903.10140v1.pdf
PWC	https://paperswithcode.com/paper/iris-r-cnn-accurate-iris-segmentation-in-non
Repo
Framework

Refining 6D Object Pose Predictions using Abstract Render-and-Compare


Title	Refining 6D Object Pose Predictions using Abstract Render-and-Compare
Authors	Arul Selvam Periyasamy, Max Schwarz, Sven Behnke
Abstract	Robotic systems often require precise scene analysis capabilities, especially in unstructured, cluttered situations, as occurring in human-made environments. While current deep-learning based methods yield good estimates of object poses, they often struggle with large amounts of occlusion and do not take inter-object effects into account. Vision as inverse graphics is a promising concept for detailed scene analysis. A key element for this idea is a method for inferring scene parameter updates from the rasterized 2D scene. However, the rasterization process is notoriously difficult to invert, both due to the projection and occlusion process, but also due to secondary effects such as lighting or reflections. We propose to remove the latter from the process by mapping the rasterized image into an abstract feature space learned in a self-supervised way from pixel correspondences. Using only a light-weight inverse rendering module, this allows us to refine 6D object pose estimations in highly cluttered scenes by optimizing a simple pixel-wise difference in the abstract image representation. We evaluate our approach on the challenging YCB-Video dataset, where it yields large improvements and demonstrates a large basin of attraction towards the correct object poses.
Tasks
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03412v1
PDF	https://arxiv.org/pdf/1910.03412v1.pdf
PWC	https://paperswithcode.com/paper/refining-6d-object-pose-predictions-using
Repo
Framework

Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation


Title	Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation
Authors	Matthias Sperber, Graham Neubig, Jan Niehues, Alex Waibel
Abstract	Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts. Several recent works have shown the feasibility of collapsing the cascade into a single, direct model that can be trained in an end-to-end fashion on a corpus of translated speech. However, experiments are inconclusive on whether the cascade or the direct model is stronger, and have only been conducted under the unrealistic assumption that both are trained on equal amounts of data, ignoring other available speech recognition and machine translation corpora. In this paper, we demonstrate that direct speech translation models require more data to perform well than cascaded models, and while they allow including auxiliary data through multi-task training, they are poor at exploiting such data, putting them at a severe disadvantage. As a remedy, we propose the use of end-to-end trainable models with two attention mechanisms, the first establishing source speech to source text alignments, the second modeling source to target text alignment. We show that such models naturally decompose into multi-task-trainable recognition and translation tasks and propose an attention-passing technique that alleviates error propagation issues in a previous formulation of a model with two attention stages. Our proposed model outperforms all examined baselines and is able to exploit auxiliary training data much more effectively than direct attentional models.
Tasks	Machine Translation, Speech Recognition
Published	2019-04-15
URL	http://arxiv.org/abs/1904.07209v1
PDF	http://arxiv.org/pdf/1904.07209v1.pdf
PWC	https://paperswithcode.com/paper/attention-passing-models-for-robust-and-data
Repo
Framework

Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings


Title	Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings
Authors	Bao Xin Chen, Raghavender Sahdev, Dekun Wu, Xing Zhao, Manos Papagelis, John K. Tsotsos
Abstract	Scene Classification has been addressed with numerous techniques in computer vision literature. However, with the increasing number of scene classes in datasets in the field, it has become difficult to achieve high accuracy in the context of robotics. In this paper, we implement an approach which combines traditional deep learning techniques with natural language processing methods to generate a word embedding based Scene Classification algorithm. We use the key idea that context (objects in the scene) of an image should be representative of the scene label meaning a group of objects could assist to predict the scene class. Objects present in the scene are represented by vectors and the images are re-classified based on the objects present in the scene to refine the initial classification by a Convolutional Neural Network (CNN). In our approach we address indoor Scene Classification task using a model trained with a reduced pre-processed version of the Places365 dataset and an empirical analysis is done on a real-world dataset that we built by capturing image sequences using a GoPro camera. We also report results obtained on a subset of the Places365 dataset using our approach and additionally show a deployment of our approach on a robot operating in a real-world environment.
Tasks	Scene Classification, Word Embeddings
Published	2019-08-18
URL	https://arxiv.org/abs/1908.06422v1
PDF	https://arxiv.org/pdf/1908.06422v1.pdf
PWC	https://paperswithcode.com/paper/scene-classification-in-indoor-environments
Repo
Framework

Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without


Title	Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without
Authors	Sébastien Bubeck, Yuanzhi Li, Yuval Peres, Mark Sellke
Abstract	We consider the non-stochastic version of the (cooperative) multi-player multi-armed bandit problem. The model assumes no communication at all between the players, and furthermore when two (or more) players select the same action this results in a maximal loss. We prove the first $\sqrt{T}$-type regret guarantee for this problem, under the feedback model where collisions are announced to the colliding players. Such a bound was not known even for the simpler stochastic version. We also prove the first sublinear guarantee for the feedback model where collision information is not available, namely $T^{1-\frac{1}{2m}}$ where $m$ is the number of players.
Tasks	Multi-Armed Bandits
Published	2019-04-28
URL	http://arxiv.org/abs/1904.12233v2
PDF	http://arxiv.org/pdf/1904.12233v2.pdf
PWC	https://paperswithcode.com/paper/non-stochastic-multi-player-multi-armed
Repo
Framework

Fiduciary Bandits


Title	Fiduciary Bandits
Authors	Gal Bahar, Omer Ben-Porat, Kevin Leyton-Brown, Moshe Tennenholtz
Abstract	Recommendation systems often face exploration-exploitation tradeoffs: the system can only learn about the desirability of new options by recommending them to some user. Such systems can thus be modeled as multi-armed bandit settings; however, users are self-interested and cannot be made to follow recommendations. We ask whether exploration can nevertheless be performed in a way that scrupulously respects agents’ interests—i.e., by a system that acts as a fiduciary. More formally, we introduce a model in which a recommendation system faces an exploration-exploitation tradeoff under the constraint that it can never recommend any action that it knows yields lower reward in expectation than an agent would achieve if it acted alone. Our main contribution is a positive result: an asymptotically optimal, incentive compatible, and ex-ante individually rational recommendation algorithm.
Tasks	Recommendation Systems
Published	2019-05-16
URL	https://arxiv.org/abs/1905.07043v2
PDF	https://arxiv.org/pdf/1905.07043v2.pdf
PWC	https://paperswithcode.com/paper/fiduciary-bandits
Repo
Framework