Paper Group ANR 78
Higher-order Graph Convolutional Networks. Unsupervised learning of foreground object detection. Online learning with kernel losses. Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification. Computational Graph Approach for Detection of Composite Human Activities. AAD: Adaptive Anomaly De …
Higher-order Graph Convolutional Networks
| Title | Higher-order Graph Convolutional Networks |
| Authors | John Boaz Lee, Ryan A. Rossi, Xiangnan Kong, Sungchul Kim, Eunyee Koh, Anup Rao |
| Abstract | Following the success of deep convolutional networks in various vision and speech related tasks, researchers have started investigating generalizations of the well-known technique for graph-structured data. A recently-proposed method called Graph Convolutional Networks has been able to achieve state-of-the-art results in the task of node classification. However, since the proposed method relies on localized first-order approximations of spectral graph convolutions, it is unable to capture higher-order interactions between nodes in the graph. In this work, we propose a motif-based graph attention model, called Motif Convolutional Networks (MCNs), which generalizes past approaches by using weighted multi-hop motif adjacency matrices to capture higher-order neighborhoods. A novel attention mechanism is used to allow each individual node to select the most relevant neighborhood to apply its filter. Experiments show that our proposed method is able to achieve state-of-the-art results on the semi-supervised node classification task. |
| Tasks | Node Classification |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.07697v1 |
| http://arxiv.org/pdf/1809.07697v1.pdf | |
| PWC | https://paperswithcode.com/paper/higher-order-graph-convolutional-networks |
| Repo | |
| Framework | |
Unsupervised learning of foreground object detection
| Title | Unsupervised learning of foreground object detection |
| Authors | Ioana Croitoru, Simion-Vlad Bogolin, Marius Leordeanu |
| Abstract | Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled videos can be collected at relatively low cost. In this paper, we address the unsupervised learning problem in the context of detecting the main foreground objects in single images. We train a student deep network to predict the output of a teacher pathway that performs unsupervised object discovery in videos or large image collections. Our approach is different from published methods on unsupervised object discovery. We move the unsupervised learning phase during training time, then at test time we apply the standard feed-forward processing along the student pathway. This strategy has the benefit of allowing increased generalization possibilities during training, while remaining fast at testing. Our unsupervised learning algorithm can run over several generations of student-teacher training. Thus, a group of student networks trained in the first generation collectively create the teacher at the next generation. In experiments our method achieves top results on three current datasets for object discovery in video, unsupervised image segmentation and saliency detection. At test time the proposed system is fast, being one to two orders of magnitude faster than published unsupervised methods. |
| Tasks | Object Detection, Object Discovery In Videos, Saliency Detection, Semantic Segmentation |
| Published | 2018-08-14 |
| URL | http://arxiv.org/abs/1808.04593v1 |
| http://arxiv.org/pdf/1808.04593v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-of-foreground-object |
| Repo | |
| Framework | |
Online learning with kernel losses
| Title | Online learning with kernel losses |
| Authors | Aldo Pacchiano, Niladri S. Chatterji, Peter L. Bartlett |
| Abstract | We present a generalization of the adversarial linear bandits framework, where the underlying losses are kernel functions (with an associated reproducing kernel Hilbert space) rather than linear functions. We study a version of the exponential weights algorithm and bound its regret in this setting. Under conditions on the eigendecay of the kernel we provide a sharp characterization of the regret for this algorithm. When we have polynomial eigendecay $\mu_j \le \mathcal{O}(j^{-\beta})$, we find that the regret is bounded by $\mathcal{R}_n \le \mathcal{O}(n^{\beta/(2(\beta-1))})$; while under the assumption of exponential eigendecay $\mu_j \le \mathcal{O}(e^{-\beta j })$, we get an even tighter bound on the regret $\mathcal{R}_n \le \mathcal{O}(n^{1/2}\log(n)^{1/2})$. We also study the full information setting when the underlying losses are kernel functions and present an adapted exponential weights algorithm and a conditional gradient descent algorithm. |
| Tasks | |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.09732v1 |
| http://arxiv.org/pdf/1802.09732v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-learning-with-kernel-losses |
| Repo | |
| Framework | |
Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification
| Title | Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification |
| Authors | Yu-Jhe Li, Fu-En Yang, Yen-Cheng Liu, Yu-Ying Yeh, Xiaofei Du, Yu-Chiang Frank Wang |
| Abstract | Person re-identification (Re-ID) aims at recognizing the same person from images taken across different cameras. To address this task, one typically requires a large amount labeled data for training an effective Re-ID model, which might not be practical for real-world applications. To alleviate this limitation, we choose to exploit a sufficient amount of pre-existing labeled data from a different (auxiliary) dataset. By jointly considering such an auxiliary dataset and the dataset of interest (but without label information), our proposed adaptation and re-identification network (ARN) performs unsupervised domain adaptation, which leverages information across datasets and derives domain-invariant features for Re-ID purposes. In our experiments, we verify that our network performs favorably against state-of-the-art unsupervised Re-ID approaches, and even outperforms a number of baseline Re-ID methods which require fully supervised data for training. |
| Tasks | Domain Adaptation, Person Re-Identification, Transfer Learning, Unsupervised Domain Adaptation |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09347v1 |
| http://arxiv.org/pdf/1804.09347v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptation-and-re-identification-network-an |
| Repo | |
| Framework | |
Computational Graph Approach for Detection of Composite Human Activities
| Title | Computational Graph Approach for Detection of Composite Human Activities |
| Authors | Niko Reunanen, Ville Könönen, Hermanni Hälvä, Jani Mäntyjärvi, Arttu Lämsä, Jussi Liikka |
| Abstract | Existing work in human activity detection classifies physical activities using a single fixed-length subset of a sensor signal. However, temporally consecutive subsets of a sensor signal are not utilized. This is not optimal for classifying physical activities (composite activities) that are composed of a temporal series of simpler activities (atomic activities). A sport consists of physical activities combined in a fashion unique to that sport. The constituent physical activities and the sport are not fundamentally different. We propose a computational graph architecture for human activity detection based on the readings of a triaxial accelerometer. The resulting model learns 1) a representation of the atomic activities of a sport and 2) to classify physical activities as compositions of the atomic activities. The proposed model, alongside with a set of baseline models, was tested for a simultaneous classification of eight physical activities (walking, nordic walking, running, soccer, rowing, bicycling, exercise bicycling and lying down). The proposed model obtained an overall mean accuracy of 77.91% (population) and 95.28% (personalized). The corresponding accuracies of the best baseline model were 73.52% and 90.03%. However, without combining consecutive atomic activities, the corresponding accuracies of the proposed model were 71.52% and 91.22%. The results show that our proposed model is accurate, outperforms the baseline models and learns to combine simple activities into complex activities. Composite activities can be classified as combinations of atomic activities. Our proposed architecture is a basis for accurate models in human activity detection. |
| Tasks | Action Detection, Activity Detection |
| Published | 2018-12-05 |
| URL | http://arxiv.org/abs/1812.01895v1 |
| http://arxiv.org/pdf/1812.01895v1.pdf | |
| PWC | https://paperswithcode.com/paper/computational-graph-approach-for-detection-of |
| Repo | |
| Framework | |
AAD: Adaptive Anomaly Detection through traffic surveillance videos
| Title | AAD: Adaptive Anomaly Detection through traffic surveillance videos |
| Authors | Mohammmad Farhadi Bajestani, Seyed Soroush Heidari Rahmat Abadi, Seyed Mostafa Derakhshandeh Fard, Roozbeh Khodadadeh |
| Abstract | Anomaly detection through video analysis is of great importance to detect any anomalous vehicle/human behavior at a traffic intersection. While most existing works use neural networks and conventional machine learning methods based on provided dataset, we will use object recognition (Faster R-CNN) to identify objects labels and their corresponding location in the video scene as the first step to implement anomaly detection. Then, the optical flow will be utilized to identify adaptive traffic flows in each region of the frame. Basically, we propose an alternative method for unusual activity detection using an adaptive anomaly detection framework. Compared to the baseline method described in the reference paper, our method is more efficient and yields the comparable accuracy. |
| Tasks | Action Detection, Activity Detection, Anomaly Detection, Object Recognition, Optical Flow Estimation |
| Published | 2018-08-29 |
| URL | http://arxiv.org/abs/1808.10044v1 |
| http://arxiv.org/pdf/1808.10044v1.pdf | |
| PWC | https://paperswithcode.com/paper/aad-adaptive-anomaly-detection-through |
| Repo | |
| Framework | |
Pileup mitigation at the Large Hadron Collider with Graph Neural Networks
| Title | Pileup mitigation at the Large Hadron Collider with Graph Neural Networks |
| Authors | Jesus Arjona Martinez, Olmo Cerri, Maurizio Pierini, Maria Spiropulu, Jean-Roch Vlimant |
| Abstract | At the Large Hadron Collider, the high transverse-momentum events studied by experimental collaborations occur in coincidence with parasitic low transverse-momentum collisions, usually referred to as pileup. Pileup mitigation is a key ingredient of the online and offline event reconstruction as pileup affects the reconstruction accuracy of many physics observables. We present a classifier based on Graph Neural Networks, trained to retain particles coming from high-transverse-momentum collisions, while rejecting those coming from pileup collisions. This model is designed as a refinement of the PUPPI algorithm, employed in many LHC data analyses since 2015. Thanks to an extended basis of input information and the learning capabilities of the considered network architecture, we show an improvement in pileup-rejection performances with respect to state-of-the-art solutions. |
| Tasks | |
| Published | 2018-10-18 |
| URL | https://arxiv.org/abs/1810.07988v4 |
| https://arxiv.org/pdf/1810.07988v4.pdf | |
| PWC | https://paperswithcode.com/paper/pileup-mitigation-at-the-large-hadron |
| Repo | |
| Framework | |
Synthesizing CT from Ultrashort Echo-Time MR Images via Convolutional Neural Networks
| Title | Synthesizing CT from Ultrashort Echo-Time MR Images via Convolutional Neural Networks |
| Authors | Snehashis Roy, John A. Butman, Dzung L. Pham |
| Abstract | With the increasing popularity of PET-MR scanners in clinical applications, synthesis of CT images from MR has been an important research topic. Accurate PET image reconstruction requires attenuation correction, which is based on the electron density of tissues and can be obtained from CT images. While CT measures electron density information for x-ray photons, MR images convey information about the magnetic properties of tissues. Therefore, with the advent of PET-MR systems, the attenuation coefficients need to be indirectly estimated from MR images. In this paper, we propose a fully convolutional neural network (CNN) based method to synthesize head CT from ultra-short echo-time (UTE) dual-echo MR images. Unlike traditional $T_1$-w images which do not have any bone signal, UTE images show some signal for bone, which makes it a good candidate for MR to CT synthesis. A notable advantage of our approach is that accurate results were achieved with a small training data set. Using an atlas of a single CT and dual-echo UTE pair, we train a deep neural network model to learn the transform of MR intensities to CT using patches. We compared our CNN based model with a state-of-the-art registration based as well as a Bayesian model based CT synthesis method, and showed that the proposed CNN model outperforms both of them. We also compared the proposed model when only $T_1$-w images are available instead of UTE, and show that UTE images produce better synthesis than using just $T_1$-w images. |
| Tasks | Image Reconstruction |
| Published | 2018-07-27 |
| URL | http://arxiv.org/abs/1807.10850v1 |
| http://arxiv.org/pdf/1807.10850v1.pdf | |
| PWC | https://paperswithcode.com/paper/synthesizing-ct-from-ultrashort-echo-time-mr |
| Repo | |
| Framework | |
Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition
| Title | Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition |
| Authors | Benjamin Planche, Sergey Zakharov, Ziyan Wu, Andreas Hutter, Harald Kosch, Slobodan Ilic |
| Abstract | While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their training. It thus became common to use available synthetic samples along domain adaptation schemes to prepare algorithms for the target domain. Tackling this problem from a different angle, we introduce a pipeline to map unseen target samples into the synthetic domain used to train task-specific methods. Denoising the data and retaining only the features these recognition algorithms are familiar with, our solution greatly improves their performance. As this mapping is easier to learn than the opposite one (ie to learn to generate realistic features to augment the source samples), we demonstrate how our whole solution can be trained purely on augmented synthetic data, and still perform better than methods trained with domain-relevant information (eg real images or realistic textures for the 3D models). Applying our approach to object recognition from texture-less CAD data, we present a custom generative network which fully utilizes the purely geometrical information to learn robust features and achieve a more refined mapping for unseen color images. |
| Tasks | Denoising, Domain Adaptation, Object Recognition |
| Published | 2018-10-09 |
| URL | http://arxiv.org/abs/1810.04158v1 |
| http://arxiv.org/pdf/1810.04158v1.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-beyond-appearance-mapping-real-images |
| Repo | |
| Framework | |
Gradual Machine Learning for Entity Resolution
| Title | Gradual Machine Learning for Entity Resolution |
| Authors | Boyi Hou, Qun Chen, Yanyan Wang, Youcef Nafa, Zhanhuai Li |
| Abstract | Usually considered as a classification problem, entity resolution (ER) can be very challenging on real data due to the prevalence of dirty values. The state-of-the-art solutions for ER were built on a variety of learning models (most notably deep neural networks), which require lots of accurately labeled training data. Unfortunately, high-quality labeled data usually require expensive manual work, and are therefore not readily available in many real scenarios. In this paper, we propose a novel learning paradigm for ER, called gradual machine learning, which aims to enable effective machine labeling without the requirement for manual labeling effort. It begins with some easy instances in a task, which can be automatically labeled by the machine with high accuracy, and then gradually labels more challenging instances by iterative factor graph inference. In gradual machine learning, the hard instances in a task are gradually labeled in small stages based on the estimated evidential certainty provided by the labeled easier instances. Our extensive experiments on real data have shown that the performance of the proposed approach is considerably better than its unsupervised alternatives, and highly competitive compared to the state-of-the-art supervised techniques. Using ER as a test case, we demonstrate that gradual machine learning is a promising paradigm potentially applicable to other challenging classification tasks requiring extensive labeling effort. |
| Tasks | Entity Resolution |
| Published | 2018-10-29 |
| URL | https://arxiv.org/abs/1810.12125v4 |
| https://arxiv.org/pdf/1810.12125v4.pdf | |
| PWC | https://paperswithcode.com/paper/gradual-machine-learning-for-entity |
| Repo | |
| Framework | |
Reuse and Adaptation for Entity Resolution through Transfer Learning
| Title | Reuse and Adaptation for Entity Resolution through Transfer Learning |
| Authors | Saravanan Thirumuruganathan, Shameem A Puthiya Parambath, Mourad Ouzzani, Nan Tang, Shafiq Joty |
| Abstract | Entity resolution (ER) is one of the fundamental problems in data integration, where machine learning (ML) based classifiers often provide the state-of-the-art results. Considerable human effort goes into feature engineering and training data creation. In this paper, we investigate a new problem: Given a dataset D_T for ER with limited or no training data, is it possible to train a good ML classifier on D_T by reusing and adapting the training data of dataset D_S from same or related domain? Our major contributions include (1) a distributed representation based approach to encode each tuple from diverse datasets into a standard feature space; (2) identification of common scenarios where the reuse of training data can be beneficial; and (3) five algorithms for handling each of the aforementioned scenarios. We have performed comprehensive experiments on 12 datasets from 5 different domains (publications, movies, songs, restaurants, and books). Our experiments show that our algorithms provide significant benefits such as providing superior performance for a fixed training data size. |
| Tasks | Entity Resolution, Feature Engineering, Transfer Learning |
| Published | 2018-09-28 |
| URL | http://arxiv.org/abs/1809.11084v1 |
| http://arxiv.org/pdf/1809.11084v1.pdf | |
| PWC | https://paperswithcode.com/paper/reuse-and-adaptation-for-entity-resolution |
| Repo | |
| Framework | |
Identificação automática de pichação a partir de imagens urbanas
| Title | Identificação automática de pichação a partir de imagens urbanas |
| Authors | Eric K. Tokuda, Claudio T. Silva, Roberto M. Cesar-Jr |
| Abstract | Graffiti tagging is a common issue in great cities an local authorities are on the move to combat it. The tagging map of a city can be a useful tool as it may help to clean-up highly saturated regions and discourage future acts in the neighbourhood and currently there is no way of getting a tagging map of a region in an automatic fashion and manual inspection or crowd participation are required. In this work, we describe a work in progress in creating an automatic way to get a tagging map of a city or region. It is based on the use of street view images and on the detection of graffiti tags in the images. |
| Tasks | |
| Published | 2018-11-06 |
| URL | http://arxiv.org/abs/1811.02372v1 |
| http://arxiv.org/pdf/1811.02372v1.pdf | |
| PWC | https://paperswithcode.com/paper/identificacao-automatica-de-pichacao-a-partir |
| Repo | |
| Framework | |
Posterior Prototyping: Bridging the Gap between Bayesian Record Linkage and Regression
| Title | Posterior Prototyping: Bridging the Gap between Bayesian Record Linkage and Regression |
| Authors | Andee Kaplan, Brenda Betancourt, Rebecca C. Steorts |
| Abstract | Record linkage (entity resolution or de-deduplication) is the process of merging noisy databases to remove duplicate entities. While record linkage removes duplicate entities from the data, many researchers are interested in performing inference, prediction or post-linkage analysis on the linked data, which we call the downstream task. Depending on the downstream task, one may wish to find the most representative record before performing the post-linkage analysis. Motivated by the downstream task, we propose first performing record linkage using a Bayesian model and then choosing representative records through prototyping. Given the information about the representative records, we then explore two downstream tasks - linear regression and binary classification via logistic regression. In addition, we explore how error propagation occurs in both of these settings. We provide thorough empirical studies for our proposed methodology, and conclude with a discussion of practical insights into our work. |
| Tasks | Entity Resolution |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.01538v1 |
| http://arxiv.org/pdf/1810.01538v1.pdf | |
| PWC | https://paperswithcode.com/paper/posterior-prototyping-bridging-the-gap |
| Repo | |
| Framework | |
TarMAC: Targeted Multi-Agent Communication
| Title | TarMAC: Targeted Multi-Agent Communication |
| Authors | Abhishek Das, Théophile Gervet, Joshua Romoff, Dhruv Batra, Devi Parikh, Michael Rabbat, Joelle Pineau |
| Abstract | We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments. This targeting behavior is learnt solely from downstream task-specific reward without any communication supervision. We additionally augment this with a multi-round communication approach where agents coordinate via multiple rounds of communication before taking actions in the environment. We evaluate our approach on a diverse set of cooperative multi-agent tasks, of varying difficulties, with varying number of agents, in a variety of environments ranging from 2D grid layouts of shapes and simulated traffic junctions to 3D indoor environments, and demonstrate the benefits of targeted and multi-round communication. Moreover, we show that the targeted communication strategies learned by agents are interpretable and intuitive. Finally, we show that our architecture can be easily extended to mixed and competitive environments, leading to improved performance and sample complexity over recent state-of-the-art approaches. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2018-10-26 |
| URL | https://arxiv.org/abs/1810.11187v2 |
| https://arxiv.org/pdf/1810.11187v2.pdf | |
| PWC | https://paperswithcode.com/paper/tarmac-targeted-multi-agent-communication |
| Repo | |
| Framework | |
Supervised Classification Methods for Flash X-ray single particle diffraction Imaging
| Title | Supervised Classification Methods for Flash X-ray single particle diffraction Imaging |
| Authors | Jing Liu, Gijs van der Schot, Stefan Engblom |
| Abstract | Current Flash X-ray single-particle diffraction Imaging (FXI) experiments, which operate on modern X-ray Free Electron Lasers (XFELs), can record millions of interpretable diffraction patterns from individual biomolecules per day. Due to the stochastic nature of the XFELs, those patterns will to a varying degree include scatterings from contaminated samples. Also, the heterogeneity of the sample biomolecules is unavoidable and complicates data processing. Reducing the data volumes and selecting high-quality single-molecule patterns are therefore critical steps in the experimental set-up. In this paper, we present two supervised template-based learning methods for classifying FXI patterns. Our Eigen-Image and Log-Likelihood classifier can find the best-matched template for a single-molecule pattern within a few milliseconds. It is also straightforward to parallelize them so as to fully match the XFEL repetition rate, thereby enabling processing at site. |
| Tasks | |
| Published | 2018-10-25 |
| URL | http://arxiv.org/abs/1810.10786v1 |
| http://arxiv.org/pdf/1810.10786v1.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-classification-methods-for-flash-x |
| Repo | |
| Framework | |
