July 28, 2019

3280 words 16 mins read

Paper Group ANR 321

Region-Based Image Retrieval Revisited. CUR Decompositions, Similarity Matrices, and Subspace Clustering. Sufficient and necessary causation are dual. Learning from Longitudinal Face Demonstration - Where Tractable Deep Modeling Meets Inverse Reinforcement Learning. Spatially variant PSF modeling in confocal macroscopy. Multi-Task Convolutional Neu …

Region-Based Image Retrieval Revisited


Title	Region-Based Image Retrieval Revisited
Authors	Ryota Hinami, Yusuke Matsui, Shin’ichi Satoh
Abstract	Region-based image retrieval (RBIR) technique is revisited. In early attempts at RBIR in the late 90s, researchers found many ways to specify region-based queries and spatial relationships; however, the way to characterize the regions, such as by using color histograms, were very poor at that time. Here, we revisit RBIR by incorporating semantic specification of objects and intuitive specification of spatial relationships. Our contributions are the following. First, to support multiple aspects of semantic object specification (category, instance, and attribute), we propose a multitask CNN feature that allows us to use deep learning technique and to jointly handle multi-aspect object specification. Second, to help users specify spatial relationships among objects in an intuitive way, we propose recommendation techniques of spatial relationships. In particular, by mining the search results, a system can recommend feasible spatial relationships among the objects. The system also can recommend likely spatial relationships by assigned object category names based on language prior. Moreover, object-level inverted indexing supports very fast shortlist generation, and re-ranking based on spatial constraints provides users with instant RBIR experiences.
Tasks	Image Retrieval
Published	2017-09-26
URL	http://arxiv.org/abs/1709.09106v1
PDF	http://arxiv.org/pdf/1709.09106v1.pdf
PWC	https://paperswithcode.com/paper/region-based-image-retrieval-revisited
Repo
Framework

CUR Decompositions, Similarity Matrices, and Subspace Clustering


Title	CUR Decompositions, Similarity Matrices, and Subspace Clustering
Authors	Akram Aldroubi, Keaton Hamm, Ahmet Bugra Koku, Ali Sekmen
Abstract	A general framework for solving the subspace clustering problem using the CUR decomposition is presented. The CUR decomposition provides a natural way to construct similarity matrices for data that come from a union of unknown subspaces $\mathscr{U}=\underset{i=1}{\overset{M}\bigcup}S_i$. The similarity matrices thus constructed give the exact clustering in the noise-free case. Additionally, this decomposition gives rise to many distinct similarity matrices from a given set of data, which allow enough flexibility to perform accurate clustering of noisy data. We also show that two known methods for subspace clustering can be derived from the CUR decomposition. An algorithm based on the theoretical construction of similarity matrices is presented, and experiments on synthetic and real data are presented to test the method. Additionally, an adaptation of our CUR based similarity matrices is utilized to provide a heuristic algorithm for subspace clustering; this algorithm yields the best overall performance to date for clustering the Hopkins155 motion segmentation dataset.
Tasks	Motion Segmentation
Published	2017-11-11
URL	http://arxiv.org/abs/1711.04178v3
PDF	http://arxiv.org/pdf/1711.04178v3.pdf
PWC	https://paperswithcode.com/paper/cur-decompositions-similarity-matrices-and
Repo
Framework

Sufficient and necessary causation are dual


Title	Sufficient and necessary causation are dual
Authors	Robert Künnemann
Abstract	Causation has been the issue of philosophic debate since Hippocrates. Recent work defines actual causation in terms of Pearl/Halpern’s causality framework, formalizing necessary causes (IJCAI’15). This has inspired causality notions in the security domain (CSF’15), which, perhaps surprisingly, formalize sufficient causes instead. We provide an explicit relation between necessary and sufficient causes.
Tasks
Published	2017-10-25
URL	http://arxiv.org/abs/1710.09102v1
PDF	http://arxiv.org/pdf/1710.09102v1.pdf
PWC	https://paperswithcode.com/paper/sufficient-and-necessary-causation-are-dual
Repo
Framework

Learning from Longitudinal Face Demonstration - Where Tractable Deep Modeling Meets Inverse Reinforcement Learning


Title	Learning from Longitudinal Face Demonstration - Where Tractable Deep Modeling Meets Inverse Reinforcement Learning
Authors	Chi Nhan Duong, Kha Gia Quach, Khoa Luu, T. Hoang Ngan Le, Marios Savvides, Tien D. Bui
Abstract	This paper presents a novel Subject-dependent Deep Aging Path (SDAP), which inherits the merits of both Generative Probabilistic Modeling and Inverse Reinforcement Learning to model the facial structures and the longitudinal face aging process of a given subject. The proposed SDAP is optimized using tractable log-likelihood objective functions with Convolutional Neural Networks (CNNs) based deep feature extraction. Instead of applying a fixed aging development path for all input faces and subjects, SDAP is able to provide the most appropriate aging development path for individual subject that optimizes the reward aging formulation. Unlike previous methods that can take only one image as the input, SDAP further allows multiple images as inputs, i.e. all information of a subject at either the same or different ages, to produce the optimal aging path for the given subject. Finally, SDAP allows efficiently synthesizing in-the-wild aging faces. The proposed model is experimented in both tasks of face aging synthesis and cross-age face verification. The experimental results consistently show SDAP achieves the state-of-the-art performance on numerous face aging databases, i.e. FG-NET, MORPH, AginG Faces in the Wild (AGFW), and Cross-Age Celebrity Dataset (CACD). Furthermore, we also evaluate the performance of SDAP on large-scale Megaface challenge to demonstrate the advantages of the proposed solution.
Tasks	Face Verification
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10520v4
PDF	http://arxiv.org/pdf/1711.10520v4.pdf
PWC	https://paperswithcode.com/paper/learning-from-longitudinal-face-demonstration
Repo
Framework

Spatially variant PSF modeling in confocal macroscopy


Title	Spatially variant PSF modeling in confocal macroscopy
Authors	Anna Jezierska, Hugues Talbot, Jean-Christophe Pesquet, Gilbert Engler
Abstract	Point spread function (PSF) plays an essential role in image reconstruction. In the context of confocal microscopy, optical performance degrades towards the edge of the field of view as astigmatism, coma and vignetting. Thus, one should expect the related artifacts to be even stronger in macroscopy, where the field of view is much larger. The field aberrations in macroscopy fluorescence imaging system was observed to be symmetrical and to increase with the distance from the center of the field of view. In this paper we propose an experiment and an optimization method for assessing the center of the field of view. The obtained results constitute a step towards reducing the number of parameters in macroscopy PSF model.
Tasks	Image Reconstruction
Published	2017-07-14
URL	http://arxiv.org/abs/1707.09858v1
PDF	http://arxiv.org/pdf/1707.09858v1.pdf
PWC	https://paperswithcode.com/paper/spatially-variant-psf-modeling-in-confocal
Repo
Framework

Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition


Title	Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition
Authors	Xi Yin, Xiaoming Liu
Abstract	This paper explores multi-task learning (MTL) for face recognition. We answer the questions of how and why MTL can improve the face recognition performance. First, we propose a multi-task Convolutional Neural Network (CNN) for face recognition where identity classification is the main task and pose, illumination, and expression estimations are the side tasks. Second, we develop a dynamic-weighting scheme to automatically assign the loss weight to each side task, which is a crucial problem in MTL. Third, we propose a pose-directed multi-task CNN by grouping different poses to learn pose-specific identity features, simultaneously across all poses. Last but not least, we propose an energy-based weight analysis method to explore how CNN-based MTL works. We observe that the side tasks serve as regularizations to disentangle the variations from the learnt identity features. Extensive experiments on the entire Multi-PIE dataset demonstrate the effectiveness of the proposed approach. To the best of our knowledge, this is the first work using all data in Multi-PIE for face recognition. Our approach is also applicable to in-the-wild datasets for pose-invariant face recognition and achieves comparable or better performance than state of the art on LFW, CFP, and IJB-A datasets.
Tasks	Face Recognition, Multi-Task Learning, Robust Face Recognition
Published	2017-02-15
URL	http://arxiv.org/abs/1702.04710v2
PDF	http://arxiv.org/pdf/1702.04710v2.pdf
PWC	https://paperswithcode.com/paper/multi-task-convolutional-neural-network-for
Repo
Framework

Effective Evaluation using Logged Bandit Feedback from Multiple Loggers


Title	Effective Evaluation using Logged Bandit Feedback from Multiple Loggers
Authors	Aman Agarwal, Soumya Basu, Tobias Schnabel, Thorsten Joachims
Abstract	Accurately evaluating new policies (e.g. ad-placement models, ranking functions, recommendation functions) is one of the key prerequisites for improving interactive systems. While the conventional approach to evaluation relies on online A/B tests, recent work has shown that counterfactual estimators can provide an inexpensive and fast alternative, since they can be applied offline using log data that was collected from a different policy fielded in the past. In this paper, we address the question of how to estimate the performance of a new target policy when we have log data from multiple historic policies. This question is of great relevance in practice, since policies get updated frequently in most online systems. We show that naively combining data from multiple logging policies can be highly suboptimal. In particular, we find that the standard Inverse Propensity Score (IPS) estimator suffers especially when logging and target policies diverge – to a point where throwing away data improves the variance of the estimator. We therefore propose two alternative estimators which we characterize theoretically and compare experimentally. We find that the new estimators can provide substantially improved estimation accuracy.
Tasks
Published	2017-03-17
URL	http://arxiv.org/abs/1703.06180v2
PDF	http://arxiv.org/pdf/1703.06180v2.pdf
PWC	https://paperswithcode.com/paper/effective-evaluation-using-logged-bandit
Repo
Framework

Learning Musical Relations using Gated Autoencoders


Title	Learning Musical Relations using Gated Autoencoders
Authors	Stefan Lattner, Maarten Grachten, Gerhard Widmer
Abstract	Music is usually highly structured and it is still an open question how to design models which can successfully learn to recognize and represent musical structure. A fundamental problem is that structurally related patterns can have very distinct appearances, because the structural relationships are often based on transformations of musical material, like chromatic or diatonic transposition, inversion, retrograde, or rhythm change. In this preliminary work, we study the potential of two unsupervised learning techniques - Restricted Boltzmann Machines (RBMs) and Gated Autoencoders (GAEs) - to capture pre-defined transformations from constructed data pairs. We evaluate the models by using the learned representations as inputs in a discriminative task where for a given type of transformation (e.g. diatonic transposition), the specific relation between two musical patterns must be recognized (e.g. an upward transposition of diatonic steps). Furthermore, we measure the reconstruction error of models when reconstructing musical transformed patterns. Lastly, we test the models in an analogy-making task. We find that it is difficult to learn musical transformations with the RBM and that the GAE is much more adequate for this task, since it is able to learn representations of specific transformations that are largely content-invariant. We believe these results show that models such as GAEs may provide the basis for more encompassing music analysis systems, by endowing them with a better understanding of the structures underlying music.
Tasks
Published	2017-08-17
URL	http://arxiv.org/abs/1708.05325v1
PDF	http://arxiv.org/pdf/1708.05325v1.pdf
PWC	https://paperswithcode.com/paper/learning-musical-relations-using-gated
Repo
Framework

Gigamachine: incremental machine learning on desktop computers


Title	Gigamachine: incremental machine learning on desktop computers
Authors	Eray Özkural
Abstract	We present a concrete design for Solomonoff’s incremental machine learning system suitable for desktop computers. We use R5RS Scheme and its standard library with a few omissions as the reference machine. We introduce a Levin Search variant based on a stochastic Context Free Grammar together with new update algorithms that use the same grammar as a guiding probability distribution for incremental machine learning. The updates include adjusting production probabilities, re-using previous solutions, learning programming idioms and discovery of frequent subprograms. The issues of extending the a priori probability distribution and bootstrapping are discussed. We have implemented a good portion of the proposed algorithms. Experiments with toy problems show that the update algorithms work as expected.
Tasks
Published	2017-09-08
URL	http://arxiv.org/abs/1709.03413v1
PDF	http://arxiv.org/pdf/1709.03413v1.pdf
PWC	https://paperswithcode.com/paper/gigamachine-incremental-machine-learning-on
Repo
Framework

TraNNsformer: Neural network transformation for memristive crossbar based neuromorphic system design


Title	TraNNsformer: Neural network transformation for memristive crossbar based neuromorphic system design
Authors	Aayush Ankit, Abhronil Sengupta, Kaushik Roy
Abstract	Implementation of Neuromorphic Systems using post Complementary Metal-Oxide-Semiconductor (CMOS) technology based Memristive Crossbar Array (MCA) has emerged as a promising solution to enable low-power acceleration of neural networks. However, the recent trend to design Deep Neural Networks (DNNs) for achieving human-like cognitive abilities poses significant challenges towards the scalable design of neuromorphic systems (due to the increase in computation/storage demands). Network pruning [7] is a powerful technique to remove redundant connections for designing optimally connected (maximally sparse) DNNs. However, such pruning techniques induce irregular connections that are incoherent to the crossbar structure. Eventually they produce DNNs with highly inefficient hardware realizations (in terms of area and energy). In this work, we propose TraNNsformer - an integrated training framework that transforms DNNs to enable their efficient realization on MCA-based systems. TraNNsformer first prunes the connectivity matrix while forming clusters with the remaining connections. Subsequently, it retrains the network to fine tune the connections and reinforce the clusters. This is done iteratively to transform the original connectivity into an optimally pruned and maximally clustered mapping. Without accuracy loss, TraNNsformer reduces the area (energy) consumption by 28% - 55% (49% - 67%) with respect to the original network. Compared to network pruning, TraNNsformer achieves 28% - 49% (15% - 29%) area (energy) savings. Furthermore, TraNNsformer is a technology-aware framework that allows mapping a given DNN to any MCA size permissible by the memristive technology for reliable operations.
Tasks	Network Pruning
Published	2017-08-26
URL	http://arxiv.org/abs/1708.07949v2
PDF	http://arxiv.org/pdf/1708.07949v2.pdf
PWC	https://paperswithcode.com/paper/trannsformer-neural-network-transformation
Repo
Framework

Latent Constrained Correlation Filter


Title	Latent Constrained Correlation Filter
Authors	Baochang Zhang, Shangzhen Luan, Chen Chen, Jungong Han, Wei Wang, Alessandro Perina, Ling Shao
Abstract	Correlation filters are special classifiers designed for shift-invariant object recognition, which are robust to pattern distortions. The recent literature shows that combining a set of sub-filters trained based on a single or a small group of images obtains the best performance. The idea is equivalent to estimating variable distribution based on the data sampling (bagging), which can be interpreted as finding solutions (variable distribution approximation) directly from sampled data space. However, this methodology fails to account for the variations existed in the data. In this paper, we introduce an intermediate step – solution sampling – after the data sampling step to form a subspace, in which an optimal solution can be estimated. More specifically, we propose a new method, named latent constrained correlation filters (LCCF), by mapping the correlation filters to a given latent subspace, and develop a new learning framework in the latent subspace that embeds distribution-related constraints into the original problem. To solve the optimization problem, we introduce a subspace based alternating direction method of multipliers (SADMM), which is proven to converge at the saddle point. Our approach is successfully applied to three different tasks, including eye localization, car detection and object tracking. Extensive experiments demonstrate that LCCF outperforms the state-of-the-art methods. The source code will be publicly available. https://github.com/bczhangbczhang/.
Tasks	Object Recognition, Object Tracking
Published	2017-11-11
URL	http://arxiv.org/abs/1711.04192v1
PDF	http://arxiv.org/pdf/1711.04192v1.pdf
PWC	https://paperswithcode.com/paper/latent-constrained-correlation-filter
Repo
Framework

Duality-free Methods for Stochastic Composition Optimization


Title	Duality-free Methods for Stochastic Composition Optimization
Authors	Liu Liu, Ji Liu, Dacheng Tao
Abstract	We consider the composition optimization with two expected-value functions in the form of $\frac{1}{n}\sum\nolimits_{i = 1}^n F_i(\frac{1}{m}\sum\nolimits_{j = 1}^m G_j(x))+R(x)$, { which formulates many important problems in statistical learning and machine learning such as solving Bellman equations in reinforcement learning and nonlinear embedding}. Full Gradient or classical stochastic gradient descent based optimization algorithms are unsuitable or computationally expensive to solve this problem due to the inner expectation $\frac{1}{m}\sum\nolimits_{j = 1}^m G_j(x)$. We propose a duality-free based stochastic composition method that combines variance reduction methods to address the stochastic composition problem. We apply SVRG and SAGA based methods to estimate the inner function, and duality-free method to estimate the outer function. We prove the linear convergence rate not only for the convex composition problem, but also for the case that the individual outer functions are non-convex while the objective function is strongly-convex. We also provide the results of experiments that show the effectiveness of our proposed methods.
Tasks
Published	2017-10-26
URL	http://arxiv.org/abs/1710.09554v1
PDF	http://arxiv.org/pdf/1710.09554v1.pdf
PWC	https://paperswithcode.com/paper/duality-free-methods-for-stochastic
Repo
Framework

Robust Registration and Geometry Estimation from Unstructured Facial Scans


Title	Robust Registration and Geometry Estimation from Unstructured Facial Scans
Authors	Maxim Bazik, Daniel Crispell
Abstract	Commercial off the shelf (COTS) 3D scanners are capable of generating point clouds covering visible portions of a face with sub-millimeter accuracy at close range, but lack the coverage and specialized anatomic registration provided by more expensive 3D facial scanners. We demonstrate an effective pipeline for joint alignment of multiple unstructured 3D point clouds and registration to a parameterized 3D model which represents shape variation of the human head. Most algorithms separate the problems of pose estimation and mesh warping, however we propose a new iterative method where these steps are interwoven. Error decreases with each iteration, showing the proposed approach is effective in improving geometry and alignment. The approach described is used to align the NDOff-2007 dataset, which contains 7,358 individual scans at various poses of 396 subjects. The dataset has a number of full profile scans which are correctly aligned and contribute directly to the associated mesh geometry. The dataset in its raw form contains a significant number of mislabeled scans, which are identified and corrected based on alignment error using the proposed algorithm. The average point to surface distance between the aligned scans and the produced geometries is one half millimeter.
Tasks	Pose Estimation
Published	2017-08-17
URL	http://arxiv.org/abs/1708.05340v1
PDF	http://arxiv.org/pdf/1708.05340v1.pdf
PWC	https://paperswithcode.com/paper/robust-registration-and-geometry-estimation
Repo
Framework

Unsupervised Heart-rate Estimation in Wearables With Liquid States and A Probabilistic Readout


Title	Unsupervised Heart-rate Estimation in Wearables With Liquid States and A Probabilistic Readout
Authors	Anup Das, Paruthi Pradhapan, Willemijn Groenendaal, Prathyusha Adiraju, Raj Thilak Rajan, Francky Catthoor, Siebren Schaafsma, Jeffrey L. Krichmar, Nikil Dutt, Chris Van Hoof
Abstract	Heart-rate estimation is a fundamental feature of modern wearable devices. In this paper we propose a machine intelligent approach for heart-rate estimation from electrocardiogram (ECG) data collected using wearable devices. The novelty of our approach lies in (1) encoding spatio-temporal properties of ECG signals directly into spike train and using this to excite recurrently connected spiking neurons in a Liquid State Machine computation model; (2) a novel learning algorithm; and (3) an intelligently designed unsupervised readout based on Fuzzy c-Means clustering of spike responses from a subset of neurons (Liquid states), selected using particle swarm optimization. Our approach differs from existing works by learning directly from ECG signals (allowing personalization), without requiring costly data annotations. Additionally, our approach can be easily implemented on state-of-the-art spiking-based neuromorphic systems, offering high accuracy, yet significantly low energy footprint, leading to an extended battery life of wearable devices. We validated our approach with CARLsim, a GPU accelerated spiking neural network simulator modeling Izhikevich spiking neurons with Spike Timing Dependent Plasticity (STDP) and homeostatic scaling. A range of subjects are considered from in-house clinical trials and public ECG databases. Results show high accuracy and low energy footprint in heart-rate estimation across subjects with and without cardiac irregularities, signifying the strong potential of this approach to be integrated in future wearable devices.
Tasks	Heart rate estimation
Published	2017-07-18
URL	http://arxiv.org/abs/1708.05356v1
PDF	http://arxiv.org/pdf/1708.05356v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-heart-rate-estimation-in
Repo
Framework

Dataset Construction via Attention for Aspect Term Extraction with Distant Supervision


Title	Dataset Construction via Attention for Aspect Term Extraction with Distant Supervision
Authors	Athanasios Giannakopoulos, Diego Antognini, Claudiu Musat, Andreea Hossmann, Michael Baeriswyl
Abstract	Aspect Term Extraction (ATE) detects opinionated aspect terms in sentences or text spans, with the end goal of performing aspect-based sentiment analysis. The small amount of available datasets for supervised ATE and the fact that they cover only a few domains raise the need for exploiting other data sources in new and creative ways. Publicly available review corpora contain a plethora of opinionated aspect terms and cover a larger domain spectrum. In this paper, we first propose a method for using such review corpora for creating a new dataset for ATE. Our method relies on an attention mechanism to select sentences that have a high likelihood of containing actual opinionated aspects. We thus improve the quality of the extracted aspects. We then use the constructed dataset to train a model and perform ATE with distant supervision. By evaluating on human annotated datasets, we prove that our method achieves a significantly improved performance over various unsupervised and supervised baselines. Finally, we prove that sentence selection matters when it comes to creating new datasets for ATE. Specifically, we show that, using a set of selected sentences leads to higher ATE performance compared to using the whole sentence set.
Tasks	Aspect-Based Sentiment Analysis, Sentiment Analysis
Published	2017-09-26
URL	http://arxiv.org/abs/1709.09220v1
PDF	http://arxiv.org/pdf/1709.09220v1.pdf
PWC	https://paperswithcode.com/paper/dataset-construction-via-attention-for-aspect
Repo
Framework