May 6, 2019

2884 words 14 mins read

Paper Group ANR 423

Semantic Facial Expression Editing using Autoencoded Flow. Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning. Conversational Markers of Constructive Discussions. Syntactically Guided Neural Machine Translation. Stochastic Dykstra Algorithms for Metric Learning on Positive Semi-Definite Cone. Detecting Moving …

Semantic Facial Expression Editing using Autoencoded Flow


Title	Semantic Facial Expression Editing using Autoencoded Flow
Authors	Raymond Yeh, Ziwei Liu, Dan B Goldman, Aseem Agarwala
Abstract	High-level manipulation of facial expressions in images — such as changing a smile to a neutral expression — is challenging because facial expression changes are highly non-linear, and vary depending on the appearance of the face. We present a fully automatic approach to editing faces that combines the advantages of flow-based face manipulation with the more recent generative capabilities of Variational Autoencoders (VAEs). During training, our model learns to encode the flow from one expression to another over a low-dimensional latent space. At test time, expression editing can be done simply using latent vector arithmetic. We evaluate our methods on two applications: 1) single-image facial expression editing, and 2) facial expression interpolation between two images. We demonstrate that our method generates images of higher perceptual quality than previous VAE and flow-based methods.
Tasks
Published	2016-11-30
URL	http://arxiv.org/abs/1611.09961v1
PDF	http://arxiv.org/pdf/1611.09961v1.pdf
PWC	https://paperswithcode.com/paper/semantic-facial-expression-editing-using
Repo
Framework

Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning


Title	Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning
Authors	Gang Niu, Marthinus Christoffel du Plessis, Tomoya Sakai, Yao Ma, Masashi Sugiyama
Abstract	In PU learning, a binary classifier is trained from positive (P) and unlabeled (U) data without negative (N) data. Although N data is missing, it sometimes outperforms PN learning (i.e., ordinary supervised learning). Hitherto, neither theoretical nor experimental analysis has been given to explain this phenomenon. In this paper, we theoretically compare PU (and NU) learning against PN learning based on the upper bounds on estimation errors. We find simple conditions when PU and NU learning are likely to outperform PN learning, and we prove that, in terms of the upper bounds, either PU or NU learning (depending on the class-prior probability and the sizes of P and N data) given infinite U data will improve on PN learning. Our theoretical findings well agree with the experimental results on artificial and benchmark data even when the experimental setup does not match the theoretical assumptions exactly.
Tasks
Published	2016-03-10
URL	http://arxiv.org/abs/1603.03130v3
PDF	http://arxiv.org/pdf/1603.03130v3.pdf
PWC	https://paperswithcode.com/paper/theoretical-comparisons-of-positive-unlabeled
Repo
Framework

Conversational Markers of Constructive Discussions


Title	Conversational Markers of Constructive Discussions
Authors	Vlad Niculae, Cristian Danescu-Niculescu-Mizil
Abstract	Group discussions are essential for organizing every aspect of modern life, from faculty meetings to senate debates, from grant review panels to papal conclaves. While costly in terms of time and organization effort, group discussions are commonly seen as a way of reaching better decisions compared to solutions that do not require coordination between the individuals (e.g. voting)—through discussion, the sum becomes greater than the parts. However, this assumption is not irrefutable: anecdotal evidence of wasteful discussions abounds, and in our own experiments we find that over 30% of discussions are unproductive. We propose a framework for analyzing conversational dynamics in order to determine whether a given task-oriented discussion is worth having or not. We exploit conversational patterns reflecting the flow of ideas and the balance between the participants, as well as their linguistic choices. We apply this framework to conversations naturally occurring in an online collaborative world exploration game developed and deployed to support this research. Using this setting, we show that linguistic cues and conversational patterns extracted from the first 20 seconds of a team discussion are predictive of whether it will be a wasteful or a productive one.
Tasks
Published	2016-04-25
URL	http://arxiv.org/abs/1604.07407v1
PDF	http://arxiv.org/pdf/1604.07407v1.pdf
PWC	https://paperswithcode.com/paper/conversational-markers-of-constructive
Repo
Framework

Syntactically Guided Neural Machine Translation


Title	Syntactically Guided Neural Machine Translation
Authors	Felix Stahlberg, Eva Hasler, Aurelien Waite, Bill Byrne
Abstract	We investigate the use of hierarchical phrase-based SMT lattices in end-to-end neural machine translation (NMT). Weight pushing transforms the Hiero scores for complete translation hypotheses, with the full translation grammar score and full n-gram language model score, into posteriors compatible with NMT predictive probabilities. With a slightly modified NMT beam-search decoder we find gains over both Hiero and NMT decoding alone, with practical advantages in extending NMT to very large input and output vocabularies.
Tasks	Language Modelling, Machine Translation
Published	2016-05-15
URL	http://arxiv.org/abs/1605.04569v2
PDF	http://arxiv.org/pdf/1605.04569v2.pdf
PWC	https://paperswithcode.com/paper/syntactically-guided-neural-machine
Repo
Framework

Stochastic Dykstra Algorithms for Metric Learning on Positive Semi-Definite Cone


Title	Stochastic Dykstra Algorithms for Metric Learning on Positive Semi-Definite Cone
Authors	Tomoki Matsuzawa, Raissa Relator, Jun Sese, Tsuyoshi Kato
Abstract	Recently, covariance descriptors have received much attention as powerful representations of set of points. In this research, we present a new metric learning algorithm for covariance descriptors based on the Dykstra algorithm, in which the current solution is projected onto a half-space at each iteration, and runs at O(n^3) time. We empirically demonstrate that randomizing the order of half-spaces in our Dykstra-based algorithm significantly accelerates the convergence to the optimal solution. Furthermore, we show that our approach yields promising experimental results on pattern recognition tasks.
Tasks	Metric Learning
Published	2016-01-07
URL	http://arxiv.org/abs/1601.01422v1
PDF	http://arxiv.org/pdf/1601.01422v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-dykstra-algorithms-for-metric
Repo
Framework

Detecting Moving Regions in CrowdCam Images


Title	Detecting Moving Regions in CrowdCam Images
Authors	Adi Dafni, Yael Moses, Shai Avidan
Abstract	We address the novel problem of detecting dynamic regions in CrowdCam images, a set of still images captured by a group of people. These regions capture the most interesting parts of the scene, and detecting them plays an important role in the analysis of visual data. Our method is based on the observation that matching static points must satisfy the epipolar geometry constraints, but computing exact matches is challenging. Instead, we compute the probability that a pixel has a match, not necessarily the correct one, along the corresponding epipolar line. The complement of this probability is not necessarily the probability of a dynamic point because of occlusions, noise, and matching errors. Therefore, information from all pairs of images is aggregated to obtain a high quality dynamic probability map, per image. Experiments on challenging datasets demonstrate the effectiveness of the algorithm on a broad range of settings; no prior knowledge about the scene, the camera characteristics or the camera locations is required.
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03270v1
PDF	http://arxiv.org/pdf/1611.03270v1.pdf
PWC	https://paperswithcode.com/paper/detecting-moving-regions-in-crowdcam-images
Repo
Framework

Efficient differentially private learning improves drug sensitivity prediction


Title	Efficient differentially private learning improves drug sensitivity prediction
Authors	Antti Honkela, Mrinal Das, Arttu Nieminen, Onur Dikmen, Samuel Kaski
Abstract	Users of a personalised recommendation system face a dilemma: recommendations can be improved by learning from data, but only if the other users are willing to share their private information. Good personalised predictions are vitally important in precision medicine, but genomic information on which the predictions are based is also particularly sensitive, as it directly identifies the patients and hence cannot easily be anonymised. Differential privacy has emerged as a potentially promising solution: privacy is considered sufficient if presence of individual patients cannot be distinguished. However, differentially private learning with current methods does not improve predictions with feasible data sizes and dimensionalities. Here we show that useful predictors can be learned under powerful differential privacy guarantees, and even from moderately-sized data sets, by demonstrating significant improvements with a new robust private regression method in the accuracy of private drug sensitivity prediction. The method combines two key properties not present even in recent proposals, which can be generalised to other predictors: we prove it is asymptotically consistently and efficiently private, and demonstrate that it performs well on finite data. Good finite data performance is achieved by limiting the sharing of private information by decreasing the dimensionality and by projecting outliers to fit tighter bounds, therefore needing to add less noise for equal privacy. As already the simple-to-implement method shows promise on the challenging genomic data, we anticipate rapid progress towards practical applications in many fields, such as mobile sensing and social media, in addition to the badly needed precision medicine solutions.
Tasks
Published	2016-06-07
URL	http://arxiv.org/abs/1606.02109v2
PDF	http://arxiv.org/pdf/1606.02109v2.pdf
PWC	https://paperswithcode.com/paper/efficient-differentially-private-learning
Repo
Framework

Concatenated image completion via tensor augmentation and completion


Title	Concatenated image completion via tensor augmentation and completion
Authors	Johann A. Bengua, Hoang D. Tuan, Ho N. Phien, Minh N. Do
Abstract	This paper proposes a novel framework called concatenated image completion via tensor augmentation and completion (ICTAC), which recovers missing entries of color images with high accuracy. Typical images are second- or third-order tensors (2D/3D) depending if they are grayscale or color, hence tensor completion algorithms are ideal for their recovery. The proposed framework performs image completion by concatenating copies of a single image that has missing entries into a third-order tensor, applying a dimensionality augmentation technique to the tensor, utilizing a tensor completion algorithm for recovering its missing entries, and finally extracting the recovered image from the tensor. The solution relies on two key components that have been recently proposed to take advantage of the tensor train (TT) rank: A tensor augmentation tool called ket augmentation (KA) that represents a low-order tensor by a higher-order tensor, and the algorithm tensor completion by parallel matrix factorization via tensor train (TMac-TT), which has been demonstrated to outperform state-of-the-art tensor completion algorithms. Simulation results for color image recovery show the clear advantage of our framework against current state-of-the-art tensor completion algorithms.
Tasks
Published	2016-07-14
URL	http://arxiv.org/abs/1607.03967v1
PDF	http://arxiv.org/pdf/1607.03967v1.pdf
PWC	https://paperswithcode.com/paper/concatenated-image-completion-via-tensor
Repo
Framework

Segmentation of large images based on super-pixels and community detection in graphs


Title	Segmentation of large images based on super-pixels and community detection in graphs
Authors	Oscar A. C. Linares, Glenda Michele Botelho, Francisco Aparecido Rodrigues, João Batista Neto
Abstract	Image segmentation has many applications which range from machine learning to medical diagnosis. In this paper, we propose a framework for the segmentation of images based on super-pixels and algorithms for community identification in graphs. The super-pixel pre-segmentation step reduces the number of nodes in the graph, rendering the method the ability to process large images. Moreover, community detection algorithms provide more accurate segmentation than traditional approaches, such as those based on spectral graph partition. We also compare our method with two algorithms: a) the graph-based approach by Felzenszwalb and Huttenlocher and b) the contour-based method by Arbelaez. Results have shown that our method provides more precise segmentation and is faster than both of them.
Tasks	Community Detection, Medical Diagnosis, Semantic Segmentation
Published	2016-12-12
URL	http://arxiv.org/abs/1612.03705v1
PDF	http://arxiv.org/pdf/1612.03705v1.pdf
PWC	https://paperswithcode.com/paper/segmentation-of-large-images-based-on-super
Repo
Framework

Visual Processing by a Unified Schatten-$p$ Norm and $\ell_q$ Norm Regularized Principal Component Pursuit


Title	Visual Processing by a Unified Schatten-$p$ Norm and $\ell_q$ Norm Regularized Principal Component Pursuit
Authors	Jing Wang, Meng Wang, Xuegang Hu, Shuicheng Yan
Abstract	In this paper, we propose a non-convex formulation to recover the authentic structure from the corrupted real data. Typically, the specific structure is assumed to be low rank, which holds for a wide range of data, such as images and videos. Meanwhile, the corruption is assumed to be sparse. In the literature, such a problem is known as Robust Principal Component Analysis (RPCA), which usually recovers the low rank structure by approximating the rank function with a nuclear norm and penalizing the error by an $\ell_1$-norm. Although RPCA is a convex formulation and can be solved effectively, the introduced norms are not tight approximations, which may cause the solution to deviate from the authentic one. Therefore, we consider here a non-convex relaxation, consisting of a Schatten-$p$ norm and an $\ell_q$-norm that promote low rank and sparsity respectively. We derive a proximal iteratively reweighted algorithm (PIRA) to solve the problem. Our algorithm is based on an alternating direction method of multipliers, where in each iteration we linearize the underlying objective function that allows us to have a closed form solution. We demonstrate that solutions produced by the linearized approximation always converge and have a tighter approximation than the convex counterpart. Experimental results on benchmarks show encouraging results of our approach.
Tasks
Published	2016-08-20
URL	http://arxiv.org/abs/1608.05856v1
PDF	http://arxiv.org/pdf/1608.05856v1.pdf
PWC	https://paperswithcode.com/paper/visual-processing-by-a-unified-schatten-p
Repo
Framework

Properties of ABA+ for Non-Monotonic Reasoning


Title	Properties of ABA+ for Non-Monotonic Reasoning
Authors	Kristijonas Cyras, Francesca Toni
Abstract	We investigate properties of ABA+, a formalism that extends the well studied structured argumentation formalism Assumption-Based Argumentation (ABA) with a preference handling mechanism. In particular, we establish desirable properties that ABA+ semantics exhibit. These pave way to the satisfaction by ABA+ of some (arguably) desirable principles of preference handling in argumentation and nonmonotonic reasoning, as well as non-monotonic inference properties of ABA+ under various semantics.
Tasks
Published	2016-03-29
URL	http://arxiv.org/abs/1603.08714v3
PDF	http://arxiv.org/pdf/1603.08714v3.pdf
PWC	https://paperswithcode.com/paper/properties-of-aba-for-non-monotonic-reasoning
Repo
Framework

Factored Contextual Policy Search with Bayesian Optimization


Title	Factored Contextual Policy Search with Bayesian Optimization
Authors	Peter Karkus, Andras Kupcsik, David Hsu, Wee Sun Lee
Abstract	Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different “contexts”. Bayesian optimization approaches to contextual policy search (CPS) offer data-efficient policy learning that generalize over a context space. We propose to improve data-efficiency by factoring typically considered contexts into two components: target-type contexts that correspond to a desired outcome of the learned behavior, e.g. target position for throwing a ball; and environment type contexts that correspond to some state of the environment, e.g. initial ball position or wind speed. Our key observation is that experience can be directly generalized over target-type contexts. Based on that we introduce Factored Contextual Policy Search with Bayesian Optimization for both passive and active learning settings. Preliminary results show faster policy generalization on a simulated toy problem. A full paper extension is available at arXiv:1904.11761
Tasks	Active Learning
Published	2016-12-06
URL	https://arxiv.org/abs/1612.01746v2
PDF	https://arxiv.org/pdf/1612.01746v2.pdf
PWC	https://paperswithcode.com/paper/factored-contextual-policy-search-with
Repo
Framework

Universal Clustering via Crowdsourcing


Title	Universal Clustering via Crowdsourcing
Authors	Ravi Kiran Raman, Lav Varshney
Abstract	Consider unsupervised clustering of objects drawn from a discrete set, through the use of human intelligence available in crowdsourcing platforms. This paper defines and studies the problem of universal clustering using responses of crowd workers, without knowledge of worker reliability or task difficulty. We model stochastic worker response distributions by incorporating traits of memory for similar objects and traits of distance among differing objects. We are particularly interested in two limiting worker types—temporary workers who retain no memory of responses and long-term workers with memory. We first define clustering algorithms for these limiting cases and then integrate them into an algorithm for the unified worker model. We prove asymptotic consistency of the algorithms and establish sufficient conditions on the sample complexity of the algorithm. Converse arguments establish necessary conditions on sample complexity, proving that the defined algorithms are asymptotically order-optimal in cost.
Tasks
Published	2016-10-05
URL	http://arxiv.org/abs/1610.02276v1
PDF	http://arxiv.org/pdf/1610.02276v1.pdf
PWC	https://paperswithcode.com/paper/universal-clustering-via-crowdsourcing
Repo
Framework

Boundary-aware Instance Segmentation


Title	Boundary-aware Instance Segmentation
Authors	Zeeshan Hayder, Xuming He, Mathieu Salzmann
Abstract	We address the problem of instance-level semantic segmentation, which aims at jointly detecting, segmenting and classifying every individual object in an image. In this context, existing methods typically propose candidate objects, usually as bounding boxes, and directly predict a binary mask within each such proposal. As a consequence, they cannot recover from errors in the object candidate generation process, such as too small or shifted boxes. In this paper, we introduce a novel object segment representation based on the distance transform of the object masks. We then design an object mask network (OMN) with a new residual-deconvolution architecture that infers such a representation and decodes it into the final binary object mask. This allows us to predict masks that go beyond the scope of the bounding boxes and are thus robust to inaccurate object candidates. We integrate our OMN into a Multitask Network Cascade framework, and learn the resulting boundary-aware instance segmentation (BAIS) network in an end-to-end manner. Our experiments on the PASCAL VOC 2012 and the Cityscapes datasets demonstrate the benefits of our approach, which outperforms the state-of-the-art in both object proposal generation and instance segmentation.
Tasks	Instance Segmentation, Object Proposal Generation, Semantic Segmentation
Published	2016-12-09
URL	http://arxiv.org/abs/1612.03129v2
PDF	http://arxiv.org/pdf/1612.03129v2.pdf
PWC	https://paperswithcode.com/paper/boundary-aware-instance-segmentation
Repo
Framework

Learning to Segment Object Candidates via Recursive Neural Networks


Title	Learning to Segment Object Candidates via Recursive Neural Networks
Authors	Tianshui Chen, Liang Lin, Xian Wu, Nong Xiao, Xiaonan Luo
Abstract	To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple yet effective approach for segmenting object proposals via a deep architecture of recursive neural networks (ReNNs), which hierarchically groups regions for detecting object candidates over scales. Unlike traditional methods that mainly adopt fixed similarity measures for merging regions or finding object proposals, our approach adaptively learns the region merging similarity and the objectness measure during the process of hierarchical region grouping. Specifically, guided by a structured loss, the ReNN model jointly optimizes the cross-region similarity metric with the region merging process as well as the objectness prediction. During inference of the object proposal generation, we introduce randomness into the greedy search to cope with the ambiguity of grouping regions. Extensive experiments on standard benchmarks, e.g., PASCAL VOC and ImageNet, suggest that our approach is capable of producing object proposals with high recall while well preserving the object boundaries and outperforms other existing methods in both accuracy and efficiency.
Tasks	Object Detection, Object Proposal Generation
Published	2016-12-04
URL	http://arxiv.org/abs/1612.01057v4
PDF	http://arxiv.org/pdf/1612.01057v4.pdf
PWC	https://paperswithcode.com/paper/learning-to-segment-object-candidates-via
Repo
Framework