July 28, 2019

3053 words 15 mins read

Paper Group ANR 309

Recasting Residual-based Local Descriptors as Convolutional Neural Networks: an Application to Image Forgery Detection. Cartoonish sketch-based face editing in videos using identity deformation transfer. Towards personalized human AI interaction - adapting the behavior of AI agents using neural signatures of subjective interest. Learning to Use Lea …

Recasting Residual-based Local Descriptors as Convolutional Neural Networks: an Application to Image Forgery Detection


Title	Recasting Residual-based Local Descriptors as Convolutional Neural Networks: an Application to Image Forgery Detection
Authors	Davide Cozzolino, Giovanni Poggi, Luisa Verdoliva
Abstract	Local descriptors based on the image noise residual have proven extremely effective for a number of forensic applications, like forgery detection and localization. Nonetheless, motivated by promising results in computer vision, the focus of the research community is now shifting on deep learning. In this paper we show that a class of residual-based descriptors can be actually regarded as a simple constrained convolutional neural network (CNN). Then, by relaxing the constraints, and fine-tuning the net on a relatively small training set, we obtain a significant performance improvement with respect to the conventional detector.
Tasks
Published	2017-03-14
URL	http://arxiv.org/abs/1703.04615v1
PDF	http://arxiv.org/pdf/1703.04615v1.pdf
PWC	https://paperswithcode.com/paper/recasting-residual-based-local-descriptors-as
Repo
Framework

Cartoonish sketch-based face editing in videos using identity deformation transfer


Title	Cartoonish sketch-based face editing in videos using identity deformation transfer
Authors	Long Zhao, Fangda Han, Xi Peng, Xun Zhang, Mubbasir Kapadia, Vladimir Pavlovic, Dimitris N. Metaxas
Abstract	We address the problem of using hand-drawn sketches to create exaggerated deformations to faces in videos, such as enlarging the shape or modifying the position of eyes or mouth. This task is formulated as a 3D face model reconstruction and deformation problem. We first recover the facial identity and expressions from the video by fitting a face morphable model for each frame. At the same time, user’s editing intention is recognized from input sketches as a set of facial modifications. Then a novel identity deformation algorithm is proposed to transfer these facial deformations from 2D space to the 3D facial identity directly while preserving the facial expressions. After an optional stage for further refining the 3D face model, these changes are propagated to the whole video with the modified identity. Both the user study and experimental results demonstrate that our sketching framework can help users effectively edit facial identities in videos, while high consistency and fidelity are ensured at the same time.
Tasks
Published	2017-03-25
URL	http://arxiv.org/abs/1703.08738v3
PDF	http://arxiv.org/pdf/1703.08738v3.pdf
PWC	https://paperswithcode.com/paper/cartoonish-sketch-based-face-editing-in
Repo
Framework

Towards personalized human AI interaction - adapting the behavior of AI agents using neural signatures of subjective interest


Title	Towards personalized human AI interaction - adapting the behavior of AI agents using neural signatures of subjective interest
Authors	Victor Shih, David C Jangraw, Paul Sajda, Sameer Saproo
Abstract	Reinforcement Learning AI commonly uses reward/penalty signals that are objective and explicit in an environment – e.g. game score, completion time, etc. – in order to learn the optimal strategy for task performance. However, Human-AI interaction for such AI agents should include additional reinforcement that is implicit and subjective – e.g. human preferences for certain AI behavior – in order to adapt the AI behavior to idiosyncratic human preferences. Such adaptations would mirror naturally occurring processes that increase trust and comfort during social interactions. Here, we show how a hybrid brain-computer-interface (hBCI), which detects an individual’s level of interest in objects/events in a virtual environment, can be used to adapt the behavior of a Deep Reinforcement Learning AI agent that is controlling a virtual autonomous vehicle. Specifically, we show that the AI learns a driving strategy that maintains a safe distance from a lead vehicle, and most novelly, preferentially slows the vehicle when the human passengers of the vehicle encounter objects of interest. This adaptation affords an additional 20% viewing time for subjectively interesting objects. This is the first demonstration of how an hBCI can be used to provide implicit reinforcement to an AI agent in a way that incorporates user preferences into the control system.
Tasks
Published	2017-09-14
URL	http://arxiv.org/abs/1709.04574v1
PDF	http://arxiv.org/pdf/1709.04574v1.pdf
PWC	https://paperswithcode.com/paper/towards-personalized-human-ai-interaction
Repo
Framework

Learning to Use Learners’ Advice


Title	Learning to Use Learners’ Advice
Authors	Adish Singla, Hamed Hassani, Andreas Krause
Abstract	In this paper, we study a variant of the framework of online learning using expert advice with limited/bandit feedback. We consider each expert as a learning entity, seeking to more accurately reflecting certain real-world applications. In our setting, the feedback at any time $t$ is limited in a sense that it is only available to the expert $i^t$ that has been selected by the central algorithm (forecaster), \emph{i.e.}, only the expert $i^t$ receives feedback from the environment and gets to learn at time $t$. We consider a generic black-box approach whereby the forecaster does not control or know the learning dynamics of the experts apart from knowing the following no-regret learning property: the average regret of any expert $j$ vanishes at a rate of at least $O(t_j^{\regretRate-1})$ with $t_j$ learning steps where $\regretRate \in [0, 1]$ is a parameter. In the spirit of competing against the best action in hindsight in multi-armed bandits problem, our goal here is to be competitive w.r.t. the cumulative losses the algorithm could receive by following the policy of always selecting one expert. We prove the following hardness result: without any coordination between the forecaster and the experts, it is impossible to design a forecaster achieving no-regret guarantees. In order to circumvent this hardness result, we consider a practical assumption allowing the forecaster to “guide” the learning process of the experts by filtering/blocking some of the feedbacks observed by them from the environment, \emph{i.e.}, not allowing the selected expert $i^t$ to learn at time $t$ for some time steps. Then, we design a novel no-regret learning algorithm \algo for this problem setting by carefully guiding the feedbacks observed by experts. We prove that \algo achieves the worst-case expected cumulative regret of $O(\Time^\frac{1}{2 - \regretRate})$ after $\Time$ time steps.
Tasks	Multi-Armed Bandits
Published	2017-02-16
URL	http://arxiv.org/abs/1702.04825v2
PDF	http://arxiv.org/pdf/1702.04825v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-use-learners-advice
Repo
Framework

Phase Congruency Parameter Optimization for Enhanced Detection of Image Features for both Natural and Medical Applications


Title	Phase Congruency Parameter Optimization for Enhanced Detection of Image Features for both Natural and Medical Applications
Authors	Seyed Mohammad Mahdi Alavi, Yunyan Zhang
Abstract	Following the presentation and proof of the hypothesis that image features are particularly perceived at points where the Fourier components are maximally in phase, the concept of phase congruency (PC) is introduced. Subsequently, a two-dimensional multi-scale phase congruency (2D-MSPC) is developed, which has been an important tool for detecting and evaluation of image features. However, the 2D-MSPC requires many parameters to be appropriately tuned for optimal image features detection. In this paper, we defined a criterion for parameter optimization of the 2D-MSPC, which is a function of its maximum and minimum moments. We formulated the problem in various optimal and suboptimal frameworks, and discussed the conditions and features of the suboptimal solutions. The effectiveness of the proposed method was verified through several examples, ranging from natural objects to medical images from patients with a neurological disease, multiple sclerosis.
Tasks
Published	2017-05-05
URL	http://arxiv.org/abs/1705.02102v1
PDF	http://arxiv.org/pdf/1705.02102v1.pdf
PWC	https://paperswithcode.com/paper/phase-congruency-parameter-optimization-for
Repo
Framework

Stochastic Configuration Networks Ensemble for Large-Scale Data Analytics


Title	Stochastic Configuration Networks Ensemble for Large-Scale Data Analytics
Authors	Dianhui Wang, Caihao Cui
Abstract	This paper presents a fast decorrelated neuro-ensemble with heterogeneous features for large-scale data analytics, where stochastic configuration networks (SCNs) are employed as base learner models and the well-known negative correlation learning (NCL) strategy is adopted to evaluate the output weights. By feeding a large number of samples into the SCN base models, we obtain a huge sized linear equation system which is difficult to be solved by means of computing a pseudo-inverse used in the least squares method. Based on the group of heterogeneous features, the block Jacobi and Gauss-Seidel methods are employed to iteratively evaluate the output weights, and a convergence analysis is given with a demonstration on the uniqueness of these iterative solutions. Experiments with comparisons on two large-scale datasets are carried out, and the system robustness with respect to the regularizing factor used in NCL is given. Results indicate that the proposed ensemble learning techniques have good potential for resolving large-scale data modelling problems.
Tasks
Published	2017-07-02
URL	http://arxiv.org/abs/1707.00300v2
PDF	http://arxiv.org/pdf/1707.00300v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-configuration-networks-ensemble
Repo
Framework

Provenance and Pseudo-Provenance for Seeded Learning-Based Automated Test Generation


Title	Provenance and Pseudo-Provenance for Seeded Learning-Based Automated Test Generation
Authors	Alex Groce, Josie Holmes
Abstract	Many methods for automated software test generation, including some that explicitly use machine learning (and some that use ML more broadly conceived) derive new tests from existing tests (often referred to as seeds). Often, the seed tests from which new tests are derived are manually constructed, or at least simpler than the tests that are produced as the final outputs of such test generators. We propose annotation of generated tests with a provenance (trail) showing how individual generated tests of interest (especially failing tests) derive from seed tests, and how the population of generated tests relates to the original seed tests. In some cases, post-processing of generated tests can invalidate provenance information, in which case we also propose a method for attempting to construct “pseudo-provenance” describing how the tests could have been (partly) generated from seeds.
Tasks
Published	2017-11-05
URL	http://arxiv.org/abs/1711.01661v2
PDF	http://arxiv.org/pdf/1711.01661v2.pdf
PWC	https://paperswithcode.com/paper/provenance-and-pseudo-provenance-for-seeded
Repo
Framework

Scalable Online Convolutional Sparse Coding


Title	Scalable Online Convolutional Sparse Coding
Authors	Yaqing Wang, Quanming Yao, James T. Kwok, Lionel M. Ni
Abstract	Convolutional sparse coding (CSC) improves sparse coding by learning a shift-invariant dictionary from the data. However, existing CSC algorithms operate in the batch mode and are expensive, in terms of both space and time, on large datasets. In this paper, we alleviate these problems by using online learning. The key is a reformulation of the CSC objective so that convolution can be handled easily in the frequency domain and much smaller history matrices are needed. We use the alternating direction method of multipliers (ADMM) to solve the resulting optimization problem and the ADMM subproblems have efficient closed-form solutions. Theoretical analysis shows that the learned dictionary converges to a stationary point of the optimization problem. Extensive experiments show that convergence of the proposed method is much faster and its reconstruction performance is also better. Moreover, while existing CSC algorithms can only run on a small number of images, the proposed method can handle at least ten times more images.
Tasks
Published	2017-06-21
URL	http://arxiv.org/abs/1706.06972v3
PDF	http://arxiv.org/pdf/1706.06972v3.pdf
PWC	https://paperswithcode.com/paper/scalable-online-convolutional-sparse-coding
Repo
Framework

Automatically Extracting Action Graphs from Materials Science Synthesis Procedures


Title	Automatically Extracting Action Graphs from Materials Science Synthesis Procedures
Authors	Sheshera Mysore, Edward Kim, Emma Strubell, Ao Liu, Haw-Shiuan Chang, Srikrishna Kompella, Kevin Huang, Andrew McCallum, Elsa Olivetti
Abstract	Computational synthesis planning approaches have achieved recent success in organic chemistry, where tabulated synthesis procedures are readily available for supervised learning. The syntheses of inorganic materials, however, exist primarily as natural language narratives contained within scientific journal articles. This synthesis information must first be extracted from the text in order to enable analogous synthesis planning methods for inorganic materials. In this work, we present a system for automatically extracting structured representations of synthesis procedures from the texts of materials science journal articles that describe explicit, experimental syntheses of inorganic compounds. We define the structured representation as a set of linked events made up of extracted scientific entities and evaluate two unsupervised approaches for extracting these structures on expert-annotated articles: a strong heuristic baseline and a generative model of procedural text. We also evaluate a variety of supervised models for extracting scientific entities. Our results provide insight into the nature of the data and directions for further work in this exciting new area of research.
Tasks
Published	2017-11-18
URL	http://arxiv.org/abs/1711.06872v2
PDF	http://arxiv.org/pdf/1711.06872v2.pdf
PWC	https://paperswithcode.com/paper/automatically-extracting-action-graphs-from
Repo
Framework

Acoustic-To-Word Model Without OOV


Title	Acoustic-To-Word Model Without OOV
Authors	Jinyu Li, Guoli Ye, Rui Zhao, Jasha Droppo, Yifan Gong
Abstract	Recently, the acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion was shown as a natural end-to-end model directly targeting words as output units. However, this type of word-based CTC model suffers from the out-of-vocabulary (OOV) issue as it can only model limited number of words in the output layer and maps all the remaining words into an OOV output node. Therefore, such word-based CTC model can only recognize the frequent words modeled by the network output nodes. It also cannot easily handle the hot-words which emerge after the model is trained. In this study, we improve the acoustic-to-word model with a hybrid CTC model which can predict both words and characters at the same time. With a shared-hidden-layer structure and modular design, the alignments of words generated from the word-based CTC and the character-based CTC are synchronized. Whenever the acoustic-to-word model emits an OOV token, we back off that OOV segment to the word output generated from the character-based CTC, hence solving the OOV or hot-words issue. Evaluated on a Microsoft Cortana voice assistant task, the proposed model can reduce the errors introduced by the OOV output token in the acoustic-to-word model by 30%.
Tasks
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10136v1
PDF	http://arxiv.org/pdf/1711.10136v1.pdf
PWC	https://paperswithcode.com/paper/acoustic-to-word-model-without-oov
Repo
Framework

The Informativeness of $k$-Means for Learning Mixture Models


Title	The Informativeness of $k$-Means for Learning Mixture Models
Authors	Zhaoqiang Liu, Vincent Y. F. Tan
Abstract	The learning of mixture models can be viewed as a clustering problem. Indeed, given data samples independently generated from a mixture of distributions, we often would like to find the correct target clustering of the samples according to which component distribution they were generated from. For a clustering problem, practitioners often choose to use the simple k-means algorithm. k-means attempts to find an optimal clustering which minimizes the sum-of-squared distance between each point and its cluster center. In this paper, we provide sufficient conditions for the closeness of any optimal clustering and the correct target clustering assuming that the data samples are generated from a mixture of log-concave distributions. Moreover, we show that under similar or even weaker conditions on the mixture model, any optimal clustering for the samples with reduced dimensionality is also close to the correct target clustering. These results provide intuition for the informativeness of k-means (with and without dimensionality reduction) as an algorithm for learning mixture models. We verify the correctness of our theorems using numerical experiments and demonstrate using datasets with reduced dimensionality significant speed ups for the time required to perform clustering.
Tasks	Dimensionality Reduction
Published	2017-03-30
URL	https://arxiv.org/abs/1703.10534v3
PDF	https://arxiv.org/pdf/1703.10534v3.pdf
PWC	https://paperswithcode.com/paper/the-informativeness-of-k-means-and
Repo
Framework

Towards a New Interpretation of Separable Convolutions


Title	Towards a New Interpretation of Separable Convolutions
Authors	Tapabrata Ghosh
Abstract	In recent times, the use of separable convolutions in deep convolutional neural network architectures has been explored. Several researchers, most notably (Chollet, 2016) and (Ghosh, 2017) have used separable convolutions in their deep architectures and have demonstrated state of the art or close to state of the art performance. However, the underlying mechanism of action of separable convolutions are still not fully understood. Although their mathematical definition is well understood as a depthwise convolution followed by a pointwise convolution, deeper interpretations such as the extreme Inception hypothesis (Chollet, 2016) have failed to provide a thorough explanation of their efficacy. In this paper, we propose a hybrid interpretation that we believe is a better model for explaining the efficacy of separable convolutions.
Tasks
Published	2017-01-16
URL	http://arxiv.org/abs/1701.04489v1
PDF	http://arxiv.org/pdf/1701.04489v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-new-interpretation-of-separable
Repo
Framework

Subspace Clustering with Missing and Corrupted Data


Title	Subspace Clustering with Missing and Corrupted Data
Authors	Zachary Charles, Amin Jalali, Rebecca Willett
Abstract	Given full or partial information about a collection of points that lie close to a union of several subspaces, subspace clustering refers to the process of clustering the points according to their subspace and identifying the subspaces. One popular approach, sparse subspace clustering (SSC), represents each sample as a weighted combination of the other samples, with weights of minimal $\ell_1$ norm, and then uses those learned weights to cluster the samples. SSC is stable in settings where each sample is contaminated by a relatively small amount of noise. However, when there is a significant amount of additive noise, or a considerable number of entries are missing, theoretical guarantees are scarce. In this paper, we study a robust variant of SSC and establish clustering guarantees in the presence of corrupted or missing data. We give explicit bounds on amount of noise and missing data that the algorithm can tolerate, both in deterministic settings and in a random generative model. Notably, our approach provides guarantees for higher tolerance to noise and missing data than existing analyses for this method. By design, the results hold even when we do not know the locations of the missing data; e.g., as in presence-only data.
Tasks
Published	2017-07-08
URL	http://arxiv.org/abs/1707.02461v2
PDF	http://arxiv.org/pdf/1707.02461v2.pdf
PWC	https://paperswithcode.com/paper/subspace-clustering-with-missing-and
Repo
Framework

Long Short-Term Memory for Japanese Word Segmentation


Title	Long Short-Term Memory for Japanese Word Segmentation
Authors	Yoshiaki Kitagawa, Mamoru Komachi
Abstract	This study presents a Long Short-Term Memory (LSTM) neural network approach to Japanese word segmentation (JWS). Previous studies on Chinese word segmentation (CWS) succeeded in using recurrent neural networks such as LSTM and gated recurrent units (GRU). However, in contrast to Chinese, Japanese includes several character types, such as hiragana, katakana, and kanji, that produce orthographic variations and increase the difficulty of word segmentation. Additionally, it is important for JWS tasks to consider a global context, and yet traditional JWS approaches rely on local features. In order to address this problem, this study proposes employing an LSTM-based approach to JWS. The experimental results indicate that the proposed model achieves state-of-the-art accuracy with respect to various Japanese corpora.
Tasks	Chinese Word Segmentation
Published	2017-09-23
URL	http://arxiv.org/abs/1709.08011v3
PDF	http://arxiv.org/pdf/1709.08011v3.pdf
PWC	https://paperswithcode.com/paper/long-short-term-memory-for-japanese-word
Repo
Framework

Revisiting Selectional Preferences for Coreference Resolution


Title	Revisiting Selectional Preferences for Coreference Resolution
Authors	Benjamin Heinzerling, Nafise Sadat Moosavi, Michael Strube
Abstract	Selectional preferences have long been claimed to be essential for coreference resolution. However, they are mainly modeled only implicitly by current coreference resolvers. We propose a dependency-based embedding model of selectional preferences which allows fine-grained compatibility judgments with high coverage. We show that the incorporation of our model improves coreference resolution performance on the CoNLL dataset, matching the state-of-the-art results of a more complex system. However, it comes with a cost that makes it debatable how worthwhile such improvements are.
Tasks	Coreference Resolution
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06456v1
PDF	http://arxiv.org/pdf/1707.06456v1.pdf
PWC	https://paperswithcode.com/paper/revisiting-selectional-preferences-for
Repo
Framework