October 18, 2019

2831 words 14 mins read

Paper Group ANR 651

Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis. Interactive Image Manipulation with Natural Language Instruction Commands. 3D Convolutional Neural Networks for Classification of Functional Connectomes. Bridging the gap between regret minimization and best arm identification, with application to A/B te …

Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis


Title	Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis
Authors	Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi
Abstract	Japanese predicate-argument structure (PAS) analysis involves zero anaphora resolution, which is notoriously difficult. To improve the performance of Japanese PAS analysis, it is straightforward to increase the size of corpora annotated with PAS. However, since it is prohibitively expensive, it is promising to take advantage of a large amount of raw corpora. In this paper, we propose a novel Japanese PAS analysis model based on semi-supervised adversarial training with a raw corpus. In our experiments, our model outperforms existing state-of-the-art models for Japanese PAS analysis.
Tasks
Published	2018-06-04
URL	http://arxiv.org/abs/1806.00971v2
PDF	http://arxiv.org/pdf/1806.00971v2.pdf
PWC	https://paperswithcode.com/paper/neural-adversarial-training-for-semi
Repo
Framework

Interactive Image Manipulation with Natural Language Instruction Commands


Title	Interactive Image Manipulation with Natural Language Instruction Commands
Authors	Seitaro Shinagawa, Koichiro Yoshino, Sakriani Sakti, Yu Suzuki, Satoshi Nakamura
Abstract	We propose an interactive image-manipulation system with natural language instruction, which can generate a target image from a source image and an instruction that describes the difference between the source and the target image. The system makes it possible to modify a generated image interactively and make natural language conditioned image generation more controllable. We construct a neural network that handles image vectors in latent space to transform the source vector to the target vector by using the vector of instruction. The experimental results indicate that the proposed framework successfully generates the target image by using a source image and an instruction on manipulation in our dataset.
Tasks	Image Generation
Published	2018-02-23
URL	http://arxiv.org/abs/1802.08645v1
PDF	http://arxiv.org/pdf/1802.08645v1.pdf
PWC	https://paperswithcode.com/paper/interactive-image-manipulation-with-natural
Repo
Framework

3D Convolutional Neural Networks for Classification of Functional Connectomes


Title	3D Convolutional Neural Networks for Classification of Functional Connectomes
Authors	Meenakshi Khosla, Keith Jamison, Amy Kuceyeski, Mert Sabuncu
Abstract	Resting-state functional MRI (rs-fMRI) scans hold the potential to serve as a diagnostic or prognostic tool for a wide variety of conditions, such as autism, Alzheimer’s disease, and stroke. While a growing number of studies have demonstrated the promise of machine learning algorithms for rs-fMRI based clinical or behavioral prediction, most prior models have been limited in their capacity to exploit the richness of the data. For example, classification techniques applied to rs-fMRI often rely on region-based summary statistics and/or linear models. In this work, we propose a novel volumetric Convolutional Neural Network (CNN) framework that takes advantage of the full-resolution 3D spatial structure of rs-fMRI data and fits non-linear predictive models. We showcase our approach on a challenging large-scale dataset (ABIDE, with N > 2,000) and report state-of-the-art accuracy results on rs-fMRI-based discrimination of autism patients and healthy controls.
Tasks
Published	2018-06-11
URL	http://arxiv.org/abs/1806.04209v2
PDF	http://arxiv.org/pdf/1806.04209v2.pdf
PWC	https://paperswithcode.com/paper/3d-convolutional-neural-networks-for
Repo
Framework

Bridging the gap between regret minimization and best arm identification, with application to A/B tests


Title	Bridging the gap between regret minimization and best arm identification, with application to A/B tests
Authors	Rémy Degenne, Thomas Nedelec, Clément Calauzènes, Vianney Perchet
Abstract	State of the art online learning procedures focus either on selecting the best alternative (“best arm identification”) or on minimizing the cost (the “regret”). We merge these two objectives by providing the theoretical analysis of cost minimizing algorithms that are also delta-PAC (with a proven guaranteed bound on the decision time), hence fulfilling at the same time regret minimization and best arm identification. This analysis sheds light on the common observation that ill-callibrated UCB-algorithms minimize regret while still identifying quickly the best arm. We also extend these results to the non-iid case faced by many practitioners. This provides a technique to make cost versus decision time compromise when doing adaptive tests with applications ranging from website A/B testing to clinical trials.
Tasks
Published	2018-10-09
URL	http://arxiv.org/abs/1810.04088v2
PDF	http://arxiv.org/pdf/1810.04088v2.pdf
PWC	https://paperswithcode.com/paper/bridging-the-gap-between-regret-minimization
Repo
Framework

VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions


Title	VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions
Authors	Qing Li, Qingyi Tao, Shafiq Joty, Jianfei Cai, Jiebo Luo
Abstract	Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even more importance compared with the answer itself, since it makes the question and answering process more understandable and traceable. To this end, we propose a new task of VQA-E (VQA with Explanation), where the computational models are required to generate an explanation with the predicted answer. We first construct a new dataset, and then frame the VQA-E problem in a multi-task learning architecture. Our VQA-E dataset is automatically derived from the VQA v2 dataset by intelligently exploiting the available captions. We have conducted a user study to validate the quality of explanations synthesized by our method. We quantitatively show that the additional supervision from explanations can not only produce insightful textual sentences to justify the answers, but also improve the performance of answer prediction. Our model outperforms the state-of-the-art methods by a clear margin on the VQA v2 dataset.
Tasks	Multi-Task Learning, Question Answering, Visual Question Answering
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07464v2
PDF	http://arxiv.org/pdf/1803.07464v2.pdf
PWC	https://paperswithcode.com/paper/vqa-e-explaining-elaborating-and-enhancing
Repo
Framework

Universal Image Manipulation Detection using Deep Siamese Convolutional Neural Network


Title	Universal Image Manipulation Detection using Deep Siamese Convolutional Neural Network
Authors	Aniruddha Mazumdar, Jaya Singh, Yosha Singh Tomar, Prabin Kumar Bora
Abstract	Detection of different types of image editing operations carried out on an image is an important problem in image forensics. It gives the information about the processing history of an image, and also can expose forgeries present in an image. There have been few methods proposed to detect different types of image editing operations in a single framework. However, all the operations have to be known a priori in the training phase. But, in real-forensics scenarios it may not be possible to know about the editing operations carried out on an image. To solve this problem, we propose a novel deep learning-based method which can differentiate between different types of image editing operations. The proposed method classifies image patches in a pair-wise fashion as either similarly or differently processed using a deep siamese neural network. Once the network learns feature that can discriminate between different image editing operations, it can differentiate between different image editing operations not present in the training stage. The experimental results show the efficacy of the proposed method in detecting/discriminating different image editing operations.
Tasks	Image Manipulation Detection
Published	2018-08-20
URL	http://arxiv.org/abs/1808.06323v2
PDF	http://arxiv.org/pdf/1808.06323v2.pdf
PWC	https://paperswithcode.com/paper/universal-image-manipulation-detection-using
Repo
Framework

Improving Generalization of Deep Neural Networks by Leveraging Margin Distribution


Title	Improving Generalization of Deep Neural Networks by Leveraging Margin Distribution
Authors	Shen-Huan Lyu, Lu Wang, Zhi-Hua Zhou
Abstract	Recent researches use margin theory to analyze the generalization performance for deep neural networks. The main results are based on the spectrally-normalized minimum margin. However, optimizing the minimum margin ignores a mass of information about margin distribution which is crucial to generalization performance. In this paper, we prove a generalization bound dominated by a ratio of the margin standard deviation to the margin mean, where the huge magnitude of spectral norms is reduced. Compared with the spectral norm terms in the existing results, the margin ratio term in our bound is orders of magnitude better in practice. On the other hand, our bound inspires us to optimize the margin ratio. We utilize a convex margin distribution loss function on the deep neural networks to validate our theoretical results. Experiments and visualizations confirm the effectiveness of our approach in terms of performance and representation learning ability.
Tasks	Representation Learning
Published	2018-12-27
URL	https://arxiv.org/abs/1812.10761v2
PDF	https://arxiv.org/pdf/1812.10761v2.pdf
PWC	https://paperswithcode.com/paper/optimal-margin-distribution-network
Repo
Framework

Composite Gaussian Processes: Scalable Computation and Performance Analysis


Title	Composite Gaussian Processes: Scalable Computation and Performance Analysis
Authors	Xiuming Liu, Dave Zachariah, Edith C. H. Ngai
Abstract	Gaussian process (GP) models provide a powerful tool for prediction but are computationally prohibitive using large data sets. In such scenarios, one has to resort to approximate methods. We derive an approximation based on a composite likelihood approach using a general belief updating framework, which leads to a recursive computation of the predictor as well as of learning the hyper-parameters. We then provide an analysis of the derived composite GP model in predictive and information-theoretic terms. Finally, we evaluate the approximation with both synthetic data and a real-world application.
Tasks	Gaussian Processes
Published	2018-01-31
URL	http://arxiv.org/abs/1802.00045v1
PDF	http://arxiv.org/pdf/1802.00045v1.pdf
PWC	https://paperswithcode.com/paper/composite-gaussian-processes-scalable
Repo
Framework

Accelerating Large Scale Knowledge Distillation via Dynamic Importance Sampling


Title	Accelerating Large Scale Knowledge Distillation via Dynamic Importance Sampling
Authors	Minghan Li, Tanli Zuo, Ruicheng Li, Martha White, Weishi Zheng
Abstract	Knowledge distillation is an effective technique that transfers knowledge from a large teacher model to a shallow student. However, just like massive classification, large scale knowledge distillation also imposes heavy computational costs on training models of deep neural networks, as the softmax activations at the last layer involve computing probabilities over numerous classes. In this work, we apply the idea of importance sampling which is often used in Neural Machine Translation on large scale knowledge distillation. We present a method called dynamic importance sampling, where ranked classes are sampled from a dynamic distribution derived from the interaction between the teacher and student in full distillation. We highlight the utility of our proposal prior which helps the student capture the main information in the loss function. Our approach manages to reduce the computational cost at training time while maintaining the competitive performance on CIFAR-100 and Market-1501 person re-identification datasets.
Tasks	Machine Translation, Person Re-Identification
Published	2018-12-03
URL	http://arxiv.org/abs/1812.00914v1
PDF	http://arxiv.org/pdf/1812.00914v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-large-scale-knowledge
Repo
Framework

On Implicit Filter Level Sparsity in Convolutional Neural Networks


Title	On Implicit Filter Level Sparsity in Convolutional Neural Networks
Authors	Dushyant Mehta, Kwang In Kim, Christian Theobalt
Abstract	We investigate filter level sparsity that emerges in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay. We conduct an extensive experimental study casting our initial findings into hypotheses and conclusions about the mechanisms underlying the emergent filter level sparsity. This study allows new insight into the performance gap obeserved between adapative and non-adaptive gradient descent methods in practice. Further, analysis of the effect of training strategies and hyperparameters on the sparsity leads to practical suggestions in designing CNN training strategies enabling us to explore the tradeoffs between feature selectivity, network capacity, and generalization performance. Lastly, we show that the implicit sparsity can be harnessed for neural network speedup at par or better than explicit sparsification / pruning approaches, with no modifications to the typical training pipeline required.
Tasks	L2 Regularization
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12495v2
PDF	http://arxiv.org/pdf/1811.12495v2.pdf
PWC	https://paperswithcode.com/paper/on-implicit-filter-level-sparsity-in
Repo
Framework

Hypergraph Spectral Clustering in the Weighted Stochastic Block Model


Title	Hypergraph Spectral Clustering in the Weighted Stochastic Block Model
Authors	Kwangjun Ahn, Kangwook Lee, Changho Suh
Abstract	Spectral clustering is a celebrated algorithm that partitions objects based on pairwise similarity information. While this approach has been successfully applied to a variety of domains, it comes with limitations. The reason is that there are many other applications in which only \emph{multi}-way similarity measures are available. This motivates us to explore the multi-way measurement setting. In this work, we develop two algorithms intended for such setting: Hypergraph Spectral Clustering (HSC) and Hypergraph Spectral Clustering with Local Refinement (HSCLR). Our main contribution lies in performance analysis of the poly-time algorithms under a random hypergraph model, which we name the weighted stochastic block model, in which objects and multi-way measures are modeled as nodes and weights of hyperedges, respectively. Denoting by $n$ the number of nodes, our analysis reveals the following: (1) HSC outputs a partition which is better than a random guess if the sum of edge weights (to be explained later) is $\Omega(n)$; (2) HSC outputs a partition which coincides with the hidden partition except for a vanishing fraction of nodes if the sum of edge weights is $\omega(n)$; and (3) HSCLR exactly recovers the hidden partition if the sum of edge weights is on the order of $n \log n$. Our results improve upon the state of the arts recently established under the model and they firstly settle the order-wise optimal results for the binary edge weight case. Moreover, we show that our results lead to efficient sketching algorithms for subspace clustering, a computer vision application. Lastly, we show that HSCLR achieves the information-theoretic limits for a special yet practically relevant model, thereby showing no computational barrier for the case.
Tasks
Published	2018-05-23
URL	http://arxiv.org/abs/1805.08956v1
PDF	http://arxiv.org/pdf/1805.08956v1.pdf
PWC	https://paperswithcode.com/paper/hypergraph-spectral-clustering-in-the
Repo
Framework

Co-evolving Real-Time Strategy Game Micro


Title	Co-evolving Real-Time Strategy Game Micro
Authors	Navin K Adhikari, Sushil J. Louis, Siming Liu, Walker Spurgeon
Abstract	We investigate competitive co-evolution of unit micromanagement in real-time strategy games. Although good long-term macro-strategy and good short-term unit micromanagement both impact real-time strategy games performance, this paper focuses on generating quality micro. Better micro, for example, can help players win skirmishes and battles even when outnumbered. Prior work has shown that we can evolve micro to beat a given opponent. We remove the need for a good opponent to evolve against by using competitive co-evolution to evolve high-quality micro for both sides from scratch. We first co-evolve micro to control a group of ranged units versus a group of melee units. We then move to co-evolve micro for a group of ranged and melee units versus a group of ranged and melee units. Results show that competitive co-evolution produces good quality micro and when combined with the well-known techniques of fitness sharing, shared sampling, and a hall of fame takes less time to produce better quality micro than simple co-evolution. We believe these results indicate the viability of co-evolutionary approaches for generating good unit micro-management.
Tasks	Real-Time Strategy Games
Published	2018-03-27
URL	http://arxiv.org/abs/1803.10314v1
PDF	http://arxiv.org/pdf/1803.10314v1.pdf
PWC	https://paperswithcode.com/paper/co-evolving-real-time-strategy-game-micro
Repo
Framework

Real-Time Workload Classification during Driving using HyperNetworks


Title	Real-Time Workload Classification during Driving using HyperNetworks
Authors	Ruohan Wang, Pierluigi V. Amadori, Yiannis Demiris
Abstract	Classifying human cognitive states from behavioral and physiological signals is a challenging problem with important applications in robotics. The problem is challenging due to the data variability among individual users, and sensor artefacts. In this work, we propose an end-to-end framework for real-time cognitive workload classification with mixture Hyper Long Short Term Memory Networks, a novel variant of HyperNetworks. Evaluating the proposed approach on an eye-gaze pattern dataset collected from simulated driving scenarios of different cognitive demands, we show that the proposed framework outperforms previous baseline methods and achieves 83.9% precision and 87.8% recall during test. We also demonstrate the merit of our proposed architecture by showing improved performance over other LSTM-based methods.
Tasks
Published	2018-10-07
URL	http://arxiv.org/abs/1810.03145v1
PDF	http://arxiv.org/pdf/1810.03145v1.pdf
PWC	https://paperswithcode.com/paper/real-time-workload-classification-during
Repo
Framework

Person Re-Identification in Identity Regression Space


Title	Person Re-Identification in Identity Regression Space
Authors	Hanxiao Wang, Xiatian Zhu, Shaogang Gong, Tao Xiang
Abstract	Most existing person re-identification (re-id) methods are unsuitable for real-world deployment due to two reasons: Unscalability to large population size, and Inadaptability over time. In this work, we present a unified solution to address both problems. Specifically, we propose to construct an Identity Regression Space (IRS) based on embedding different training person identities (classes) and formulate re-id as a regression problem solved by identity regression in the IRS. The IRS approach is characterised by a closed-form solution with high learning efficiency and an inherent incremental learning capability with human-in-the-loop. Extensive experiments on four benchmarking datasets(VIPeR, CUHK01, CUHK03 and Market-1501) show that the IRS model not only outperforms state-of-the-art re-id methods, but also is more scalable to large re-id population size by rapidly updating model and actively selecting informative samples with reduced human labelling effort.
Tasks	Person Re-Identification
Published	2018-06-25
URL	http://arxiv.org/abs/1806.09695v1
PDF	http://arxiv.org/pdf/1806.09695v1.pdf
PWC	https://paperswithcode.com/paper/person-re-identification-in-identity
Repo
Framework

Asymptotic optimality of adaptive importance sampling


Title	Asymptotic optimality of adaptive importance sampling
Authors	Bernard Delyon, François Portier
Abstract	Adaptive importance sampling (AIS) uses past samples to update the \textit{sampling policy} $q_t$ at each stage $t$. Each stage $t$ is formed with two steps : (i) to explore the space with $n_t$ points according to $q_t$ and (ii) to exploit the current amount of information to update the sampling policy. The very fundamental question raised in this paper concerns the behavior of empirical sums based on AIS. Without making any assumption on the allocation policy $n_t$, the theory developed involves no restriction on the split of computational resources between the explore (i) and the exploit (ii) step. It is shown that AIS is asymptotically optimal : the asymptotic behavior of AIS is the same as some “oracle” strategy that knows the targeted sampling policy from the beginning. From a practical perspective, weighted AIS is introduced, a new method that allows to forget poor samples from early stages.
Tasks
Published	2018-06-04
URL	http://arxiv.org/abs/1806.00989v2
PDF	http://arxiv.org/pdf/1806.00989v2.pdf
PWC	https://paperswithcode.com/paper/asymptotic-optimality-of-adaptive-importance
Repo
Framework