Paper Group ANR 800
Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation. Convolutional Neural Networks for the segmentation of microcalcification in Mammography Imaging. Multi-Layer Sparse Coding: The Holistic Way. Single-Perspective Warps in Natural Image Stitching. Backdoor Embedding in Convolutional Neural Network Models via Invisib …
Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation
| Title | Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation |
| Authors | Han Guo, Ramakanth Pasunuru, Mohit Bansal |
| Abstract | An accurate abstractive summary of a document should contain all its salient information and should be logically entailed by the input document. We improve these important aspects of abstractive summarization via multi-task learning with the auxiliary tasks of question generation and entailment generation, where the former teaches the summarization model how to look for salient questioning-worthy details, and the latter teaches the model how to rewrite a summary which is a directed-logical subset of the input document. We also propose novel multi-task architectures with high-level (semantic) layer-specific sharing across multiple encoder and decoder layers of the three tasks, as well as soft-sharing mechanisms (and show performance ablations and analysis examples of each contribution). Overall, we achieve statistically significant improvements over the state-of-the-art on both the CNN/DailyMail and Gigaword datasets, as well as on the DUC-2002 transfer setup. We also present several quantitative and qualitative analysis studies of our model’s learned saliency and entailment skills. |
| Tasks | Abstractive Text Summarization, Multi-Task Learning, Question Generation |
| Published | 2018-05-28 |
| URL | http://arxiv.org/abs/1805.11004v1 |
| http://arxiv.org/pdf/1805.11004v1.pdf | |
| PWC | https://paperswithcode.com/paper/soft-layer-specific-multi-task-summarization |
| Repo | |
| Framework | |
Convolutional Neural Networks for the segmentation of microcalcification in Mammography Imaging
| Title | Convolutional Neural Networks for the segmentation of microcalcification in Mammography Imaging |
| Authors | Gabriele Valvano, Gianmarco Santini, Nicola Martini, Andrea Ripoli, Chiara Iacconi, Dante Chiappino, Daniele Della Latta |
| Abstract | Cluster of microcalcifications can be an early sign of breast cancer. In this paper we propose a novel approach based on convolutional neural networks for the detection and segmentation of microcalcification clusters. In this work we used 283 mammograms to train and validate our model, obtaining an accuracy of 98.22% in the detection of preliminary suspect regions and of 97.47% in the segmentation task. Our results show how deep learning could be an effective tool to effectively support radiologists during mammograms examination. |
| Tasks | |
| Published | 2018-09-11 |
| URL | http://arxiv.org/abs/1809.03788v1 |
| http://arxiv.org/pdf/1809.03788v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-networks-for-the |
| Repo | |
| Framework | |
Multi-Layer Sparse Coding: The Holistic Way
| Title | Multi-Layer Sparse Coding: The Holistic Way |
| Authors | Aviad Aberdam, Jeremias Sulam, Michael Elad |
| Abstract | The recently proposed multi-layer sparse model has raised insightful connections between sparse representations and convolutional neural networks (CNN). In its original conception, this model was restricted to a cascade of convolutional synthesis representations. In this paper, we start by addressing a more general model, revealing interesting ties to fully connected networks. We then show that this multi-layer construction admits a brand new interpretation in a unique symbiosis between synthesis and analysis models: while the deepest layer indeed provides a synthesis representation, the mid-layers decompositions provide an analysis counterpart. This new perspective exposes the suboptimality of previously proposed pursuit approaches, as they do not fully leverage all the information comprised in the model constraints. Armed with this understanding, we address fundamental theoretical issues, revisiting previous analysis and expanding it. Motivated by the limitations of previous algorithms, we then propose an integrated - holistic - alternative that estimates all representations in the model simultaneously, and analyze all these different schemes under stochastic noise assumptions. Inspired by the synthesis-analysis duality, we further present a Holistic Pursuit algorithm, which alternates between synthesis and analysis sparse coding steps, eventually solving for the entire model as a whole, with provable improved performance. Finally, we present numerical results that demonstrate the practical advantages of our approach. |
| Tasks | |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09788v2 |
| http://arxiv.org/pdf/1804.09788v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-layer-sparse-coding-the-holistic-way |
| Repo | |
| Framework | |
Single-Perspective Warps in Natural Image Stitching
| Title | Single-Perspective Warps in Natural Image Stitching |
| Authors | Tianli Liao, Nan Li |
| Abstract | Results of image stitching can be perceptually divided into single-perspective and multiple-perspective. Compared to the multiple-perspective result, the single-perspective result excels in perspective consistency but suffers from projective distortion. In this paper, we propose two single-perspective warps for natural image stitching. The first one is a parametric warp, which is a combination of the as-projective-as-possible warp and the quasi-homography warp via dual-feature. The second one is a mesh-based warp, which is determined by optimizing a total energy function that simultaneously emphasizes different characteristics of the single-perspective warp, including alignment, naturalness, distortion and saliency. A comprehensive evaluation demonstrates that the proposed warp outperforms some state-of-the-art warps, including homography, APAP, AutoStitch, SPHP and GSP. |
| Tasks | Image Stitching |
| Published | 2018-02-13 |
| URL | http://arxiv.org/abs/1802.04645v2 |
| http://arxiv.org/pdf/1802.04645v2.pdf | |
| PWC | https://paperswithcode.com/paper/single-perspective-warps-in-natural-image |
| Repo | |
| Framework | |
Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation
| Title | Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation |
| Authors | Cong Liao, Haoti Zhong, Anna Squicciarini, Sencun Zhu, David Miller |
| Abstract | Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications including those where security is of great concern. Such popularity, however, may attract attackers to exploit the vulnerabilities of the deployed deep learning models and launch attacks against security-sensitive applications. In this paper, we focus on a specific type of data poisoning attack, which we refer to as a {\em backdoor injection attack}. The main goal of the adversary performing such attack is to generate and inject a backdoor into a deep learning model that can be triggered to recognize certain embedded patterns with a target label of the attacker’s choice. Additionally, a backdoor injection attack should occur in a stealthy manner, without undermining the efficacy of the victim model. Specifically, we propose two approaches for generating a backdoor that is hardly perceptible yet effective in poisoning the model. We consider two attack settings, with backdoor injection carried out either before model training or during model updating. We carry out extensive experimental evaluations under various assumptions on the adversary model, and demonstrate that such attacks can be effective and achieve a high attack success rate (above $90%$) at a small cost of model accuracy loss (below $1%$) with a small injection rate (around $1%$), even under the weakest assumption wherein the adversary has no knowledge either of the original training data or the classifier model. |
| Tasks | data poisoning, Image Classification |
| Published | 2018-08-30 |
| URL | http://arxiv.org/abs/1808.10307v1 |
| http://arxiv.org/pdf/1808.10307v1.pdf | |
| PWC | https://paperswithcode.com/paper/backdoor-embedding-in-convolutional-neural |
| Repo | |
| Framework | |
Canonical Correlation Analysis of Datasets with a Common Source Graph
| Title | Canonical Correlation Analysis of Datasets with a Common Source Graph |
| Authors | Jia Chen, Gang Wang, Yanning Shen, Georgios B. Giannakis |
| Abstract | Canonical correlation analysis (CCA) is a powerful technique for discovering whether or not hidden sources are commonly present in two (or more) datasets. Its well-appreciated merits include dimensionality reduction, clustering, classification, feature selection, and data fusion. The standard CCA however, does not exploit the geometry of the common sources, which may be available from the given data or can be deduced from (cross-) correlations. In this paper, this extra information provided by the common sources generating the data is encoded in a graph, and is invoked as a graph regularizer. This leads to a novel graph-regularized CCA approach, that is termed graph (g) CCA. The novel gCCA accounts for the graph-induced knowledge of common sources, while minimizing the distance between the wanted canonical variables. Tailored for diverse practical settings where the number of data is smaller than the data vector dimensions, the dual formulation of gCCA is also developed. One such setting includes kernels that are incorporated to account for nonlinear data dependencies. The resultant graph-kernel (gk) CCA is also obtained in closed form. Finally, corroborating image classification tests over several real datasets are presented to showcase the merits of the novel linear, dual, and kernel approaches relative to competing alternatives. |
| Tasks | Dimensionality Reduction, Feature Selection, Image Classification |
| Published | 2018-03-27 |
| URL | http://arxiv.org/abs/1803.10309v1 |
| http://arxiv.org/pdf/1803.10309v1.pdf | |
| PWC | https://paperswithcode.com/paper/canonical-correlation-analysis-of-datasets |
| Repo | |
| Framework | |
Information Bottleneck Methods for Distributed Learning
| Title | Information Bottleneck Methods for Distributed Learning |
| Authors | Parinaz Farajiparvar, Ahmad Beirami, Matthew Nokleby |
| Abstract | We study a distributed learning problem in which Alice sends a compressed distillation of a set of training data to Bob, who uses the distilled version to best solve an associated learning problem. We formalize this as a rate-distortion problem in which the training set is the source and Bob’s cross-entropy loss is the distortion measure. We consider this problem for unsupervised learning for batch and sequential data. In the batch data, this problem is equivalent to the information bottleneck (IB), and we show that reduced-complexity versions of standard IB methods solve the associated rate-distortion problem. For the streaming data, we present a new algorithm, which may be of independent interest, that solves the rate-distortion problem for Gaussian sources. Furthermore, to improve the results of the iterative algorithm for sequential data we introduce a two-pass version of this algorithm. Finally, we show the dependency of the rate on the number of samples $k$ required for Gaussian sources to ensure cross-entropy loss that scales optimally with the growth of the training set. |
| Tasks | |
| Published | 2018-10-26 |
| URL | http://arxiv.org/abs/1810.11499v1 |
| http://arxiv.org/pdf/1810.11499v1.pdf | |
| PWC | https://paperswithcode.com/paper/information-bottleneck-methods-for |
| Repo | |
| Framework | |
Recurrent Neural Network for Learning DenseDepth and Ego-Motion from Video
| Title | Recurrent Neural Network for Learning DenseDepth and Ego-Motion from Video |
| Authors | Rui Wang, Jan-Michael Frahm, Stephen M. Pizer |
| Abstract | Learning-based, single-view depth estimation often generalizes poorly to unseen datasets. While learning-based, two-frame depth estimation solves this problem to some extent by learning to match features across frames, it performs poorly at large depth where the uncertainty is high. There exists few learning-based, multi-view depth estimation methods. In this paper, we present a learning-based, multi-view dense depth map and ego-motion estimation method that uses Recurrent Neural Networks (RNN). Our model is designed for 3D reconstruction from video where the input frames are temporally correlated. It is generalizable to single- or two-view dense depth estimation. Compared to recent single- or two-view CNN-based depth estimation methods, our model leverages more views and achieves more accurate results, especially at large distances. Our method produces superior results to the state-of-the-art learning-based, single- or two-view depth estimation methods on both indoor and outdoor benchmark datasets. We also demonstrate that our method can even work on extremely difficult sequences, such as endoscopic video, where none of the assumptions (static scene, constant lighting, Lambertian reflection, etc.) from traditional 3D reconstruction methods hold. |
| Tasks | 3D Reconstruction, Depth Estimation, Motion Estimation |
| Published | 2018-05-17 |
| URL | http://arxiv.org/abs/1805.06558v1 |
| http://arxiv.org/pdf/1805.06558v1.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-neural-network-for-learning |
| Repo | |
| Framework | |
Layered Optical Flow Estimation Using a Deep Neural Network with a Soft Mask
| Title | Layered Optical Flow Estimation Using a Deep Neural Network with a Soft Mask |
| Authors | Xi Zhang, Di Ma, Xu Ouyang, Shanshan Jiang, Lin Gan, Gady Agam |
| Abstract | Using a layered representation for motion estimation has the advantage of being able to cope with discontinuities and occlusions. In this paper, we learn to estimate optical flow by combining a layered motion representation with deep learning. Instead of pre-segmenting the image to layers, the proposed approach automatically generates a layered representation of optical flow using the proposed soft-mask module. The essential components of the soft-mask module are maxout and fuse operations, which enable a disjoint layered representation of optical flow and more accurate flow estimation. We show that by using masks the motion estimate results in a quadratic function of input features in the output layer. The proposed soft-mask module can be added to any existing optical flow estimation networks by replacing their flow output layer. In this work, we use FlowNet as the base network to which we add the soft-mask module. The resulting network is tested on three well-known benchmarks with both supervised and unsupervised flow estimation tasks. Evaluation results show that the proposed network achieve better results compared with the original FlowNet. |
| Tasks | Motion Estimation, Optical Flow Estimation |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.03596v1 |
| http://arxiv.org/pdf/1805.03596v1.pdf | |
| PWC | https://paperswithcode.com/paper/layered-optical-flow-estimation-using-a-deep |
| Repo | |
| Framework | |
Hybrid Subspace Learning for High-Dimensional Data
| Title | Hybrid Subspace Learning for High-Dimensional Data |
| Authors | Micol Marchetti-Bowick, Benjamin J. Lengerich, Ankur P. Parikh, Eric P. Xing |
| Abstract | The high-dimensional data setting, in which p » n, is a challenging statistical paradigm that appears in many real-world problems. In this setting, learning a compact, low-dimensional representation of the data can substantially help distinguish signal from noise. One way to achieve this goal is to perform subspace learning to estimate a small set of latent features that capture the majority of the variance in the original data. Most existing subspace learning models, such as PCA, assume that the data can be fully represented by its embedding in one or more latent subspaces. However, in this work, we argue that this assumption is not suitable for many high-dimensional datasets; often only some variables can easily be projected to a low-dimensional space. We propose a hybrid dimensionality reduction technique in which some features are mapped to a low-dimensional subspace while others remain in the original space. Our model leads to more accurate estimation of the latent space and lower reconstruction error. We present a simple optimization procedure for the resulting biconvex problem and show synthetic data results that demonstrate the advantages of our approach over existing methods. Finally, we demonstrate the effectiveness of this method for extracting meaningful features from both gene expression and video background subtraction datasets. |
| Tasks | Dimensionality Reduction, Video Background Subtraction |
| Published | 2018-08-05 |
| URL | http://arxiv.org/abs/1808.01687v1 |
| http://arxiv.org/pdf/1808.01687v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-subspace-learning-for-high-dimensional |
| Repo | |
| Framework | |
Superframes, A Temporal Video Segmentation
| Title | Superframes, A Temporal Video Segmentation |
| Authors | Hajar Sadeghi Sokeh, Vasileios Argyriou, Dorothy Monekosso, Paolo Remagnino |
| Abstract | The goal of video segmentation is to turn video data into a set of concrete motion clusters that can be easily interpreted as building blocks of the video. There are some works on similar topics like detecting scene cuts in a video, but there is few specific research on clustering video data into the desired number of compact segments. It would be more intuitive, and more efficient, to work with perceptually meaningful entity obtained from a low-level grouping process which we call it superframe. This paper presents a new simple and efficient technique to detect superframes of similar content patterns in videos. We calculate the similarity of content-motion to obtain the strength of change between consecutive frames. With the help of existing optical flow technique using deep models, the proposed method is able to perform more accurate motion estimation efficiently. We also propose two criteria for measuring and comparing the performance of different algorithms on various databases. Experimental results on the videos from benchmark databases have demonstrated the effectiveness of the proposed method. |
| Tasks | Motion Estimation, Optical Flow Estimation, Video Semantic Segmentation |
| Published | 2018-04-18 |
| URL | http://arxiv.org/abs/1804.06642v2 |
| http://arxiv.org/pdf/1804.06642v2.pdf | |
| PWC | https://paperswithcode.com/paper/superframes-a-temporal-video-segmentation |
| Repo | |
| Framework | |
Adversarial Neural Networks for Cross-lingual Sequence Tagging
| Title | Adversarial Neural Networks for Cross-lingual Sequence Tagging |
| Authors | Heike Adel, Anton Bryl, David Weiss, Aliaksei Severyn |
| Abstract | We study cross-lingual sequence tagging with little or no labeled data in the target language. Adversarial training has previously been shown to be effective for training cross-lingual sentence classifiers. However, it is not clear if language-agnostic representations enforced by an adversarial language discriminator will also enable effective transfer for token-level prediction tasks. Therefore, we experiment with different types of adversarial training on two tasks: dependency parsing and sentence compression. We show that adversarial training consistently leads to improved cross-lingual performance on each task compared to a conventionally trained baseline. |
| Tasks | Dependency Parsing, Sentence Compression |
| Published | 2018-08-14 |
| URL | http://arxiv.org/abs/1808.04736v1 |
| http://arxiv.org/pdf/1808.04736v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-neural-networks-for-cross-lingual |
| Repo | |
| Framework | |
An Investigation on Support Vector Clustering for Big Data in Quantum Paradigm
| Title | An Investigation on Support Vector Clustering for Big Data in Quantum Paradigm |
| Authors | Arit Kumar Bishwas, Ashish Mani, Vasile Palade |
| Abstract | The support vector clustering algorithm is a well-known clustering algorithm based on support vector machines using Gaussian or polynomial kernels. The classical support vector clustering algorithm works well in general, but its performance degrades when applied on big data. In this paper, we have investigated the performance of support vector clustering algorithm implemented in a quantum paradigm for possible run-time improvements. We have developed and analyzed a quantum version of the support vector clustering algorithm. The proposed approach is based on the quantum support vector machine and quantum kernels (i.e., Gaussian and polynomial). The proposed quantum version of the SVM clustering method demonstrates a significant speed-up gain on the overall run-time complexity as compared to the classical counterpart. |
| Tasks | |
| Published | 2018-04-29 |
| URL | https://arxiv.org/abs/1804.10905v2 |
| https://arxiv.org/pdf/1804.10905v2.pdf | |
| PWC | https://paperswithcode.com/paper/big-data-quantum-support-vector-clustering |
| Repo | |
| Framework | |
Fully Nonparametric Bayesian Additive Regression Trees
| Title | Fully Nonparametric Bayesian Additive Regression Trees |
| Authors | Edward George, Prakash Laud, Brent Logan, Robert McCulloch, Rodney Sparapani |
| Abstract | Bayesian Additive Regression Trees (BART) is a fully Bayesian approach to modeling with ensembles of trees. BART can uncover complex regression functions with high dimensional regressors in a fairly automatic way and provide Bayesian quantification of the uncertainty through the posterior. However, BART assumes IID normal errors. This strong parametric assumption can lead to misleading inference and uncertainty quantification. In this paper, we use the classic Dirichlet process mixture (DPM) mechanism to nonparametrically model the error distribution. A key strength of BART is that default prior settings work reasonably well in a variety of problems. The challenge in extending BART is to choose the parameters of the DPM so that the strengths of the standard BART approach is not lost when the errors are close to normal, but the DPM has the ability to adapt to non-normal errors. |
| Tasks | |
| Published | 2018-06-29 |
| URL | http://arxiv.org/abs/1807.00068v2 |
| http://arxiv.org/pdf/1807.00068v2.pdf | |
| PWC | https://paperswithcode.com/paper/fully-nonparametric-bayesian-additive |
| Repo | |
| Framework | |
Continuous Learning of Context-dependent Processing in Neural Networks
| Title | Continuous Learning of Context-dependent Processing in Neural Networks |
| Authors | Guanxiong Zeng, Yang Chen, Bo Cui, Shan Yu |
| Abstract | Deep artificial neural networks (DNNs) are powerful tools for recognition and classification as they learn sophisticated mapping rules between the inputs and the outputs. However, the rules that learned by the majority of current DNNs used for pattern recognition are largely fixed and do not vary with different conditions. This limits the network’s ability to work in more complex and dynamical situations in which the mapping rules themselves are not fixed but constantly change according to contexts, such as different environments and goals. Inspired by the role of the prefrontal cortex (PFC) in mediating context-dependent processing in the primate brain, here we propose a novel approach, involving a learning algorithm named orthogonal weights modification (OWM) with the addition of a PFC-like module, that enables networks to continually learn different mapping rules in a context-dependent way. We demonstrate that with OWM to protect previously acquired knowledge, the networks could sequentially learn up to thousands of different mapping rules without interference, and needing as few as $\sim$10 samples to learn each, reaching a human level ability in online, continual learning. In addition, by using a PFC-like module to enable contextual information to modulate the representation of sensory features, a network could sequentially learn different, context-specific mappings for identical stimuli. Taken together, these approaches allow us to teach a single network numerous context-dependent mapping rules in an online, continual manner. This would enable highly compact systems to gradually learn myriad of regularities of the real world and eventually behave appropriately within it. |
| Tasks | Continual Learning |
| Published | 2018-09-29 |
| URL | http://arxiv.org/abs/1810.01256v2 |
| http://arxiv.org/pdf/1810.01256v2.pdf | |
| PWC | https://paperswithcode.com/paper/continuous-learning-of-context-dependent |
| Repo | |
| Framework | |
