Paper Group ANR 137
Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification. SynNet: Structure-Preserving Fully Convolutional Networks for Medical Image Synthesis. A General Account of Argumentation with Preferences. Local SGD Converges Fast and Communicates Little. A Hardware-Friendly Algorithm for Scalable Training and Deploy …
Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification
| Title | Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification |
| Authors | Lin Wu, Yang Wang, Junbin Gao, Xue Li |
| Abstract | Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security. Matching persons across disjoint camera views in their video fragments is inherently challenging due to the large visual variations and uncontrolled frame rates. There are two steps crucial to person re-id, namely discriminative feature learning and metric learning. However, existing approaches consider the two steps independently, and they do not make full use of the temporal and spatial information in videos. In this paper, we propose a Siamese attention architecture that jointly learns spatiotemporal video representations and their similarity metrics. The network extracts local convolutional features from regions of each frame, and enhance their discriminative capability by focusing on distinct regions when measuring the similarity with another pedestrian video. The attention mechanism is embedded into spatial gated recurrent units to selectively propagate relevant features and memorize their spatial dependencies through the network. The model essentially learns which parts (\emph{where}) from which frames (\emph{when}) are relevant and distinctive for matching persons and attaches higher importance therein. The proposed Siamese model is end-to-end trainable to jointly learn comparable hidden representations for paired pedestrian videos and their similarity value. Extensive experiments on three benchmark datasets show the effectiveness of each component of the proposed deep network while outperforming state-of-the-art methods. |
| Tasks | Metric Learning, Person Re-Identification, Video-Based Person Re-Identification |
| Published | 2018-08-03 |
| URL | http://arxiv.org/abs/1808.01911v2 |
| http://arxiv.org/pdf/1808.01911v2.pdf | |
| PWC | https://paperswithcode.com/paper/where-and-when-to-look-deep-siamese-attention |
| Repo | |
| Framework | |
SynNet: Structure-Preserving Fully Convolutional Networks for Medical Image Synthesis
| Title | SynNet: Structure-Preserving Fully Convolutional Networks for Medical Image Synthesis |
| Authors | Deepa Gunashekar, Sailesh Conjeti, Abhijit Guha Roy, Nassir Navab, Kuangyu Shi |
| Abstract | Cross modal image syntheses is gaining significant interests for its ability to estimate target images of a different modality from a given set of source images,like estimating MR to MR, MR to CT, CT to PET etc, without the need for an actual acquisition.Though they show potential for applications in radiation therapy planning,image super resolution, atlas construction, image segmentation etc.The synthesis results are not as accurate as the actual acquisition.In this paper,we address the problem of multi modal image synthesis by proposing a fully convolutional deep learning architecture called the SynNet.We extend the proposed architecture for various input output configurations. And finally, we propose a structure preserving custom loss function for cross-modal image synthesis.We validate the proposed SynNet and its extended framework on BRATS dataset with comparisons against three state-of-the art methods.And the results of the proposed custom loss function is validated against the traditional loss function used by the state-of-the-art methods for cross modal image synthesis. |
| Tasks | Image Generation, Image Super-Resolution, Semantic Segmentation, Super-Resolution |
| Published | 2018-06-29 |
| URL | http://arxiv.org/abs/1806.11475v1 |
| http://arxiv.org/pdf/1806.11475v1.pdf | |
| PWC | https://paperswithcode.com/paper/synnet-structure-preserving-fully |
| Repo | |
| Framework | |
A General Account of Argumentation with Preferences
| Title | A General Account of Argumentation with Preferences |
| Authors | Sanjay Modgil, Henry Prakken |
| Abstract | This paper builds on the recent ASPIC+ formalism, to develop a general framework for argumentation with preferences. We motivate a revised definition of conflict free sets of arguments, adapt ASPIC+ to accommodate a broader range of instantiating logics, and show that under some assumptions, the resulting framework satisfies key properties and rationality postulates. We then show that the generalised framework accommodates Tarskian logic instantiations extended with preferences, and then study instantiations of the framework by classical logic approaches to argumentation. We conclude by arguing that ASPIC+'s modelling of defeasible inference rules further testifies to the generality of the framework, and then examine and counter recent critiques of Dung’s framework and its extensions to accommodate preferences. |
| Tasks | |
| Published | 2018-04-18 |
| URL | http://arxiv.org/abs/1804.06763v1 |
| http://arxiv.org/pdf/1804.06763v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-account-of-argumentation-with |
| Repo | |
| Framework | |
Local SGD Converges Fast and Communicates Little
| Title | Local SGD Converges Fast and Communicates Little |
| Authors | Sebastian U. Stich |
| Abstract | Mini-batch stochastic gradient descent (SGD) is state of the art in large scale distributed training. The scheme can reach a linear speedup with respect to the number of workers, but this is rarely seen in practice as the scheme often suffers from large network delays and bandwidth limits. To overcome this communication bottleneck recent works propose to reduce the communication frequency. An algorithm of this type is local SGD that runs SGD independently in parallel on different workers and averages the sequences only once in a while. This scheme shows promising results in practice, but eluded thorough theoretical analysis. We prove concise convergence rates for local SGD on convex problems and show that it converges at the same rate as mini-batch SGD in terms of number of evaluated gradients, that is, the scheme achieves linear speedup in the number of workers and mini-batch size. The number of communication rounds can be reduced up to a factor of T^{1/2}—where T denotes the number of total steps—compared to mini-batch SGD. This also holds for asynchronous implementations. Local SGD can also be used for large scale training of deep learning models. The results shown here aim serving as a guideline to further explore the theoretical and practical aspects of local SGD in these applications. |
| Tasks | |
| Published | 2018-05-24 |
| URL | https://arxiv.org/abs/1805.09767v3 |
| https://arxiv.org/pdf/1805.09767v3.pdf | |
| PWC | https://paperswithcode.com/paper/local-sgd-converges-fast-and-communicates |
| Repo | |
| Framework | |
A Hardware-Friendly Algorithm for Scalable Training and Deployment of Dimensionality Reduction Models on FPGA
| Title | A Hardware-Friendly Algorithm for Scalable Training and Deployment of Dimensionality Reduction Models on FPGA |
| Authors | Mahdi Nazemi, Amir Erfan Eshratifar, Massoud Pedram |
| Abstract | With ever-increasing application of machine learning models in various domains such as image classification, speech recognition and synthesis, and health care, designing efficient hardware for these models has gained a lot of popularity. While the majority of researches in this area focus on efficient deployment of machine learning models (a.k.a inference), this work concentrates on challenges of training these models in hardware. In particular, this paper presents a high-performance, scalable, reconfigurable solution for both training and deployment of different dimensionality reduction models in hardware by introducing a hardware-friendly algorithm. Compared to state-of-the-art implementations, our proposed algorithm and its hardware realization decrease resource consumption by 50% without any degradation in accuracy. |
| Tasks | Dimensionality Reduction, Image Classification, Speech Recognition |
| Published | 2018-01-11 |
| URL | http://arxiv.org/abs/1801.04014v2 |
| http://arxiv.org/pdf/1801.04014v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-hardware-friendly-algorithm-for-scalable |
| Repo | |
| Framework | |
Text Morphing
| Title | Text Morphing |
| Authors | Shaohan Huang, Yu Wu, Furu Wei, Ming Zhou |
| Abstract | In this paper, we introduce a novel natural language generation task, termed as text morphing, which targets at generating the intermediate sentences that are fluency and smooth with the two input sentences. We propose the Morphing Networks consisting of the editing vector generation networks and the sentence editing networks which are trained jointly. Specifically, the editing vectors are generated with a recurrent neural networks model from the lexical gap between the source sentence and the target sentence. Then the sentence editing networks iteratively generate new sentences with the current editing vector and the sentence generated in the previous step. We conduct experiments with 10 million text morphing sequences which are extracted from the Yelp review dataset. Experiment results show that the proposed method outperforms baselines on the text morphing task. We also discuss directions and opportunities for future research of text morphing. |
| Tasks | Text Generation |
| Published | 2018-09-30 |
| URL | http://arxiv.org/abs/1810.00341v1 |
| http://arxiv.org/pdf/1810.00341v1.pdf | |
| PWC | https://paperswithcode.com/paper/text-morphing |
| Repo | |
| Framework | |
A salt and pepper noise image denoising method based on the generative classification
| Title | A salt and pepper noise image denoising method based on the generative classification |
| Authors | Bo Fu, Xiao-Yang Zhao, Yong-Gong Ren, Xi-Ming Li, Xiang-Hai Wang |
| Abstract | In this paper, an image denoising algorithm is proposed for salt and pepper noise. First, a generative model is built on a patch as a basic unit and then the algorithm locates the image noise within that patch in order to better describe the patch and obtain better subsequent clustering. Second, the algorithm classifies patches using a generative clustering method, thus providing additional similarity information for noise repair and suppressing the interference of noise, abandoning those categories that consist of a smaller number of patches. Finally, the algorithm builds a non-local switching filter to remove the salt and pepper noise. Simulation results show that the proposed algorithm effectively denoises salt and pepper noise of various densities. It obtains a better visual quality and higher peak signal-to-noise ratio score than several state-of-the-art algorithms. In short, our algorithm uses a noisy patch as the basic unit, a patch clustering method to optimize the repair data set as well as obtain a better denoising effect, and provides a guideline for future denoising and repair methods. |
| Tasks | Denoising, Image Denoising |
| Published | 2018-07-15 |
| URL | http://arxiv.org/abs/1807.05478v1 |
| http://arxiv.org/pdf/1807.05478v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-salt-and-pepper-noise-image-denoising |
| Repo | |
| Framework | |
Visual Sensor Network Reconfiguration with Deep Reinforcement Learning
| Title | Visual Sensor Network Reconfiguration with Deep Reinforcement Learning |
| Authors | Paul Jasek, Bernard Abayowa |
| Abstract | We present an approach for reconfiguration of dynamic visual sensor networks with deep reinforcement learning (RL). Our RL agent uses a modified asynchronous advantage actor-critic framework and the recently proposed Relational Network module at the foundation of its network architecture. To address the issue of sample inefficiency in current approaches to model-free reinforcement learning, we train our system in an abstract simulation environment that represents inputs from a dynamic scene. Our system is validated using inputs from a real-world scenario and preexisting object detection and tracking algorithms. |
| Tasks | Object Detection |
| Published | 2018-08-13 |
| URL | http://arxiv.org/abs/1808.04287v1 |
| http://arxiv.org/pdf/1808.04287v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-sensor-network-reconfiguration-with |
| Repo | |
| Framework | |
Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback
| Title | Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback |
| Authors | Carolin Lawrence, Stefan Riezler |
| Abstract | Counterfactual learning from human bandit feedback describes a scenario where user feedback on the quality of outputs of a historic system is logged and used to improve a target system. We show how to apply this learning framework to neural semantic parsing. From a machine learning perspective, the key challenge lies in a proper reweighting of the estimator so as to avoid known degeneracies in counterfactual learning, while still being applicable to stochastic gradient optimization. To conduct experiments with human users, we devise an easy-to-use interface to collect human feedback on semantic parses. Our work is the first to show that semantic parsers can be improved significantly by counterfactual learning from logged human feedback data. |
| Tasks | Semantic Parsing |
| Published | 2018-05-03 |
| URL | http://arxiv.org/abs/1805.01252v2 |
| http://arxiv.org/pdf/1805.01252v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-a-neural-semantic-parser-by |
| Repo | |
| Framework | |
Holistic Decomposition Convolution for Effective Semantic Segmentation of 3D MR Images
| Title | Holistic Decomposition Convolution for Effective Semantic Segmentation of 3D MR Images |
| Authors | Guodong Zeng, Guoyan Zheng |
| Abstract | Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many different 2D medical image analysis tasks. In clinical practice, however, a large part of the medical imaging data available is in 3D. This has motivated the development of 3D CNNs for volumetric image segmentation in order to benefit from more spatial context. Due to GPU memory restrictions caused by moving to fully 3D, state-of-the-art methods depend on subvolume/patch processing and the size of the input patch is usually small, limiting the incorporation of larger context information for a better performance. In this paper, we propose a novel Holistic Decomposition Convolution (HDC), for an effective and efficient semantic segmentation of volumetric images. HDC consists of a periodic down-shuffling operation followed by a conventional 3D convolution. HDC has the advantage of significantly reducing the size of the data for sub-sequential processing while using all the information available in the input irrespective of the down-shuffling factors. Results obtained from comprehensive experiments conducted on hip T1 MR images and intervertebral disc T2 MR images demonstrate the efficacy of the present approach. |
| Tasks | Semantic Segmentation |
| Published | 2018-12-24 |
| URL | http://arxiv.org/abs/1812.09834v1 |
| http://arxiv.org/pdf/1812.09834v1.pdf | |
| PWC | https://paperswithcode.com/paper/holistic-decomposition-convolution-for |
| Repo | |
| Framework | |
Bridging the Gap Between Layout Pattern Sampling and Hotspot Detection via Batch Active Sampling
| Title | Bridging the Gap Between Layout Pattern Sampling and Hotspot Detection via Batch Active Sampling |
| Authors | Haoyu Yang, Shuhe Li, Cyrus Tabery, Bingqing Lin, Bei Yu |
| Abstract | Layout hotpot detection is one of the main steps in modern VLSI design. A typical hotspot detection flow is extremely time consuming due to the computationally expensive mask optimization and lithographic simulation. Recent researches try to facilitate the procedure with a reduced flow including feature extraction, training set generation and hotspot detection, where feature extraction methods and hotspot detection engines are deeply studied. However, the performance of hotspot detectors relies highly on the quality of reference layout libraries which are costly to obtain and usually predetermined or randomly sampled in previous works. In this paper, we propose an active learning-based layout pattern sampling and hotspot detection flow, which simultaneously optimizes the machine learning model and the training set that aims to achieve similar or better hotspot detection performance with much smaller number of training instances. Experimental results show that our proposed method can significantly reduce lithography simulation overhead while attaining satisfactory detection accuracy on designs under both DUV and EUV lithography technologies. |
| Tasks | Active Learning |
| Published | 2018-07-13 |
| URL | http://arxiv.org/abs/1807.06446v1 |
| http://arxiv.org/pdf/1807.06446v1.pdf | |
| PWC | https://paperswithcode.com/paper/bridging-the-gap-between-layout-pattern |
| Repo | |
| Framework | |
Dynamic Network Model from Partial Observations
| Title | Dynamic Network Model from Partial Observations |
| Authors | Elahe Ghalebi, Baharan Mirzasoleiman, Radu Grosu, Jure Leskovec |
| Abstract | Can evolving networks be inferred and modeled without directly observing their nodes and edges? In many applications, the edges of a dynamic network might not be observed, but one can observe the dynamics of stochastic cascading processes (e.g., information diffusion, virus propagation) occurring over the unobserved network. While there have been efforts to infer networks based on such data, providing a generative probabilistic model that is able to identify the underlying time-varying network remains an open question. Here we consider the problem of inferring generative dynamic network models based on network cascade diffusion data. We propose a novel framework for providing a non-parametric dynamic network model–based on a mixture of coupled hierarchical Dirichlet processes– based on data capturing cascade node infection times. Our approach allows us to infer the evolving community structure in networks and to obtain an explicit predictive distribution over the edges of the underlying network–including those that were not involved in transmission of any cascade, or are likely to appear in the future. We show the effectiveness of our approach using extensive experiments on synthetic as well as real-world networks. |
| Tasks | |
| Published | 2018-05-27 |
| URL | http://arxiv.org/abs/1805.10616v4 |
| http://arxiv.org/pdf/1805.10616v4.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-network-model-from-partial |
| Repo | |
| Framework | |
Natural data structure extracted from neighborhood-similarity graphs
| Title | Natural data structure extracted from neighborhood-similarity graphs |
| Authors | Tom Lorimer, Karlis Kanders, Ruedi Stoop |
| Abstract | ‘Big’ high-dimensional data are commonly analyzed in low-dimensions, after performing a dimensionality-reduction step that inherently distorts the data structure. For the same purpose, clustering methods are also often used. These methods also introduce a bias, either by starting from the assumption of a particular geometric form of the clusters, or by using iterative schemes to enhance cluster contours, with uncontrollable consequences. The goal of data analysis should, however, be to encode and detect structural data features at all scales and densities simultaneously, without assuming a parametric form of data point distances, or modifying them. We propose a novel approach that directly encodes data point neighborhood similarities as a sparse graph. Our non-iterative framework permits a transparent interpretation of data, without altering the original data dimension and metric. Several natural and synthetic data applications demonstrate the efficacy of our novel approach. |
| Tasks | Dimensionality Reduction |
| Published | 2018-02-15 |
| URL | http://arxiv.org/abs/1803.00500v1 |
| http://arxiv.org/pdf/1803.00500v1.pdf | |
| PWC | https://paperswithcode.com/paper/natural-data-structure-extracted-from |
| Repo | |
| Framework | |
Exploring Semantic Incrementality with Dynamic Syntax and Vector Space Semantics
| Title | Exploring Semantic Incrementality with Dynamic Syntax and Vector Space Semantics |
| Authors | Mehrnoosh Sadrzadeh, Matthew Purver, Julian Hough, Ruth Kempson |
| Abstract | One of the fundamental requirements for models of semantic processing in dialogue is incrementality: a model must reflect how people interpret and generate language at least on a word-by-word basis, and handle phenomena such as fragments, incomplete and jointly-produced utterances. We show that the incremental word-by-word parsing process of Dynamic Syntax (DS) can be assigned a compositional distributional semantics, with the composition operator of DS corresponding to the general operation of tensor contraction from multilinear algebra. We provide abstract semantic decorations for the nodes of DS trees, in terms of vectors, tensors, and sums thereof; using the latter to model the underspecified elements crucial to assigning partial representations during incremental processing. As a working example, we give an instantiation of this theory using plausibility tensors of compositional distributional semantics, and show how our framework can incrementally assign a semantic plausibility measure as it parses phrases and sentences. |
| Tasks | |
| Published | 2018-11-01 |
| URL | http://arxiv.org/abs/1811.00614v1 |
| http://arxiv.org/pdf/1811.00614v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-semantic-incrementality-with |
| Repo | |
| Framework | |
Cubic Regularization with Momentum for Nonconvex Optimization
| Title | Cubic Regularization with Momentum for Nonconvex Optimization |
| Authors | Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan |
| Abstract | Momentum is a popular technique to accelerate the convergence in practical training, and its impact on convergence guarantee has been well-studied for first-order algorithms. However, such a successful acceleration technique has not yet been proposed for second-order algorithms in nonconvex optimization.In this paper, we apply the momentum scheme to cubic regularized (CR) Newton’s method and explore the potential for acceleration. Our numerical experiments on various nonconvex optimization problems demonstrate that the momentum scheme can substantially facilitate the convergence of cubic regularization, and perform even better than the Nesterov’s acceleration scheme for CR. Theoretically, we prove that CR under momentum achieves the best possible convergence rate to a second-order stationary point for nonconvex optimization. Moreover, we study the proposed algorithm for solving problems satisfying an error bound condition and establish a local quadratic convergence rate. Then, particularly for finite-sum problems, we show that the proposed algorithm can allow computational inexactness that reduces the overall sample complexity without degrading the convergence rate. |
| Tasks | |
| Published | 2018-10-09 |
| URL | https://arxiv.org/abs/1810.03763v2 |
| https://arxiv.org/pdf/1810.03763v2.pdf | |
| PWC | https://paperswithcode.com/paper/cubic-regularization-with-momentum-for |
| Repo | |
| Framework | |
