Paper Group ANR 261
Generating Multiple Diverse Responses for Short-Text Conversation. Algorithms for Destructive Shift Bribery. Optimal arrangements of hyperplanes for multiclass classification. Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation. Piecewise Convex Function Estimation and Model Selection. Crowd Counting by A …
Generating Multiple Diverse Responses for Short-Text Conversation
| Title | Generating Multiple Diverse Responses for Short-Text Conversation |
| Authors | Jun Gao, Wei Bi, Xiaojiang Liu, Junhui Li, Shuming Shi |
| Abstract | Neural generative models have become popular and achieved promising performance on short-text conversation tasks. They are generally trained to build a 1-to-1 mapping from the input post to its output response. However, a given post is often associated with multiple replies simultaneously in real applications. Previous research on this task mainly focuses on improving the relevance and informativeness of the top one generated response for each post. Very few works study generating multiple accurate and diverse responses for the same post. In this paper, we propose a novel response generation model, which considers a set of responses jointly and generates multiple diverse responses simultaneously. A reinforcement learning algorithm is designed to solve our model. Experiments on two short-text conversation tasks validate that the multiple responses generated by our model obtain higher quality and larger diversity compared with various state-of-the-art generative models. |
| Tasks | Short-Text Conversation |
| Published | 2018-11-14 |
| URL | http://arxiv.org/abs/1811.05696v3 |
| http://arxiv.org/pdf/1811.05696v3.pdf | |
| PWC | https://paperswithcode.com/paper/generating-multiple-diverse-responses-for |
| Repo | |
| Framework | |
Algorithms for Destructive Shift Bribery
| Title | Algorithms for Destructive Shift Bribery |
| Authors | Andrzej Kaczmarczyk, Piotr Faliszewski |
| Abstract | We study the complexity of Destructive Shift Bribery. In this problem, we are given an election with a set of candidates and a set of voters (each ranking the candidates from the best to the worst), a despised candidate $d$, a budget $B$, and prices for shifting $d$ back in the voters’ rankings. The goal is to ensure that $d$ is not a winner of the election. We show that this problem is polynomial-time solvable for scoring protocols (encoded in unary), the Bucklin and Simplified Bucklin rules, and the Maximin rule, but is NP-hard for the Copeland rule. This stands in contrast to the results for the constructive setting (known from the literature), for which the problem is polynomial-time solvable for $k$-Approval family of rules, but is NP-hard for the Borda, Copeland, and Maximin rules. We complement the analysis of the Copeland rule showing W-hardness for the parameterization by the budget value, and by the number of affected voters. We prove that the problem is W-hard when parameterized by the number of voters even for unit prices. From the positive perspective we provide an efficient algorithm for solving the problem parameterized by the combined parameter the number of candidates and the maximum bribery price (alternatively the number of different bribery prices). |
| Tasks | |
| Published | 2018-10-03 |
| URL | http://arxiv.org/abs/1810.01763v1 |
| http://arxiv.org/pdf/1810.01763v1.pdf | |
| PWC | https://paperswithcode.com/paper/algorithms-for-destructive-shift-bribery |
| Repo | |
| Framework | |
Optimal arrangements of hyperplanes for multiclass classification
| Title | Optimal arrangements of hyperplanes for multiclass classification |
| Authors | Víctor Blanco, Alberto Japón, Justo Puerto |
| Abstract | In this paper, we present a novel approach to construct multiclass classifiers by means of arrangements of hyperplanes. We propose different mixed integer (linear and non linear) programming formulations for the problem using extensions of widely used measures for misclassifying observations where the \textit{kernel trick} can be adapted to be applicable. Some dimensionality reductions and variable fixing strategies are also developed for these models. An extensive battery of experiments has been run which reveal the powerfulness of our proposal as compared with other previously proposed methodologies. |
| Tasks | |
| Published | 2018-10-22 |
| URL | http://arxiv.org/abs/1810.09167v2 |
| http://arxiv.org/pdf/1810.09167v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-arrangements-of-hyperplanes-for |
| Repo | |
| Framework | |
Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation
| Title | Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation |
| Authors | Yuan-Ting Hu, Jia-Bin Huang, Alexander G. Schwing |
| Abstract | Unsupervised video segmentation plays an important role in a wide variety of applications from object identification to compression. However, to date, fast motion, motion blur and occlusions pose significant challenges. To address these challenges for unsupervised video segmentation, we develop a novel saliency estimation technique as well as a novel neighborhood graph, based on optical flow and edge cues. Our approach leads to significantly better initial foreground-background estimates and their robust as well as accurate diffusion across time. We evaluate our proposed algorithm on the challenging DAVIS, SegTrack v2 and FBMS-59 datasets. Despite the usage of only a standard edge detector trained on 200 images, our method achieves state-of-the-art results outperforming deep learning based methods in the unsupervised setting. We even demonstrate competitive results comparable to deep learning based methods in the semi-supervised setting on the DAVIS dataset. |
| Tasks | Optical Flow Estimation, Saliency Prediction, Semantic Segmentation, Unsupervised Video Object Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2018-09-04 |
| URL | http://arxiv.org/abs/1809.01125v1 |
| http://arxiv.org/pdf/1809.01125v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-video-object-segmentation-using |
| Repo | |
| Framework | |
Piecewise Convex Function Estimation and Model Selection
| Title | Piecewise Convex Function Estimation and Model Selection |
| Authors | Kurt S. Riedel |
| Abstract | Given noisy data, function estimation is considered when the unknown function is known apriori to consist of a small number of regions where the function is either convex or concave. When the regions are known apriori, the estimate is reduced to a finite dimensional convex optimization in the dual space. When the number of regions is unknown, the model selection problem is to determine the number of convexity change points. We use a pilot estimator based on the expected number of false inflection points. |
| Tasks | Model Selection |
| Published | 2018-03-11 |
| URL | https://arxiv.org/abs/1803.03903v1 |
| https://arxiv.org/pdf/1803.03903v1.pdf | |
| PWC | https://paperswithcode.com/paper/piecewise-convex-function-estimation-and |
| Repo | |
| Framework | |
Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid
| Title | Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid |
| Authors | Di Kang, Antoni Chan |
| Abstract | Because of the powerful learning capability of deep neural networks, counting performance via density map estimation has improved significantly during the past several years. However, it is still very challenging due to severe occlusion, large scale variations, and perspective distortion. Scale variations (from image to image) coupled with perspective distortion (within one image) result in huge scale changes of the object size. Earlier methods based on convolutional neural networks (CNN) typically did not handle this scale variation explicitly, until Hydra-CNN and MCNN. MCNN uses three columns, each with different filter sizes, to extract features at different scales. In this paper, in contrast to using filters of different sizes, we utilize an image pyramid to deal with scale variations. It is more effective and efficient to resize the input fed into the network, as compared to using larger filter sizes. Secondly, we adaptively fuse the predictions from different scales (using adaptively changing per-pixel weights), which makes our method adapt to scale changes within an image. The adaptive fusing is achieved by generating an across-scale attention map, which softly selects a suitable scale for each pixel, followed by a 1x1 convolution. Extensive experiments on three popular datasets show very compelling results. |
| Tasks | Crowd Counting |
| Published | 2018-05-16 |
| URL | http://arxiv.org/abs/1805.06115v2 |
| http://arxiv.org/pdf/1805.06115v2.pdf | |
| PWC | https://paperswithcode.com/paper/crowd-counting-by-adaptively-fusing |
| Repo | |
| Framework | |
Deep Learning Reconstruction of Ultra-Short Pulses
| Title | Deep Learning Reconstruction of Ultra-Short Pulses |
| Authors | Tom Zahavy, Alex Dikopoltsev, Oren Cohen, Shie Mannor, Mordechai Segev |
| Abstract | Ultra-short laser pulses with femtosecond to attosecond pulse duration are the shortest systematic events humans can create. Characterization (amplitude and phase) of these pulses is a key ingredient in ultrafast science, e.g., exploring chemical reactions and electronic phase transitions. Here, we propose and demonstrate, numerically and experimentally, the first deep neural network technique to reconstruct ultra-short optical pulses. We anticipate that this approach will extend the range of ultrashort laser pulses that can be characterized, e.g., enabling to diagnose very weak attosecond pulses. |
| Tasks | |
| Published | 2018-03-15 |
| URL | http://arxiv.org/abs/1803.06024v1 |
| http://arxiv.org/pdf/1803.06024v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-reconstruction-of-ultra-short |
| Repo | |
| Framework | |
A Gentle Introduction to Deep Learning in Medical Image Processing
| Title | A Gentle Introduction to Deep Learning in Medical Image Processing |
| Authors | Andreas Maier, Christopher Syben, Tobias Lasser, Christian Riess |
| Abstract | This paper tries to give a gentle introduction to deep learning in medical image processing, proceeding from theoretical foundations to applications. We first discuss general reasons for the popularity of deep learning, including several major breakthroughs in computer science. Next, we start reviewing the fundamental basics of the perceptron and neural networks, along with some fundamental theory that is often omitted. Doing so allows us to understand the reasons for the rise of deep learning in many application domains. Obviously medical image processing is one of these areas which has been largely affected by this rapid progress, in particular in image detection and recognition, image segmentation, image registration, and computer-aided diagnosis. There are also recent trends in physical simulation, modelling, and reconstruction that have led to astonishing results. Yet, some of these approaches neglect prior knowledge and hence bear the risk of producing implausible results. These apparent weaknesses highlight current limitations of deep learning. However, we also briefly discuss promising approaches that might be able to resolve these problems in the future. |
| Tasks | Image Registration, Semantic Segmentation |
| Published | 2018-10-12 |
| URL | http://arxiv.org/abs/1810.05401v2 |
| http://arxiv.org/pdf/1810.05401v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-gentle-introduction-to-deep-learning-in |
| Repo | |
| Framework | |
Museum Exhibit Identification Challenge for Domain Adaptation and Beyond
| Title | Museum Exhibit Identification Challenge for Domain Adaptation and Beyond |
| Authors | Piotr Koniusz, Yusuf Tas, Hongguang Zhang, Mehrtash Harandi, Fatih Porikli, Rui Zhang |
| Abstract | In this paper, we approach an open problem of artwork identification and propose a new dataset dubbed Open Museum Identification Challenge (Open MIC). It contains photos of exhibits captured in 10 distinct exhibition spaces of several museums which showcase paintings, timepieces, sculptures, glassware, relics, science exhibits, natural history pieces, ceramics, pottery, tools and indigenous crafts. The goal of Open MIC is to stimulate research in domain adaptation, egocentric recognition and few-shot learning by providing a testbed complementary to the famous Office dataset which reaches 90% accuracy. To form our dataset, we captured a number of images per art piece with a mobile phone and wearable cameras to form the source and target data splits, respectively. To achieve robust baselines, we build on a recent approach that aligns per-class scatter matrices of the source and target CNN streams [15]. Moreover, we exploit the positive definite nature of such representations by using end-to-end Bregman divergences and the Riemannian metric. We present baselines such as training/evaluation per exhibition and training/evaluation on the combined set covering 866 exhibit identities. As each exhibition poses distinct challenges e.g., quality of lighting, motion blur, occlusions, clutter, viewpoint and scale variations, rotations, glares, transparency, non-planarity, clipping, we break down results w.r.t. these factors. |
| Tasks | Domain Adaptation, Few-Shot Learning |
| Published | 2018-02-04 |
| URL | http://arxiv.org/abs/1802.01093v1 |
| http://arxiv.org/pdf/1802.01093v1.pdf | |
| PWC | https://paperswithcode.com/paper/museum-exhibit-identification-challenge-for |
| Repo | |
| Framework | |
Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives
| Title | Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives |
| Authors | Hadrien Hendrikx, Francis Bach, Laurent Massoulié |
| Abstract | In this paper, we study the problem of minimizing a sum of smooth and strongly convex functions split over the nodes of a network in a decentralized fashion. We propose the algorithm $ESDACD$, a decentralized accelerated algorithm that only requires local synchrony. Its rate depends on the condition number $\kappa$ of the local functions as well as the network topology and delays. Under mild assumptions on the topology of the graph, $ESDACD$ takes a time $O((\tau_{\max} + \Delta_{\max})\sqrt{{\kappa}/{\gamma}}\ln(\epsilon^{-1}))$ to reach a precision $\epsilon$ where $\gamma$ is the spectral gap of the graph, $\tau_{\max}$ the maximum communication delay and $\Delta_{\max}$ the maximum computation time. Therefore, it matches the rate of $SSDA$, which is optimal when $\tau_{\max} = \Omega\left(\Delta_{\max}\right)$. Applying $ESDACD$ to quadratic local functions leads to an accelerated randomized gossip algorithm of rate $O( \sqrt{\theta_{\rm gossip}/n})$ where $\theta_{\rm gossip}$ is the rate of the standard randomized gossip. To the best of our knowledge, it is the first asynchronous gossip algorithm with a provably improved rate of convergence of the second moment of the error. We illustrate these results with experiments in idealized settings. |
| Tasks | |
| Published | 2018-10-05 |
| URL | http://arxiv.org/abs/1810.02660v3 |
| http://arxiv.org/pdf/1810.02660v3.pdf | |
| PWC | https://paperswithcode.com/paper/accelerated-decentralized-optimization-with |
| Repo | |
| Framework | |
Learning and Inferring a Driver’s Braking Action in Car-Following Scenarios
| Title | Learning and Inferring a Driver’s Braking Action in Car-Following Scenarios |
| Authors | Wenshuo Wang, Junqiang Xi, Ding Zhao |
| Abstract | Accurately predicting and inferring a driver’s decision to brake is critical for designing warning systems and avoiding collisions. In this paper we focus on predicting a driver’s intent to brake in car-following scenarios from a perception-decision-action perspective according to his/her driving history. A learning-based inference method, using onboard data from CAN-Bus, radar and cameras as explanatory variables, is introduced to infer drivers’ braking decisions by combining a Gaussian mixture model (GMM) with a hidden Markov model (HMM). The GMM is used to model stochastic relationships among variables, while the HMM is applied to infer drivers’ braking actions based on the GMM. Real-case driving data from 49 drivers (more than three years’ driving data per driver on average) have been collected from the University of Michigan Safety Pilot Model Deployment database. We compare the GMM-HMM method to a support vector machine (SVM) method and an SVM-Bayesian filtering method. The experimental results are evaluated by employing three performance metrics: accuracy, sensitivity, specificity. The comparison results show that the GMM-HMM obtains the best performance, with an accuracy of 90%, sensitivity of 84%, and specificity of 97%. Thus, we believe that this method has great potential for real-world active safety systems. |
| Tasks | |
| Published | 2018-01-11 |
| URL | http://arxiv.org/abs/1801.03905v1 |
| http://arxiv.org/pdf/1801.03905v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-and-inferring-a-drivers-braking |
| Repo | |
| Framework | |
Design of a PCIe Interface Card Control Software Based on WDF
| Title | Design of a PCIe Interface Card Control Software Based on WDF |
| Authors | Meng Shengwei, Lu Jianjie |
| Abstract | Based on a clear analysis of the latest Windows driver framework WDF, this paper has implemented a driver of the PCIe-SpaceWire interface card device and put forward a discussion about ensuring the stability of PCIe driver. At the same time, Qt and OpenGL are used to design the upper application. Finally, a functional verification of the control software is provided. |
| Tasks | |
| Published | 2018-03-24 |
| URL | http://arxiv.org/abs/1803.09052v3 |
| http://arxiv.org/pdf/1803.09052v3.pdf | |
| PWC | https://paperswithcode.com/paper/design-of-a-pcie-interface-card-control |
| Repo | |
| Framework | |
Stratified Negation in Limit Datalog Programs
| Title | Stratified Negation in Limit Datalog Programs |
| Authors | Mark Kaminski, Bernardo Cuenca Grau, Egor V. Kostylev, Boris Motik, Ian Horrocks |
| Abstract | There has recently been an increasing interest in declarative data analysis, where analytic tasks are specified using a logical language, and their implementation and optimisation are delegated to a general-purpose query engine. Existing declarative languages for data analysis can be formalised as variants of logic programming equipped with arithmetic function symbols and/or aggregation, and are typically undecidable. In prior work, the language of $\mathit{limit\ programs}$ was proposed, which is sufficiently powerful to capture many analysis tasks and has decidable entailment problem. Rules in this language, however, do not allow for negation. In this paper, we study an extension of limit programs with stratified negation-as-failure. We show that the additional expressive power makes reasoning computationally more demanding, and provide tight data complexity bounds. We also identify a fragment with tractable data complexity and sufficient expressivity to capture many relevant tasks. |
| Tasks | |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09473v1 |
| http://arxiv.org/pdf/1804.09473v1.pdf | |
| PWC | https://paperswithcode.com/paper/stratified-negation-in-limit-datalog-programs |
| Repo | |
| Framework | |
Adaptive Target Recognition: A Case Study Involving Airport Baggage Screening
| Title | Adaptive Target Recognition: A Case Study Involving Airport Baggage Screening |
| Authors | Ankit Manerikar, Tanmay Prakash, Avinash C. Kak |
| Abstract | This work addresses the question whether it is possible to design a computer-vision based automatic threat recognition (ATR) system so that it can adapt to changing specifications of a threat without having to create a new ATR each time. The changes in threat specifications, which may be warranted by intelligence reports and world events, are typically regarding the physical characteristics of what constitutes a threat: its material composition, its shape, its method of concealment, etc. Here we present our design of an AATR system (Adaptive ATR) that can adapt to changing specifications in materials characterization (meaning density, as measured by its x-ray attenuation coefficient), its mass, and its thickness. Our design uses a two-stage cascaded approach, in which the first stage is characterized by a high recall rate over the entire range of possibilities for the threat parameters that are allowed to change. The purpose of the second stage is to then fine-tune the performance of the overall system for the current threat specifications. The computational effort for this fine-tuning for achieving a desired PD/PFA rate is far less than what it would take to create a new classifier with the same overall performance for the new set of threat specifications. |
| Tasks | |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04772v2 |
| http://arxiv.org/pdf/1811.04772v2.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-target-recognition-a-case-study |
| Repo | |
| Framework | |
Context-aware Data Aggregation with Localized Information Privacy
| Title | Context-aware Data Aggregation with Localized Information Privacy |
| Authors | Bo Jiang, Ming Li, Ravi Tandon |
| Abstract | In this paper, localized information privacy (LIP) is proposed, as a new privacy definition, which allows statistical aggregation while protecting users’ privacy without relying on a trusted third party. The notion of context-awareness is incorporated in LIP by the introduction of priors, which enables the design of privacy-preserving data aggregation with knowledge of priors. We show that LIP relaxes the Localized Differential Privacy (LDP) notion by explicitly modeling the adversary’s knowledge. However, it is stricter than $2\epsilon$-LDP and $\epsilon$-mutual information privacy. The incorporation of local priors allows LIP to achieve higher utility compared to other approaches. We then present an optimization framework for privacy-preserving data aggregation, with the goal of minimizing the expected squared error while satisfying the LIP privacy constraints. Utility-privacy tradeoffs are obtained under several models in closed-form. We then validate our analysis by {numerical analysis} using both synthetic and real-world data. Results show that our LIP mechanism provides better utility-privacy tradeoffs than LDP and when the prior is not uniformly distributed, the advantage of LIP is even more significant. |
| Tasks | |
| Published | 2018-04-06 |
| URL | http://arxiv.org/abs/1804.02149v3 |
| http://arxiv.org/pdf/1804.02149v3.pdf | |
| PWC | https://paperswithcode.com/paper/context-aware-data-aggregation-with-localized |
| Repo | |
| Framework | |
