Paper Group ANR 317
Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting. Evaluating Crowd Density Estimators via Their Uncertainty Bounds. Thompson Sampling with Information Relaxation Penalties. Extension of Convolutional Neural Network with General Image Processing Kernels. Fashion++: Minimal Edits for Outfit Improvement. The Function Representat …
Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting
| Title | Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting |
| Authors | Vishwanath A Sindagi, Vishal M. Patel |
| Abstract | Crowd counting presents enormous challenges in the form of large variation in scales within images and across the dataset. These issues are further exacerbated in highly congested scenes. Approaches based on straightforward fusion of multi-scale features from a deep network seem to be obvious solutions to this problem. However, these fusion approaches do not yield significant improvements in the case of crowd counting in congested scenes. This is usually due to their limited abilities in effectively combining the multi-scale features for problems like crowd counting. To overcome this, we focus on how to efficiently leverage information present in different layers of the network. Specifically, we present a network that involves: (i) a multi-level bottom-top and top-bottom fusion (MBTTBF) method to combine information from shallower to deeper layers and vice versa at multiple levels, (ii) scale complementary feature extraction blocks (SCFB) involving cross-scale residual functions to explicitly enable flow of complementary features from adjacent conv layers along the fusion paths. Furthermore, in order to increase the effectiveness of the multi-scale fusion, we employ a principled way of generating scale-aware ground-truth density maps for training. Experiments conducted on three datasets that contain highly congested scenes (ShanghaiTech, UCF_CC_50, and UCF-QNRF) demonstrate that the proposed method is able to outperform several recent methods in all the datasets. |
| Tasks | Crowd Counting |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10937v1 |
| https://arxiv.org/pdf/1908.10937v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-level-bottom-top-and-top-bottom-feature |
| Repo | |
| Framework | |
Evaluating Crowd Density Estimators via Their Uncertainty Bounds
| Title | Evaluating Crowd Density Estimators via Their Uncertainty Bounds |
| Authors | Jennifer Vandoni, Emanuel Aldea, Sylvie Le Hégarat-Mascle |
| Abstract | In this work, we use the Belief Function Theory which extends the probabilistic framework in order to provide uncertainty bounds to different categories of crowd density estimators. Our method allows us to compare the multi-scale performance of the estimators, and also to characterize their reliability for crowd monitoring applications requiring varying degrees of prudence. |
| Tasks | |
| Published | 2019-02-07 |
| URL | http://arxiv.org/abs/1902.02831v1 |
| http://arxiv.org/pdf/1902.02831v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-crowd-density-estimators-via-their |
| Repo | |
| Framework | |
Thompson Sampling with Information Relaxation Penalties
| Title | Thompson Sampling with Information Relaxation Penalties |
| Authors | Seungki Min, Costis Maglaras, Ciamac C. Moallemi |
| Abstract | We consider a finite time horizon multi-armed bandit (MAB) problem in a Bayesian framework, for which we develop a general set of control policies that leverage ideas from information relaxations of stochastic dynamic optimization problems. In crude terms, an information relaxation allows the decision maker (DM) to have access to the future (unknown) rewards and incorporate them in her optimization problem to pick an action at time $t$, but penalizes the decision maker for using this information. In our setting, the future rewards allow the DM to better estimate the unknown mean reward parameters of the multiple arms, and optimize her sequence of actions. By picking different information penalties, the DM can construct a family of policies of increasing complexity that, for example, include Thompson Sampling and the true optimal (but intractable) policy as special cases. We systematically develop this framework of information relaxation sampling, propose an intuitive family of control policies for our motivating finite time horizon Bayesian MAB problem, and prove associated structural results and performance bounds. Numerical experiments suggest that this new class of policies performs well, in particular in settings where the finite time horizon introduces significant tension in the problem. Finally, inspired by the finite time horizon Gittins index, we propose an index policy that builds on our framework that particularly outperforms to the state-of-the-art algorithms in our numerical experiments. |
| Tasks | |
| Published | 2019-02-12 |
| URL | http://arxiv.org/abs/1902.04251v1 |
| http://arxiv.org/pdf/1902.04251v1.pdf | |
| PWC | https://paperswithcode.com/paper/thompson-sampling-with-information-relaxation |
| Repo | |
| Framework | |
Extension of Convolutional Neural Network with General Image Processing Kernels
| Title | Extension of Convolutional Neural Network with General Image Processing Kernels |
| Authors | Jay Hoon Jung, Yousun Shin, YoungMin Kwon |
| Abstract | We applied pre-defined kernels also known as filters or masks developed for image processing to convolution neural network. Instead of letting neural networks find its own kernels, we used 41 different general-purpose kernels of blurring, edge detecting, sharpening, discrete cosine transformation, etc. for the first layer of the convolution neural networks. This architecture, thus named as general filter convolutional neural network (GFNN), can reduce training time by 30% with a better accuracy compared to the regular convolutional neural network (CNN). GFNN also can be trained to achieve 90% accuracy with only 500 samples. Furthermore, even though these kernels are not specialized for the MNIST dataset, we achieved 99.56% accuracy without ensemble nor any other special algorithms. |
| Tasks | |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1901.07375v1 |
| http://arxiv.org/pdf/1901.07375v1.pdf | |
| PWC | https://paperswithcode.com/paper/extension-of-convolutional-neural-network |
| Repo | |
| Framework | |
Fashion++: Minimal Edits for Outfit Improvement
| Title | Fashion++: Minimal Edits for Outfit Improvement |
| Authors | Wei-Lin Hsiao, Isay Katsman, Chao-Yuan Wu, Devi Parikh, Kristen Grauman |
| Abstract | Given an outfit, what small changes would most improve its fashionability? This question presents an intriguing new vision challenge. We introduce Fashion++, an approach that proposes minimal adjustments to a full-body clothing outfit that will have maximal impact on its fashionability. Our model consists of a deep image generation neural network that learns to synthesize clothing conditioned on learned per-garment encodings. The latent encodings are explicitly factorized according to shape and texture, thereby allowing direct edits for both fit/presentation and color/patterns/material, respectively. We show how to bootstrap Web photos to automatically train a fashionability model, and develop an activation maximization-style approach to transform the input image into its more fashionable self. The edits suggested range from swapping in a new garment to tweaking its color, how it is worn (e.g., rolling up sleeves), or its fit (e.g., making pants baggier). Experiments demonstrate that Fashion++ provides successful edits, both according to automated metrics and human opinion. Project page is at http://vision.cs.utexas.edu/projects/FashionPlus. |
| Tasks | Image Generation |
| Published | 2019-04-19 |
| URL | https://arxiv.org/abs/1904.09261v3 |
| https://arxiv.org/pdf/1904.09261v3.pdf | |
| PWC | https://paperswithcode.com/paper/fashion-minimal-edits-for-outfit-improvement |
| Repo | |
| Framework | |
The Function Representation of Artificial Neural Network
| Title | The Function Representation of Artificial Neural Network |
| Authors | Zhongkui Ma |
| Abstract | This paper expresses the structure of artificial neural network (ANN) as a functional form, using the activation integral concept derived from the activation function. In this way, the structure of ANN can be represented by a simple function, and it is possible to find the mathematical solutions of ANN. Thus, it can be recognized that the current ANN can be placed in a more reasonable framework. Perhaps all questions about ANN will be eliminated. |
| Tasks | |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10493v2 |
| https://arxiv.org/pdf/1908.10493v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-function-representation-of-artificial |
| Repo | |
| Framework | |
Automatic Ambiguity Detection
| Title | Automatic Ambiguity Detection |
| Authors | Richard Sproat, Jan van Santen |
| Abstract | Most work on sense disambiguation presumes that one knows beforehand – e.g. from a thesaurus – a set of polysemous terms. But published lists invariably give only partial coverage. For example, the English word tan has several obvious senses, but one may overlook the abbreviation for tangent. In this paper, we present an algorithm for identifying interesting polysemous terms and measuring their degree of polysemy, given an unlabeled corpus. The algorithm involves: (i) collecting all terms within a k-term window of the target term; (ii) computing the inter-term distances of the contextual terms, and reducing the multi-dimensional distance space to two dimensions using standard methods; (iii) converting the two-dimensional representation into radial coordinates and using isotonic/antitonic regression to compute the degree to which the distribution deviates from a single-peak model. The amount of deviation is the proposed polysemy index |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.12065v1 |
| https://arxiv.org/pdf/1905.12065v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-ambiguity-detection |
| Repo | |
| Framework | |
Towards Unsupervised Segmentation of Extreme Weather Events
| Title | Towards Unsupervised Segmentation of Extreme Weather Events |
| Authors | Adam Rupe, Karthik Kashinath, Nalini Kumar, Victor Lee, Prabhat, James P. Crutchfield |
| Abstract | Extreme weather is one of the main mechanisms through which climate change will directly impact human society. Coping with such change as a global community requires markedly improved understanding of how global warming drives extreme weather events. While alternative climate scenarios can be simulated using sophisticated models, identifying extreme weather events in these simulations requires automation due to the vast amounts of complex high-dimensional data produced. Atmospheric dynamics, and hydrodynamic flows more generally, are highly structured and largely organize around a lower dimensional skeleton of coherent structures. Indeed, extreme weather events are a special case of more general hydrodynamic coherent structures. We present a scalable physics-based representation learning method that decomposes spatiotemporal systems into their structurally relevant components, which are captured by latent variables known as local causal states. For complex fluid flows we show our method is capable of capturing known coherent structures, and with promising segmentation results on CAM5.1 water vapor data we outline the path to extreme weather identification from unlabeled climate model simulation data. |
| Tasks | Representation Learning |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07520v1 |
| https://arxiv.org/pdf/1909.07520v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-unsupervised-segmentation-of-extreme |
| Repo | |
| Framework | |
Noise Induces Loss Discrepancy Across Groups for Linear Regression
| Title | Noise Induces Loss Discrepancy Across Groups for Linear Regression |
| Authors | Fereshte Khani, Percy Liang |
| Abstract | We study the effect of feature noise (measurement error) on the discrepancy between losses across two groups (e.g., men and women) in the context of linear regression. Our main finding is that adding even the same amount of noise on all individuals impacts groups differently. We characterize several forms of loss discrepancy in terms of the amount of noise and difference between moments of the two groups, for estimators that either do or do not use group membership information. We then study how long it takes for an estimator to adapt to a shift in the population that makes the groups have the same mean. We finally validate our results on three real-world datasets. |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09876v1 |
| https://arxiv.org/pdf/1911.09876v1.pdf | |
| PWC | https://paperswithcode.com/paper/noise-induces-loss-discrepancy-across-groups |
| Repo | |
| Framework | |
Equation Discovery for Nonlinear System Identification
| Title | Equation Discovery for Nonlinear System Identification |
| Authors | Nikola Simidjievski, Ljupčo Todorovski, Juš Kocijan, Sašo Džeroski |
| Abstract | Equation discovery methods enable modelers to combine domain-specific knowledge and system identification to construct models most suitable for a selected modeling task. The method described and evaluated in this paper can be used as a nonlinear system identification method for gray-box modeling. It consists of two interlaced parts of modeling that are computer-aided. The first performs computer-aided identification of a model structure composed of elements selected from user-specified domain-specific modeling knowledge, while the second part performs parameter estimation. In this paper, recent developments of the equation discovery method called process-based modeling, suited for nonlinear system identification, are elaborated and illustrated on two continuous-time case studies. The first case study illustrates the use of the process-based modeling on synthetic data while the second case-study evaluates on measured data for a standard system-identification benchmark. The experimental results clearly demonstrate the ability of process-based modeling to reconstruct both model structure and parameters from measured data. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.00821v1 |
| https://arxiv.org/pdf/1907.00821v1.pdf | |
| PWC | https://paperswithcode.com/paper/equation-discovery-for-nonlinear-system |
| Repo | |
| Framework | |
Cluster-wise Unsupervised Hashing for Cross-Modal Similarity Search
| Title | Cluster-wise Unsupervised Hashing for Cross-Modal Similarity Search |
| Authors | Lu Wang, Jie Yang |
| Abstract | Large-scale cross-modal hashing similarity retrieval has attracted more and more attention in modern search applications such as search engines and autopilot, showing great superiority in computation and storage. However, current unsupervised cross-modal hashing methods still have some limitations: (1)many methods relax the discrete constraints to solve the optimization objective which may significantly degrade the retrieval performance;(2)most existing hashing model project heterogenous data into a common latent space, which may always lose sight of diversity in heterogenous data;(3)transforming real-valued data point to binary codes always results in abundant loss of information, producing the suboptimal continuous latent space. To overcome above problems, in this paper, a novel Cluster-wise Unsupervised Hashing (CUH) method is proposed. Specifically, CUH jointly performs the multi-view clustering that projects the original data points from different modalities into its own low-dimensional latent semantic space and finds the cluster centroid points and the common clustering indicators in its own low-dimensional space, and learns the compact hash codes and the corresponding linear hash functions. An discrete optimization framework is developed to learn the unified binary codes across modalities under the guidance cluster-wise code-prototypes. The reasonableness and effectiveness of CUH is well demonstrated by comprehensive experiments on diverse benchmark datasets. |
| Tasks | |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.07923v2 |
| https://arxiv.org/pdf/1911.07923v2.pdf | |
| PWC | https://paperswithcode.com/paper/cluster-wise-unsupervised-hashing-for-cross |
| Repo | |
| Framework | |
SemEval-2017 Task 3: Community Question Answering
| Title | SemEval-2017 Task 3: Community Question Answering |
| Authors | Preslav Nakov, Doris Hoogeveen, Lluís Màrquez, Alessandro Moschitti, Hamdy Mubarak, Timothy Baldwin, Karin Verspoor |
| Abstract | We describe SemEval-2017 Task 3 on Community Question Answering. This year, we reran the four subtasks from SemEval-2016:(A) Question-Comment Similarity,(B) Question-Question Similarity,(C) Question-External Comment Similarity, and (D) Rerank the correct answers for a new question in Arabic, providing all the data from 2015 and 2016 for training, and fresh data for testing. Additionally, we added a new subtask E in order to enable experimentation with Multi-domain Question Duplicate Detection in a larger-scale scenario, using StackExchange subforums. A total of 23 teams participated in the task, and submitted a total of 85 runs (36 primary and 49 contrastive) for subtasks A-D. Unfortunately, no teams participated in subtask E. A variety of approaches and features were used by the participating systems to address the different subtasks. The best systems achieved an official score (MAP) of 88.43, 47.22, 15.46, and 61.16 in subtasks A, B, C, and D, respectively. These scores are better than the baselines, especially for subtasks A-C. |
| Tasks | Community Question Answering, Question Answering, Question Similarity |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00730v1 |
| https://arxiv.org/pdf/1912.00730v1.pdf | |
| PWC | https://paperswithcode.com/paper/semeval-2017-task-3-community-question-1 |
| Repo | |
| Framework | |
Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network
| Title | Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network |
| Authors | Jiexiang Wang, Hongyu Huang, Chaoqi Chen, Wenao Ma, Yue Huang, Xinghao Ding |
| Abstract | Automatic and accurate segmentation of the ventricles and myocardium from multi-sequence cardiac MRI (CMR) is crucial for the diagnosis and treatment management for patients suffering from myocardial infarction (MI). However, due to the existence of domain shift among different modalities of datasets, the performance of deep neural networks drops significantly when the training and testing datasets are distinct. In this paper, we propose an unsupervised domain alignment method to explicitly alleviate the domain shifts among different modalities of CMR sequences, \emph{e.g.,} bSSFP, LGE, and T2-weighted. Our segmentation network is attention U-Net with pyramid pooling module, where multi-level feature space and output space adversarial learning are proposed to transfer discriminative domain knowledge across different datasets. Moreover, we further introduce a group-wise feature recalibration module to enforce the fine-grained semantic-level feature alignment that matching features from different networks but with the same class label. We evaluate our method on the multi-sequence cardiac MR Segmentation Challenge 2019 datasets, which contain three different modalities of MRI sequences. Extensive experimental results show that the proposed methods can obtain significant segmentation improvements compared with the baseline models. |
| Tasks | Domain Adaptation |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12514v1 |
| https://arxiv.org/pdf/1910.12514v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-sequence-cardiac-mr-segmentation-with |
| Repo | |
| Framework | |
A Rule-Based Relational XML Access Control Model in the Presence of Authorization Conflicts
| Title | A Rule-Based Relational XML Access Control Model in the Presence of Authorization Conflicts |
| Authors | Ali Alwehaibi, Mustafa Atay |
| Abstract | There is considerable amount of sensitive XML data stored in relational databases. It is a challenge to enforce node level fine-grained authorization policies for XML data stored in relational databases which typically support table and column level access control. Moreover, it is common to have conflicting authorization policies over the hierarchical nested structure of XML data. There are a couple of XML access control models for relational XML databases proposed in the literature. However, to our best knowledge, none of them discussed handling authorization conflicts with conditions in the domain of relational XML databases. Therefore, we believe that there is a need to define and incorporate effective fine-grained XML authorization models with conflict handling mechanisms in the presence of conditions into relational XML databases. We address this issue in this study. |
| Tasks | |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.11057v1 |
| https://arxiv.org/pdf/1909.11057v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-rule-based-relational-xml-access-control |
| Repo | |
| Framework | |
Evaluating the distribution learning capabilities of GANs
| Title | Evaluating the distribution learning capabilities of GANs |
| Authors | Amit Rege, Claire Monteleoni |
| Abstract | We evaluate the distribution learning capabilities of generative adversarial networks by testing them on synthetic datasets. The datasets include common distributions of points in $R^n$ space and images containing polygons of various shapes and sizes. We find that by and large GANs fail to faithfully recreate point datasets which contain discontinous support or sharp bends with noise. Additionally, on image datasets, we find that GANs do not seem to learn to count the number of objects of the same kind in an image. We also highlight the apparent tension between generalization and learning in GANs. |
| Tasks | |
| Published | 2019-07-05 |
| URL | https://arxiv.org/abs/1907.02662v1 |
| https://arxiv.org/pdf/1907.02662v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-the-distribution-learning |
| Repo | |
| Framework | |
