January 29, 2020

2809 words 14 mins read

Paper Group ANR 702

Similarity Measure Development for Case-Based Reasoning- A Data-driven Approach. Embedding time expressions for deep temporal ordering models. Deep Learning and Word Embeddings for Tweet Classification for Crisis Response. Reflections on “Incremental Cardinality Constraints for MaxSAT”. Everyone is a Cartoonist: Selfie Cartoonization with Attentive …

Similarity Measure Development for Case-Based Reasoning- A Data-driven Approach


Title	Similarity Measure Development for Case-Based Reasoning- A Data-driven Approach
Authors	Deepika Verma, Kerstin Bach, Paul Jarle Mork
Abstract	In this paper, we demonstrate a data-driven methodology for modelling the local similarity measures of various attributes in a dataset. We analyse the spread in the numerical attributes and estimate their distribution using polynomial function to showcase an approach for deriving strong initial value ranges of numerical attributes and use a non-overlapping distribution for categorical attributes such that the entire similarity range [0,1] is utilized. We use an open source dataset for demonstrating modelling and development of the similarity measures and will present a case-based reasoning (CBR) system that can be used to search for the most relevant similar cases.
Tasks
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08581v1
PDF	https://arxiv.org/pdf/1905.08581v1.pdf
PWC	https://paperswithcode.com/paper/similarity-measure-development-for-case-based
Repo
Framework

Embedding time expressions for deep temporal ordering models


Title	Embedding time expressions for deep temporal ordering models
Authors	Tanya Goyal, Greg Durrett
Abstract	Data-driven models have demonstrated state-of-the-art performance in inferring the temporal ordering of events in text. However, these models often overlook explicit temporal signals, such as dates and time windows. Rule-based methods can be used to identify the temporal links between these time expressions (timexes), but they fail to capture timexes’ interactions with events and are hard to integrate with the distributed representations of neural net models. In this paper, we introduce a framework to infuse temporal awareness into such models by learning a pre-trained model to embed timexes. We generate synthetic data consisting of pairs of timexes, then train a character LSTM to learn embeddings and classify the timexes’ temporal relation. We evaluate the utility of these embeddings in the context of a strong neural model for event temporal ordering, and show a small increase in performance on the MATRES dataset and more substantial gains on an automatically collected dataset with more frequent event-timex interactions.
Tasks
Published	2019-06-19
URL	https://arxiv.org/abs/1906.08287v1
PDF	https://arxiv.org/pdf/1906.08287v1.pdf
PWC	https://paperswithcode.com/paper/embedding-time-expressions-for-deep-temporal
Repo
Framework

Deep Learning and Word Embeddings for Tweet Classification for Crisis Response


Title	Deep Learning and Word Embeddings for Tweet Classification for Crisis Response
Authors	Reem ALRashdi, Simon O’Keefe
Abstract	Tradition tweet classification models for crisis response focus on convolutional layers and domain-specific word embeddings. In this paper, we study the application of different neural networks with general-purpose and domain-specific word embeddings to investigate their ability to improve the performance of tweet classification models. We evaluate four tweet classification models on CrisisNLP dataset and obtain comparable results which indicates that general-purpose word embedding such as GloVe can be used instead of domain-specific word embedding especially with Bi-LSTM where results reported the highest performance of 62.04% F1 score.
Tasks	Word Embeddings
Published	2019-03-26
URL	http://arxiv.org/abs/1903.11024v1
PDF	http://arxiv.org/pdf/1903.11024v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-and-word-embeddings-for-tweet
Repo
Framework

Reflections on “Incremental Cardinality Constraints for MaxSAT”


Title	Reflections on “Incremental Cardinality Constraints for MaxSAT”
Authors	Ruben Martins, Saurabh Joshi, Vasco Manquinho, Ines Lynce
Abstract	To celebrate the first 25 years of the International Conference on Principles and Practice of Constraint Programming (CP) the editors invited the authors of the most cited paper of each year to write a commentary on their paper. This report describes our reflections on the CP 2014 paper “Incremental Cardinality Constraints for MaxSAT” and its impact on the Maximum Satisfiability community and beyond.
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04643v1
PDF	https://arxiv.org/pdf/1910.04643v1.pdf
PWC	https://paperswithcode.com/paper/reflections-on-incremental-cardinality
Repo
Framework

Everyone is a Cartoonist: Selfie Cartoonization with Attentive Adversarial Networks


Title	Everyone is a Cartoonist: Selfie Cartoonization with Attentive Adversarial Networks
Authors	Xinyu Li, Wei Zhang, Tong Shen, Tao Mei
Abstract	Selfie and cartoon are two popular artistic forms that are widely presented in our daily life. Despite the great progress in image translation/stylization, few techniques focus specifically on selfie cartoonization, since cartoon images usually contain artistic abstraction (e.g., large smoothing areas) and exaggeration (e.g., large/delicate eyebrows). In this paper, we address this problem by proposing a selfie cartoonization Generative Adversarial Network (scGAN), which mainly uses an attentive adversarial network (AAN) to emphasize specific facial regions and ignore low-level details. More specifically, we first design a cycle-like architecture to enable training with unpaired data. Then we design three losses from different aspects. A total variation loss is used to highlight important edges and contents in cartoon portraits. An attentive cycle loss is added to lay more emphasis on delicate facial areas such as eyes. In addition, a perceptual loss is included to eliminate artifacts and improve robustness of our method. Experimental results show that our method is capable of generating different cartoon styles and outperforms a number of state-of-the-art methods.
Tasks
Published	2019-04-20
URL	http://arxiv.org/abs/1904.12615v1
PDF	http://arxiv.org/pdf/1904.12615v1.pdf
PWC	https://paperswithcode.com/paper/190412615
Repo
Framework

The Role of Publicly Available Data in MICCAI Papers from 2014 to 2018


Title	The Role of Publicly Available Data in MICCAI Papers from 2014 to 2018
Authors	Nicholas Heller, Jack Rickman, Christopher Weight, Nikolaos Papanikolopoulos
Abstract	Widely-used public benchmarks are of huge importance to computer vision and machine learning research, especially with the computational resources required to reproduce state of the art results quickly becoming untenable. In medical image computing, the wide variety of image modalities and problem formulations yields a huge task-space for benchmarks to cover, and thus the widespread adoption of standard benchmarks has been slow, and barriers to releasing medical data exacerbate this issue. In this paper, we examine the role that publicly available data has played in MICCAI papers from the past five years. We find that more than half of these papers are based on private data alone, although this proportion seems to be decreasing over time. Additionally, we observed that after controlling for open access publication and the release of code, papers based on public data were cited over 60% more per year than their private-data counterparts. Further, we found that more than 20% of papers using public data did not provide a citation to the dataset or associated manuscript, highlighting the “second-rate” status that data contributions often take compared to theoretical ones. We conclude by making recommendations for MICCAI policies which could help to better incentivise data sharing and move the field toward more efficient and reproducible science.
Tasks
Published	2019-08-12
URL	https://arxiv.org/abs/1908.06830v1
PDF	https://arxiv.org/pdf/1908.06830v1.pdf
PWC	https://paperswithcode.com/paper/the-role-of-publicly-available-data-in-miccai
Repo
Framework

Trip Table Estimation and Prediction for Dynamic Traffic Assignment Applications


Title	Trip Table Estimation and Prediction for Dynamic Traffic Assignment Applications
Authors	Sajjad Shafiei, Adriana-Simona Mihaita, Chen Cai
Abstract	The study focuses on estimating and predicting time-varying origin to destination (OD) trip tables for a dynamic traffic assignment (DTA) model. A bi-level optimisation problem is formulated and solved to estimate OD flows from pre-existent demand matrix and historical traffic flow counts. The estimated demand is then considered as an input for a time series OD demand prediction model to support the DTA model for short-term traffic condition forecasting. Results show a high capability of the proposed OD demand estimation method to reduce the DTA model error through an iterative solution algorithm. Moreover, the applicability of the OD demand prediction approach is investigated for an incident analysis application for a major corridor in Sydney, Australia.
Tasks	Time Series
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04739v1
PDF	https://arxiv.org/pdf/1906.04739v1.pdf
PWC	https://paperswithcode.com/paper/trip-table-estimation-and-prediction-for
Repo
Framework


Title	Online Deep Reinforcement Learning for Autonomous UAV Navigation and Exploration of Outdoor Environments
Authors	Bruna G. Maciel-Pearson, Letizia Marchegiani, Samet Akcay, Amir Atapour-Abarghouei, James Garforth, Toby P. Breckon
Abstract	With the rapidly growing expansion in the use of UAVs, the ability to autonomously navigate in varying environments and weather conditions remains a highly desirable but as-of-yet unsolved challenge. In this work, we use Deep Reinforcement Learning to continuously improve the learning and understanding of a UAV agent while exploring a partially observable environment, which simulates the challenges faced in a real-life scenario. Our innovative approach uses a double state-input strategy that combines the acquired knowledge from the raw image and a map containing positional information. This positional data aids the network understanding of where the UAV has been and how far it is from the target position, while the feature map from the current scene highlights cluttered areas that are to be avoided. Our approach is extensively tested using variants of Deep Q-Network adapted to cope with double state input data. Further, we demonstrate that by altering the reward and the Q-value function, the agent is capable of consistently outperforming the adapted Deep Q-Network, Double Deep Q- Network and Deep Recurrent Q-Network. Our results demonstrate that our proposed Extended Double Deep Q-Network (EDDQN) approach is capable of navigating through multiple unseen environments and under severe weather conditions.
Tasks
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05684v1
PDF	https://arxiv.org/pdf/1912.05684v1.pdf
PWC	https://paperswithcode.com/paper/online-deep-reinforcement-learning-for
Repo
Framework

Dialogue Act Classification with Context-Aware Self-Attention


Title	Dialogue Act Classification with Context-Aware Self-Attention
Authors	Vipul Raheja, Joel Tetreault
Abstract	Recent work in Dialogue Act classification has treated the task as a sequence labeling problem using hierarchical deep neural networks. We build on this prior work by leveraging the effectiveness of a context-aware self-attention mechanism coupled with a hierarchical recurrent neural network. We conduct extensive evaluations on standard Dialogue Act classification datasets and show significant improvement over state-of-the-art results on the Switchboard Dialogue Act (SwDA) Corpus. We also investigate the impact of different utterance-level representation learning methods and show that our method is effective at capturing utterance-level semantic text representations while maintaining high accuracy.
Tasks	Dialogue Act Classification, Representation Learning
Published	2019-04-04
URL	https://arxiv.org/abs/1904.02594v2
PDF	https://arxiv.org/pdf/1904.02594v2.pdf
PWC	https://paperswithcode.com/paper/dialogue-act-classification-with-context
Repo
Framework

Stochastic Variance Reduction for Deep Q-learning


Title	Stochastic Variance Reduction for Deep Q-learning
Authors	Wei-Ye Zhao, Xi-Ya Guan, Yang Liu, Xiaoming Zhao, Jian Peng
Abstract	Recent advances in deep reinforcement learning have achieved human-level performance on a variety of real-world applications. However, the current algorithms still suffer from poor gradient estimation with excessive variance, resulting in unstable training and poor sample efficiency. In our paper, we proposed an innovative optimization strategy by utilizing stochastic variance reduced gradient (SVRG) techniques. With extensive experiments on Atari domain, our method outperforms the deep q-learning baselines on 18 out of 20 games.
Tasks	Q-Learning
Published	2019-05-20
URL	https://arxiv.org/abs/1905.08152v1
PDF	https://arxiv.org/pdf/1905.08152v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-variance-reduction-for-deep-q
Repo
Framework

Baseline Desensitizing In Translation Averaging


Title	Baseline Desensitizing In Translation Averaging
Authors	Bingbing Zhuang, Loong-Fah Cheong, Gim Hee Lee
Abstract	Many existing translation averaging algorithms are either sensitive to disparate camera baselines and have to rely on extensive preprocessing to improve the observed Epipolar Geometry graph, or if they are robust against disparate camera baselines, require complicated optimization to minimize the highly nonlinear angular error objective. In this paper, we carefully design a simple yet effective bilinear objective function, introducing a variable to perform the requisite normalization. The objective function enjoys the baseline-insensitive property of the angular error and yet is amenable to simple and efficient optimization by block coordinate descent, with good empirical performance. A rotation-assisted Iterative Reweighted Least Squares scheme is further put forth to help deal with outliers. We also contribute towards a better understanding of the behavior of two recent convex algorithms, LUD and Shapefit/kick, clarifying the underlying subtle difference that leads to the performance gap. Finally, we demonstrate that our algorithm achieves overall superior accuracies in benchmark dataset compared to state-of-theart methods, and is also several times faster.
Tasks
Published	2019-01-03
URL	http://arxiv.org/abs/1901.00643v1
PDF	http://arxiv.org/pdf/1901.00643v1.pdf
PWC	https://paperswithcode.com/paper/baseline-desensitizing-in-translation
Repo
Framework

Spectral Algorithm for Low-rank Multitask Regression


Title	Spectral Algorithm for Low-rank Multitask Regression
Authors	Yotam Gigi, Ami Wiesel, Sella Nevo, Gal Elidan, Avinatan Hassidim, Yossi Matias
Abstract	Multitask learning, i.e. taking advantage of the relatedness of individual tasks in order to improve performance on all of them, is a core challenge in the field of machine learning. We focus on matrix regression tasks where the rank of the weight matrix is constrained to reduce sample complexity. We introduce the common mechanism regression (CMR) model which assumes a shared left low-rank component across all tasks, but allows an individual per-task right low-rank component. This dramatically reduces the number of samples needed for accurate estimation. The problem of jointly recovering the common and the local components has a non-convex bi-linear structure. We overcome this hurdle and provide a provably beneficial non-iterative spectral algorithm. Appealingly, the solution has favorable behavior as a function of the number of related tasks and the small number of samples available for each one. We demonstrate the efficacy of our approach for the challenging task of remote river discharge estimation across multiple river sites, where data for each task is naturally scarce. In this scenario sharing a low-rank component between the tasks translates to a shared spectral reflection of the water, which is a true underlying physical model. We also show the benefit of the approach on the markedly different setting of image classification where the common component can be interpreted as the shared convolution filters.
Tasks	Image Classification
Published	2019-10-27
URL	https://arxiv.org/abs/1910.12204v1
PDF	https://arxiv.org/pdf/1910.12204v1.pdf
PWC	https://paperswithcode.com/paper/spectral-algorithm-for-low-rank-multitask
Repo
Framework

CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing


Title	CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing
Authors	Xin Jin, Cuiling Lan, Wenjun Zeng, Zhizheng Zhang, Zhibo Chen
Abstract	Objects in an image exhibit diverse scales. Adaptive receptive fields are expected to catch suitable range of context for accurate pixel level semantic prediction for handling objects of diverse sizes. Recently, atrous convolution with different dilation rates has been used to generate features of multi-scales through several branches and these features are fused for prediction. However, there is a lack of explicit interaction among the branches to adaptively make full use of the contexts. In this paper, we propose a Content-Adaptive Scale Interaction Network (CaseNet) to exploit the multi-scale features for scene parsing. We build the CaseNet based on the classic Atrous Spatial Pyramid Pooling (ASPP) module, followed by the proposed contextual scale interaction (CSI) module, and the scale adaptation (SA) module. Specifically, first, for each spatial position, we enable context interaction among different scales through scale-aware non-local operations across the scales, \ie, CSI module, which facilitates the generation of flexible mixed receptive fields, instead of a traditional flat one. Second, the scale adaptation module (SA) explicitly and softly selects the suitable scale for each spatial position and each channel. Ablation studies demonstrate the effectiveness of the proposed modules. We achieve state-of-the-art performance on three scene parsing benchmarks Cityscapes, ADE20K and LIP.
Tasks	Scene Parsing
Published	2019-04-17
URL	https://arxiv.org/abs/1904.08170v2
PDF	https://arxiv.org/pdf/1904.08170v2.pdf
PWC	https://paperswithcode.com/paper/casenet-content-adaptive-scale-interaction
Repo
Framework

Learning Shape Templates with Structured Implicit Functions


Title	Learning Shape Templates with Structured Implicit Functions
Authors	Kyle Genova, Forrester Cole, Daniel Vlasic, Aaron Sarna, William T. Freeman, Thomas Funkhouser
Abstract	Template 3D shapes are useful for many tasks in graphics and vision, including fitting observation data, analyzing shape collections, and transferring shape attributes. Because of the variety of geometry and topology of real-world shapes, previous methods generally use a library of hand-made templates. In this paper, we investigate learning a general shape template from data. To allow for widely varying geometry and topology, we choose an implicit surface representation based on composition of local shape elements. While long known to computer graphics, this representation has not yet been explored in the context of machine learning for vision. We show that structured implicit functions are suitable for learning and allow a network to smoothly and simultaneously fit multiple classes of shapes. The learned shape template supports applications such as shape exploration, correspondence, abstraction, interpolation, and semantic segmentation from an RGB image.
Tasks	Semantic Segmentation
Published	2019-04-12
URL	http://arxiv.org/abs/1904.06447v1
PDF	http://arxiv.org/pdf/1904.06447v1.pdf
PWC	https://paperswithcode.com/paper/learning-shape-templates-with-structured
Repo
Framework

Boosting the Rating Prediction with Click Data and Textual Contents


Title	Boosting the Rating Prediction with Click Data and Textual Contents
Authors	ThaiBinh Nguyen, Atsuhiro Takasu
Abstract	Matrix factorization (MF) is one of the most efficient methods for rating predictions. MF learns user and item representations by factorizing the user-item rating matrix. Further, textual contents are integrated to conventional MF to address the cold-start problem. However, the textual contents do not reflect all aspects of the items. In this paper, we propose a model that leverages the information hidden in the item co-click (i.e., items that are often clicked together by a user) into learning item representations. We develop TCMF (Textual Co Matrix Factorization) that learns the user and item representations jointly from the user-item matrix, textual contents and item co-click matrix built from click data. Item co-click information captures the relationships between items which are not captured via textual contents. The experiments on two real-world datasets MovieTweetings, and Bookcrossing) demonstrate that our method outperforms competing methods in terms of rating prediction. Further, we show that the proposed model can learn effective item representations by comparing with state-of-the-art methods in classification task which uses the item representations as input vectors.
Tasks
Published	2019-08-21
URL	https://arxiv.org/abs/1908.07749v1
PDF	https://arxiv.org/pdf/1908.07749v1.pdf
PWC	https://paperswithcode.com/paper/190807749
Repo
Framework