Paper Group ANR 1506
Texture Retrieval in the Wild through detection-based attributes. Classification Betters Regression in Query-based Multi-document Summarisation Techniques for Question Answering: Macquarie University at BioASQ7b. Handwritten Amharic Character Recognition Using a Convolutional Neural Network. Deep Robust Subjective Visual Property Prediction in Crow …
Texture Retrieval in the Wild through detection-based attributes
| Title | Texture Retrieval in the Wild through detection-based attributes |
| Authors | Christian Joppi, Marco Godi, Andrea Giachetti, Fabio Pellacini, Marco Cristani |
| Abstract | Capturing the essence of a textile image in a robust way is important to retrieve it in a large repository, especially if it has been acquired in the wild (by taking a photo of the textile of interest). In this paper we show that a texel-based representation fits well with this task. In particular, we refer to Texel-Att, a recent texel-based descriptor which has shown to capture fine grained variations of a texture, for retrieval purposes. After a brief explanation of Texel-Att, we will show in our experiments that this descriptor is robust to distortions resulting from acquisitions in the wild by setting up an experiment in which textures from the ElBa (an Element-Based texture dataset) are artificially distorted and then used to retrieve the original image. We compare our approach with existing descriptors using a simple ranking framework based on distance functions. Results show that even under extreme conditions (such as a down-sampling with a factor of 10), we perform better than alternative approaches. |
| Tasks | |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11111v4 |
| https://arxiv.org/pdf/1908.11111v4.pdf | |
| PWC | https://paperswithcode.com/paper/texture-retrieval-in-the-wild-through |
| Repo | |
| Framework | |
Classification Betters Regression in Query-based Multi-document Summarisation Techniques for Question Answering: Macquarie University at BioASQ7b
| Title | Classification Betters Regression in Query-based Multi-document Summarisation Techniques for Question Answering: Macquarie University at BioASQ7b |
| Authors | Diego Molla, Christopher Jones |
| Abstract | Task B Phase B of the 2019 BioASQ challenge focuses on biomedical question answering. Macquarie University’s participation applies query-based multi-document extractive summarisation techniques to generate a multi-sentence answer given the question and the set of relevant snippets. In past participation we explored the use of regression approaches using deep learning architectures and a simple policy gradient architecture. For the 2019 challenge we experiment with the use of classification approaches with and without reinforcement learning. In addition, we conduct a correlation analysis between various ROUGE metrics and the BioASQ human evaluation scores. |
| Tasks | Question Answering |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.00542v1 |
| https://arxiv.org/pdf/1909.00542v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-betters-regression-in-query |
| Repo | |
| Framework | |
Handwritten Amharic Character Recognition Using a Convolutional Neural Network
| Title | Handwritten Amharic Character Recognition Using a Convolutional Neural Network |
| Authors | Mesay Samuel Gondere, Lars Schmidt-Thieme, Abiot Sinamo Boltena, Hadi Samer Jomaa |
| Abstract | Amharic is the official language of the Federal Democratic Republic of Ethiopia. There are lots of historic Amharic and Ethiopic handwritten documents addressing various relevant issues including governance, science, religious, social rules, cultures and art works which are very reach indigenous knowledge. The Amharic language has its own alphabet derived from Ge’ez which is currently the liturgical language in Ethiopia. Handwritten character recognition for non Latin scripts like Amharic is not addressed especially using the advantages of the state of the art techniques. This research work designs for the first time a model for Amharic handwritten character recognition using a convolutional neural network. The dataset was organized from collected sample handwritten documents and data augmentation was applied for machine learning. The model was further enhanced using multi-task learning from the relationships of the characters. Promising results are observed from the later model which can further be applied to word prediction. |
| Tasks | Data Augmentation, Multi-Task Learning |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.12943v1 |
| https://arxiv.org/pdf/1909.12943v1.pdf | |
| PWC | https://paperswithcode.com/paper/handwritten-amharic-character-recognition-1 |
| Repo | |
| Framework | |
Deep Robust Subjective Visual Property Prediction in Crowdsourcing
| Title | Deep Robust Subjective Visual Property Prediction in Crowdsourcing |
| Authors | Qianqian Xu, Zhiyong Yang, Yangbangyan Jiang, Xiaochun Cao, Qingming Huang, Yuan Yao |
| Abstract | The problem of estimating subjective visual properties (SVP) of images (e.g., Shoes A is more comfortable than B) is gaining rising attention. Due to its highly subjective nature, different annotators often exhibit different interpretations of scales when adopting absolute value tests. Therefore, recent investigations turn to collect pairwise comparisons via crowdsourcing platforms. However, crowdsourcing data usually contains outliers. For this purpose, it is desired to develop a robust model for learning SVP from crowdsourced noisy annotations. In this paper, we construct a deep SVP prediction model which not only leads to better detection of annotation outliers but also enables learning with extremely sparse annotations. Specifically, we construct a comparison multi-graph based on the collected annotations, where different labeling results correspond to edges with different directions between two vertexes. Then, we propose a generalized deep probabilistic framework which consists of an SVP prediction module and an outlier modeling module that work collaboratively and are optimized jointly. Extensive experiments on various benchmark datasets demonstrate that our new approach guarantees promising results. |
| Tasks | |
| Published | 2019-03-10 |
| URL | http://arxiv.org/abs/1903.03956v1 |
| http://arxiv.org/pdf/1903.03956v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-robust-subjective-visual-property |
| Repo | |
| Framework | |
OWA aggregation of multi-criteria with mixed uncertain fuzzy satisfactions
| Title | OWA aggregation of multi-criteria with mixed uncertain fuzzy satisfactions |
| Authors | Yunjuan Wang, Yong Deng |
| Abstract | We apply the Ordered Weighted Averaging (OWA) operator in multi-criteria decision-making. To satisfy different kinds of uncertainty, measure based dominance has been presented to gain the order of different criterion. However, this idea has not been applied in fuzzy system until now. In this paper, we focus on the situation where the linguistic satisfactions are fuzzy measures instead of the exact values. We review the concept of OWA operator and discuss the order mechanism of fuzzy number. Then we combine with measure-based dominance to give an overall score of each alternatives. An example is illustrated to show the whole procedure. |
| Tasks | Decision Making |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.09784v1 |
| http://arxiv.org/pdf/1901.09784v1.pdf | |
| PWC | https://paperswithcode.com/paper/owa-aggregation-of-multi-criteria-with-mixed |
| Repo | |
| Framework | |
Comparison of Generative Adversarial Networks Architectures Which Reduce Mode Collapse
| Title | Comparison of Generative Adversarial Networks Architectures Which Reduce Mode Collapse |
| Authors | Yicheng, Hong |
| Abstract | Generative Adversarial Networks are known for their high quality outputs and versatility. However, they also suffer the mode collapse in their output data distribution. There have been many efforts to revamp GANs model and reduce mode collapse. This paper focuses on two of these models, PacGAN and VEEGAN. This paper explains the mathematical theory behind aforementioned models, and compare their degree of mode collapse with vanilla GAN using MNIST digits as input data. The result indicates that PacGAN performs slightly better than vanilla GAN in terms of mode collapse, and VEEGAN performs worse than both PacGAN and vanilla GAN. VEEGAN’s poor performance may be attributed to average autoencoder loss in its objective function and small penalty for blurry features. |
| Tasks | |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04636v1 |
| https://arxiv.org/pdf/1910.04636v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-generative-adversarial-networks |
| Repo | |
| Framework | |
A Universal Parent Model for Low-Resource Neural Machine Translation Transfer
| Title | A Universal Parent Model for Low-Resource Neural Machine Translation Transfer |
| Authors | Mozhdeh Gheini, Jonathan May |
| Abstract | Transfer learning from a high-resource language pair parent' has been proven to be an effective way to improve neural machine translation quality for low-resource language pairs children.’ However, previous approaches build a custom parent model or at least update an existing parent model’s vocabulary for each child language pair they wish to train, in an effort to align parent and child vocabularies. This is not a practical solution. It is wasteful to devote the majority of training time for new language pairs to optimizing parameters on an unrelated data set. Further, this overhead reduces the utility of neural machine translation for deployment in humanitarian assistance scenarios, where extra time to deploy a new language pair can mean the difference between life and death. In this work, we present a `universal’ pre-trained neural parent model with constant vocabulary that can be used as a starting point for training practically any new low-resource language to a fixed target language. We demonstrate that our approach, which leverages orthography unification and a broad-coverage approach to subword identification, generalizes well to several languages from a variety of families, and that translation systems built with our approach can be built more quickly than competing methods and with better quality as well. | |
| Tasks | Low-Resource Neural Machine Translation, Machine Translation, Transfer Learning |
| Published | 2019-09-14 |
| URL | https://arxiv.org/abs/1909.06516v2 |
| https://arxiv.org/pdf/1909.06516v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-universal-parent-model-for-low-resource |
| Repo | |
| Framework | |
What’s Wrong with Hebrew NLP? And How to Make it Right
| Title | What’s Wrong with Hebrew NLP? And How to Make it Right |
| Authors | Reut Tsarfaty, Amit Seker, Shoval Sadde, Stav Klein |
| Abstract | For languages with simple morphology, such as English, automatic annotation pipelines such as spaCy or Stanford’s CoreNLP successfully serve projects in academia and the industry. For many morphologically-rich languages (MRLs), similar pipelines show sub-optimal performance that limits their applicability for text analysis in research and the industry.The sub-optimal performance is mainly due to errors in early morphological disambiguation decisions, which cannot be recovered later in the pipeline, yielding incoherent annotations on the whole. In this paper we describe the design and use of the Onlp suite, a joint morpho-syntactic parsing framework for processing Modern Hebrew texts. The joint inference over morphology and syntax substantially limits error propagation, and leads to high accuracy. Onlp provides rich and expressive output which already serves diverse academic and commercial needs. Its accompanying online demo further serves educational activities, introducing Hebrew NLP intricacies to researchers and non-researchers alike. |
| Tasks | |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05453v1 |
| https://arxiv.org/pdf/1908.05453v1.pdf | |
| PWC | https://paperswithcode.com/paper/whats-wrong-with-hebrew-nlp-and-how-to-make |
| Repo | |
| Framework | |
Model Function Based Conditional Gradient Method with Armijo-like Line Search
| Title | Model Function Based Conditional Gradient Method with Armijo-like Line Search |
| Authors | Yura Malitsky, Peter Ochs |
| Abstract | The Conditional Gradient Method is generalized to a class of non-smooth non-convex optimization problems with many applications in machine learning. The proposed algorithm iterates by minimizing so-called model functions over the constraint set. Complemented with an Amijo line search procedure, we prove that subsequences converge to a stationary point. The abstract framework of model functions provides great flexibility for the design of concrete algorithms. As special cases, for example, we develop an algorithm for additive composite problems and an algorithm for non-linear composite problems which leads to a Gauss–Newton-type algorithm. Both instances are novel in non-smooth non-convex optimization and come with numerous applications in machine learning. Moreover, we obtain a hybrid version of Conditional Gradient and Proximal Minimization schemes for free, which combines advantages of both. Our algorithm is shown to perform favorably on a sparse non-linear robust regression problem and we discuss the flexibility of the proposed framework in several matrix factorization formulations. |
| Tasks | |
| Published | 2019-01-23 |
| URL | http://arxiv.org/abs/1901.08087v1 |
| http://arxiv.org/pdf/1901.08087v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-function-based-conditional-gradient |
| Repo | |
| Framework | |
Deep Reinforcement Learning for Task-driven Discovery of Incomplete Networks
| Title | Deep Reinforcement Learning for Task-driven Discovery of Incomplete Networks |
| Authors | Peter Morales, Rajmonda Sulo Caceres, Tina Eliassi-Rad |
| Abstract | Complex networks are often either too large for full exploration, partially accessible or partially observed. Downstream learning tasks on incomplete networks can produce low quality results. In addition, reducing the incompleteness of the network can be costly and nontrivial. As a result, network discovery algorithms optimized for specific downstream learning tasks and given resource collection constraints are of great interest. In this paper we formulate the task-specific network discovery problem in an incomplete network setting as a sequential decision making problem. Our downstream task is vertex classification.We propose a framework, called Network Actor Critic (NAC), which learns concepts of policy and reward in an offline setting via a deep reinforcement learning algorithm. A quantitative study is presented on several synthetic and real benchmarks. We show that offline models of reward and network discovery policies lead to significantly improved performance when compared to competitive online discovery algorithms. |
| Tasks | Decision Making |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07294v1 |
| https://arxiv.org/pdf/1909.07294v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-task-driven |
| Repo | |
| Framework | |
Learning Deep Bayesian Latent Variable Regression Models that Generalize: When Non-identifiability is a Problem
| Title | Learning Deep Bayesian Latent Variable Regression Models that Generalize: When Non-identifiability is a Problem |
| Authors | Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez |
| Abstract | Bayesian Neural Networks with Latent Variables (BNN+LV’s) provide uncertainties in prediction estimates by explicitly modeling model uncertainty (via priors on network weights) and environmental stochasticity (via a latent input noise variable). In this work, we first show that BNN+LV suffers from a serious form of non-identifiability: explanatory power can be transferred between model parameters and input noise while fitting the data equally well. We demonstrate that, as a result, traditional inference methods may yield parameters that reconstruct observed data well but generalize poorly. Next, we develop a novel inference procedure that explicitly mitigates the effects of likelihood non-identifiability during training and yields high quality predictions as well as uncertainty estimates. We demonstrate that our inference method improves upon benchmark methods across a range of synthetic and real datasets. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00569v1 |
| https://arxiv.org/pdf/1911.00569v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-deep-bayesian-latent-variable |
| Repo | |
| Framework | |
Latent Function Decomposition for Forecasting Li-ion Battery Cells Capacity: A Multi-Output Convolved Gaussian Process Approach
| Title | Latent Function Decomposition for Forecasting Li-ion Battery Cells Capacity: A Multi-Output Convolved Gaussian Process Approach |
| Authors | Abdallah A. Chehade, Ala A. Hussein |
| Abstract | A latent function decomposition method is proposed for forecasting the capacity of lithium-ion battery cells. The method uses the Multi-Output Gaussian Process, a generative machine learning framework for multi-task and transfer learning. The MCGP decomposes the available capacity trends from multiple battery cells into latent functions. The latent functions are then convolved over kernel smoothers to reconstruct and/or forecast capacity trends of the battery cells. Besides the high prediction accuracy the proposed method possesses, it provides uncertainty information for the predictions and captures nontrivial cross-correlations between capacity trends of different battery cells. These two merits make the proposed MCGP a very reliable and practical solution for applications that use battery cell packs. The MCGP is derived and compared to benchmark methods on an experimental lithium-ion battery cells data. The results show the effectiveness of the proposed method. |
| Tasks | Transfer Learning |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.09455v1 |
| https://arxiv.org/pdf/1907.09455v1.pdf | |
| PWC | https://paperswithcode.com/paper/latent-function-decomposition-for-forecasting |
| Repo | |
| Framework | |
Exposing Fake Images with Forensic Similarity Graphs
| Title | Exposing Fake Images with Forensic Similarity Graphs |
| Authors | Owen Mayer, Matthew C. Stamm |
| Abstract | In this paper, we propose new image forgery detection and localization algorithms by recasting these problems as graph-based community detection problems. We define localized image tampering as any locally applied manipulation, including splicing and airbrushing, but not globally applied processes such as compression, whole-image resizing or contrast enhancement, etc. To show this, we propose an abstract, graph-based representation of an image, which we call the Forensic Similarity Graph. In this representation, small image patches are represented by graph vertices, and edges that connect pairs of vertices are assigned according to the forensic similarity between patches. Localized tampering introduces unique structure into this graph, which align with a concept called “communities” in graph-theory literature. A community is a subset of vertices that contain densely connected edges within the community, and relatively sparse edges to other communities. In the Forensic Similarity Graph, communities correspond to the tampered and unaltered regions in the image. As a result, forgery detection is performed by identifying whether multiple communities exist, and forgery localization is performed by partitioning these communities. In this paper, we additionally propose two community detection techniques, adapted from literature, to detect and localize image forgeries. We experimentally show that our proposed community detection methods outperform existing state-of-the-art forgery detection and localization methods. |
| Tasks | Community Detection |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02861v1 |
| https://arxiv.org/pdf/1912.02861v1.pdf | |
| PWC | https://paperswithcode.com/paper/exposing-fake-images-with-forensic-similarity |
| Repo | |
| Framework | |
Underwater Color Restoration Using U-Net Denoising Autoencoder
| Title | Underwater Color Restoration Using U-Net Denoising Autoencoder |
| Authors | Yousif Hashisho, Mohamad Albadawi, Tom Krause, Uwe Freiherr von Lukas |
| Abstract | Visual inspection of underwater structures by vehicles, e.g. remotely operated vehicles (ROVs), plays an important role in scientific, military, and commercial sectors. However, the automatic extraction of information using software tools is hindered by the characteristics of water which degrade the quality of captured videos. As a contribution for restoring the color of underwater images, Underwater Denoising Autoencoder (UDAE) model is developed using a denoising autoencoder with U-Net architecture. The proposed network takes into consideration the accuracy and the computation cost to enable real-time implementation on underwater visual tasks using end-to-end autoencoder network. Underwater vehicles perception is improved by reconstructing captured frames; hence obtaining better performance in underwater tasks. Related learning methods use generative adversarial networks (GANs) to generate color corrected underwater images, and to our knowledge this paper is the first to deal with a single autoencoder capable of producing same or better results. Moreover, image pairs are constructed for training the proposed network, where it is hard to obtain such dataset from underwater scenery. At the end, the proposed model is compared to a state-of-the-art method. |
| Tasks | Denoising |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.09000v1 |
| https://arxiv.org/pdf/1905.09000v1.pdf | |
| PWC | https://paperswithcode.com/paper/underwater-color-restoration-using-u-net |
| Repo | |
| Framework | |
Efficient Policy Learning for Non-Stationary MDPs under Adversarial Manipulation
| Title | Efficient Policy Learning for Non-Stationary MDPs under Adversarial Manipulation |
| Authors | Tiancheng Yu, Suvrit Sra |
| Abstract | A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent problems. We study an episodic setting where the parameters of an MDP can differ across episodes. We learn a reliable policy of this potentially adversarial MDP by developing an Adversarial Reinforcement Learning (ARL) algorithm that reduces our MDP to a sequence of \emph{adversarial} bandit problems. ARL achieves $O(\sqrt{SATH^3})$ regret, which is optimal with respect to $S$, $A$, and $T$, and its dependence on $H$ is the best (even for the usual stationary MDP) among existing model-free methods. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09350v2 |
| https://arxiv.org/pdf/1907.09350v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-policy-learning-for-non-stationary |
| Repo | |
| Framework | |
