Paper Group ANR 1319
Interactive Image Segmentation using Label Propagation through Complex Networks. A General Decoupled Learning Framework for Parameterized Image Operators. Improving performance and inference on audio classification tasks using capsule networks. Transductive Parsing for Universal Decompositional Semantics. Referring to Objects in Videos using Spatio …
Interactive Image Segmentation using Label Propagation through Complex Networks
| Title | Interactive Image Segmentation using Label Propagation through Complex Networks |
| Authors | Fabricio Aparecido Breve |
| Abstract | Interactive image segmentation is a topic of many studies in image processing. In a conventional approach, a user marks some pixels of the object(s) of interest and background, and an algorithm propagates these labels to the rest of the image. This paper presents a new graph-based method for interactive segmentation with two stages. In the first stage, nodes representing pixels are connected to their $k$-nearest neighbors to build a complex network with the small-world property to propagate the labels quickly. In the second stage, a regular network in a grid format is used to refine the segmentation on the object borders. Despite its simplicity, the proposed method can perform the task with high accuracy. Computer simulations are performed using some real-world images to show its effectiveness in both two-classes and multi-classes problems. It is also applied to all the images from the Microsoft GrabCut dataset for comparison, and the segmentation accuracy is comparable to those achieved by some state-of-the-art methods, while it is faster than them. In particular, it outperforms some recent approaches when the user input is composed only by a few “scribbles” draw over the objects. Its computational complexity is only linear on the image size at the best-case scenario and linearithmic in the worst case. |
| Tasks | Interactive Segmentation, Semantic Segmentation |
| Published | 2019-01-09 |
| URL | http://arxiv.org/abs/1901.02573v1 |
| http://arxiv.org/pdf/1901.02573v1.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-image-segmentation-using-label |
| Repo | |
| Framework | |
A General Decoupled Learning Framework for Parameterized Image Operators
| Title | A General Decoupled Learning Framework for Parameterized Image Operators |
| Authors | Qingnan Fan, Dongdong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen |
| Abstract | Many different deep networks have been used to approximate, accelerate or improve traditional image operators. Among these traditional operators, many contain parameters which need to be tweaked to obtain the satisfactory results, which we refer to as parameterized image operators. However, most existing deep networks trained for these operators are only designed for one specific parameter configuration, which does not meet the needs of real scenarios that usually require flexible parameters settings. To overcome this limitation, we propose a new decoupled learning algorithm to learn from the operator parameters to dynamically adjust the weights of a deep network for image operators, denoted as the base network. The learned algorithm is formed as another network, namely the weight learning network, which can be end-to-end jointly trained with the base network. Experiments demonstrate that the proposed framework can be successfully applied to many traditional parameterized image operators. To accelerate the parameter tuning for practical scenarios, the proposed framework can be further extended to dynamically change the weights of only one single layer of the base network while sharing most computation cost. We demonstrate that this cheap parameter-tuning extension of the proposed decoupled learning framework even outperforms the state-of-the-art alternative approaches. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05852v1 |
| https://arxiv.org/pdf/1907.05852v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-decoupled-learning-framework-for |
| Repo | |
| Framework | |
Improving performance and inference on audio classification tasks using capsule networks
| Title | Improving performance and inference on audio classification tasks using capsule networks |
| Authors | Royal Jain |
| Abstract | Classification of audio samples is an important part of many auditory systems. Deep learning models based on the Convolutional and the Recurrent layers are state-of-the-art in many such tasks. In this paper, we approach audio classification tasks using capsule networks trained by recently proposed dynamic routing-by-agreement mechanism. We propose an architecture for capsule networks fit for audio classification tasks and study the impact of various parameters on classification accuracy. Further, we suggest modifications for regularization and multi-label classification. We also develop insights into the data using capsule outputs and show the utility of the learned network for transfer learning. We perform experiments on 7 datasets of different domains and sizes and show significant improvements in performance compared to strong baseline models. To the best of our knowledge, this is the first detailed study about the application of capsule networks in the audio domain. |
| Tasks | Audio Classification, Multi-Label Classification, Transfer Learning |
| Published | 2019-02-13 |
| URL | http://arxiv.org/abs/1902.05069v1 |
| http://arxiv.org/pdf/1902.05069v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-performance-and-inference-on-audio |
| Repo | |
| Framework | |
Transductive Parsing for Universal Decompositional Semantics
| Title | Transductive Parsing for Universal Decompositional Semantics |
| Authors | Elias Stengel-Eskin, Aaron Steven White, Sheng Zhang, Benjamin Van Durme |
| Abstract | We introduce a transductive model for parsing into Universal Decompositional Semantics (UDS) representations, which jointly learns to map natural language utterances into UDS graph structures and annotate the graph with decompositional semantic attribute scores. We also introduce a strong pipeline model for parsing UDS graph structure, and show that our parser can perform comparably while additionally performing attribute prediction. |
| Tasks | |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.10138v2 |
| https://arxiv.org/pdf/1910.10138v2.pdf | |
| PWC | https://paperswithcode.com/paper/transductive-parsing-for-universal |
| Repo | |
| Framework | |
Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions
| Title | Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions |
| Authors | Peratham Wiriyathammabhum, Abhinav Shrivastava, Vlad I. Morariu, Larry S. Davis |
| Abstract | This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos. Previous work suggests potential bias in existing datasets and emphasizes the need for a new data creation schema to better model linguistic structure. We introduce a new data collection scheme based on grammatical constraints for surface realization to enable us to investigate the problem of grounding spatio-temporal identifying descriptions in videos. We then propose a two-stream modular attention network that learns and grounds spatio-temporal identifying descriptions based on appearance and motion. We show that motion modules help to ground motion-related words and also help to learn in appearance modules because modular neural networks resolve task interference between modules. Finally, we propose a future challenge and a need for a robust system arising from replacing ground truth visual annotations with automatic video object detector and temporal event localization. |
| Tasks | |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.03885v1 |
| http://arxiv.org/pdf/1904.03885v1.pdf | |
| PWC | https://paperswithcode.com/paper/referring-to-objects-in-videos-using-spatio |
| Repo | |
| Framework | |
Language comparison via network topology
| Title | Language comparison via network topology |
| Authors | Blaž Škrlj, Senja Pollak |
| Abstract | Modeling relations between languages can offer understanding of language characteristics and uncover similarities and differences between languages. Automated methods applied to large textual corpora can be seen as opportunities for novel statistical studies of language development over time, as well as for improving cross-lingual natural language processing techniques. In this work, we first propose how to represent textual data as a directed, weighted network by the text2net algorithm. We next explore how various fast, network-topological metrics, such as network community structure, can be used for cross-lingual comparisons. In our experiments, we employ eight different network topology metrics, and empirically showcase on a parallel corpus, how the methods can be used for modeling the relations between nine selected languages. We demonstrate that the proposed method scales to large corpora consisting of hundreds of thousands of aligned sentences on an of-the-shelf laptop. We observe that on the one hand properties such as communities, capture some of the known differences between the languages, while others can be seen as novel opportunities for linguistic studies. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.06944v2 |
| https://arxiv.org/pdf/1907.06944v2.pdf | |
| PWC | https://paperswithcode.com/paper/language-comparison-via-network-topology |
| Repo | |
| Framework | |
Matrix Lie Maps and Neural Networks for Solving Differential Equations
| Title | Matrix Lie Maps and Neural Networks for Solving Differential Equations |
| Authors | Andrei Ivanov, Sergei Andrianov |
| Abstract | The coincidence between polynomial neural networks and matrix Lie maps is discussed in the article. The matrix form of Lie transform is an approximation of the general solution of the nonlinear system of ordinary differential equations. It can be used for solving systems of differential equations more efficiently than traditional step-by-step numerical methods. Implementation of the Lie map as a polynomial neural network provides a tool for both simulation and data-driven identification of dynamical systems. If the differential equation is provided, training a neural network is unnecessary. The weights of the network can be directly calculated from the equation. On the other hand, for data-driven system learning, the weights can be fitted without any assumptions in view of differential equations. The proposed technique is discussed in the examples of both ordinary and partial differential equations. The building of a polynomial neural network that simulates the Van der Pol oscillator is discussed. For this example, we consider learning the dynamics from a single solution of the system. We also demonstrate the building of the neural network that describes the solution of Burgers’ equation that is a fundamental partial differential equation. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06088v1 |
| https://arxiv.org/pdf/1908.06088v1.pdf | |
| PWC | https://paperswithcode.com/paper/matrix-lie-maps-and-neural-networks-for |
| Repo | |
| Framework | |
Inference in High-Dimensional Linear Regression via Lattice Basis Reduction and Integer Relation Detection
| Title | Inference in High-Dimensional Linear Regression via Lattice Basis Reduction and Integer Relation Detection |
| Authors | David Gamarnik, Eren C. Kızıldağ, Ilias Zadik |
| Abstract | We focus on the high-dimensional linear regression problem, where the algorithmic goal is to efficiently infer an unknown feature vector $\beta^*\in\mathbb{R}^p$ from its linear measurements, using a small number $n$ of samples. Unlike most of the literature, we make no sparsity assumption on $\beta^*$, but instead adopt a different regularization: In the noiseless setting, we assume $\beta^*$ consists of entries, which are either rational numbers with a common denominator $Q\in\mathbb{Z}^+$ (referred to as $Q$-rationality); or irrational numbers supported on a rationally independent set of bounded cardinality, known to learner; collectively called as the mixed-support assumption. Using a novel combination of the PSLQ integer relation detection, and LLL lattice basis reduction algorithms, we propose a polynomial-time algorithm which provably recovers a $\beta^*\in\mathbb{R}^p$ enjoying the mixed-support assumption, from its linear measurements $Y=X\beta^*\in\mathbb{R}^n$ for a large class of distributions for the random entries of $X$, even with one measurement $(n=1)$. In the noisy setting, we propose a polynomial-time, lattice-based algorithm, which recovers a $\beta^*\in\mathbb{R}^p$ enjoying $Q$-rationality, from its noisy measurements $Y=X\beta^*+W\in\mathbb{R}^n$, even with a single sample $(n=1)$. We further establish for large $Q$, and normal noise, this algorithm tolerates information-theoretically optimal level of noise. We then apply these ideas to develop a polynomial-time, single-sample algorithm for the phase retrieval problem. Our methods address the single-sample $(n=1)$ regime, where the sparsity-based methods such as LASSO and Basis Pursuit are known to fail. Furthermore, our results also reveal an algorithmic connection between the high-dimensional linear regression problem, and the integer relation detection, randomized subset-sum, and shortest vector problems. |
| Tasks | |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.10890v1 |
| https://arxiv.org/pdf/1910.10890v1.pdf | |
| PWC | https://paperswithcode.com/paper/inference-in-high-dimensional-linear |
| Repo | |
| Framework | |
Deep Attentive Ranking Networks for Learning to Order Sentences
| Title | Deep Attentive Ranking Networks for Learning to Order Sentences |
| Authors | Pawan Kumar, Dhanajit Brahma, Harish Karnick, Piyush Rai |
| Abstract | We present an attention-based ranking framework for learning to order sentences given a paragraph. Our framework is built on a bidirectional sentence encoder and a self-attention based transformer network to obtain an input order invariant representation of paragraphs. Moreover, it allows seamless training using a variety of ranking based loss functions, such as pointwise, pairwise, and listwise ranking. We apply our framework on two tasks: Sentence Ordering and Order Discrimination. Our framework outperforms various state-of-the-art methods on these tasks on a variety of evaluation metrics. We also show that it achieves better results when using pairwise and listwise ranking losses, rather than the pointwise ranking loss, which suggests that incorporating relative positions of two or more sentences in the loss function contributes to better learning. |
| Tasks | Sentence Ordering |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/2001.00056v1 |
| https://arxiv.org/pdf/2001.00056v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-attentive-ranking-networks-for-learning |
| Repo | |
| Framework | |
An aggregate learning approach for interpretable semi-supervised population prediction and disaggregation using ancillary data
| Title | An aggregate learning approach for interpretable semi-supervised population prediction and disaggregation using ancillary data |
| Authors | Guillaume Derval, Frédéric Docquier, Pierre Schaus |
| Abstract | Census data provide detailed information about population characteristics at a coarse resolution. Nevertheless, fine-grained, high-resolution mappings of population counts are increasingly needed to characterize population dynamics and to assess the consequences of climate shocks, natural disasters, investments in infrastructure, development policies, etc. Dissagregating these census is a complex machine learning, and multiple solutions have been proposed in past research. We propose in this paper to view the problem in the context of the aggregate learning paradigm, where the output value for all training points is not known, but where it is only known for aggregates of the points (i.e. in this context, for regions of pixels where a census is available). We demonstrate with a very simple and interpretable model that this method is on par, and even outperforms on some metrics, the state-of-the-art, despite its simplicity. |
| Tasks | |
| Published | 2019-06-29 |
| URL | https://arxiv.org/abs/1907.00270v1 |
| https://arxiv.org/pdf/1907.00270v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-aggregate-learning-approach-for |
| Repo | |
| Framework | |
Fairness Assessment for Artificial Intelligence in Financial Industry
| Title | Fairness Assessment for Artificial Intelligence in Financial Industry |
| Authors | Yukun Zhang, Longsheng Zhou |
| Abstract | Artificial Intelligence (AI) is an important driving force for the development and transformation of the financial industry. However, with the fast-evolving AI technology and application, unintentional bias, insufficient model validation, immature contingency plan and other underestimated threats may expose the company to operational and reputational risks. In this paper, we focus on fairness evaluation, one of the key components of AI Governance, through a quantitative lens. Statistical methods are reviewed for imbalanced data treatment and bias mitigation. These methods and fairness evaluation metrics are then applied to a credit card default payment example. |
| Tasks | |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07211v1 |
| https://arxiv.org/pdf/1912.07211v1.pdf | |
| PWC | https://paperswithcode.com/paper/fairness-assessment-for-artificial |
| Repo | |
| Framework | |
Genetic Algorithms for the Optimization of Diffusion Parameters in Content-Based Image Retrieval
| Title | Genetic Algorithms for the Optimization of Diffusion Parameters in Content-Based Image Retrieval |
| Authors | Federico Magliani, Laura Sani, Stefano Cagnoni, Andrea Prati |
| Abstract | Several computer vision and artificial intelligence projects are nowadays exploiting the manifold data distribution using, e.g., the diffusion process. This approach has produced dramatic improvements on the final performance thanks to the application of such algorithms to the kNN graph. Unfortunately, this recent technique needs a manual configuration of several parameters, thus it is not straightforward to find the best configuration for each dataset. Moreover, the brute-force approach is computationally very demanding when used to optimally set the parameters of the diffusion approach. We propose to use genetic algorithms to find the optimal setting of all the diffusion parameters with respect to retrieval performance for each different dataset. Our approach is faster than others used as references (brute-force, random-search and PSO). A comparison with these methods has been made on three public image datasets: Oxford5k, Paris6k and Oxford105k. |
| Tasks | Content-Based Image Retrieval, Image Retrieval |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06896v1 |
| https://arxiv.org/pdf/1908.06896v1.pdf | |
| PWC | https://paperswithcode.com/paper/genetic-algorithms-for-the-optimization-of |
| Repo | |
| Framework | |
A new insight into the Position Optimization of Wave Energy Converters by a Hybrid Local Search
| Title | A new insight into the Position Optimization of Wave Energy Converters by a Hybrid Local Search |
| Authors | Mehdi Neshat, Bradley Alexander, Nataliia Sergiienko, Markus Wagner |
| Abstract | Renewable energy, such as ocean wave energy, plays a pivotal role in addressing the tremendous growth of global energy demand. It is expected that wave energy will be one of the fastest-growing energy resources in the next decade, offering an enormous potential source of sustainable energy. This research investigates the placement optimization of oscillating buoy-type wave energy converters (WEC). The design of a wave farm consisting of an array of fully submerged three-tether buoys is evaluated. In a wave farm, buoy positions have a notable impact on the farm’s output. Optimizing the buoy positions is a challenging research problem because of very complex interactions (constructive and destructive) between buoys. The main purpose of this research is maximizing the power output of the farm through the placement of buoys in a size-constrained environment. This paper proposes a new hybrid approach of the heuristic local search combined with a numerical optimization method that utilizes a knowledge-based surrogate power model. We compare the proposed hybrid method with other state-of-the-art search methods in five different wave scenarios – one simplified irregular wave model and four real wave climates. Our method considerably outperforms all previous heuristic methods in terms of both quality of achieved solutions and the convergence-rate of search in all tested wave regimes. |
| Tasks | |
| Published | 2019-04-21 |
| URL | https://arxiv.org/abs/1904.09599v2 |
| https://arxiv.org/pdf/1904.09599v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-insight-into-the-position-optimization |
| Repo | |
| Framework | |
Nyström landmark sampling and regularized Christoffel functions
| Title | Nyström landmark sampling and regularized Christoffel functions |
| Authors | Michaël Fanuel, Joachim Schreurs, Johan A. K. Suykens |
| Abstract | Selecting diverse and important items from a large set is a problem of interest in machine learning. As a specific example, in order to deal with large training sets, kernel methods often rely on low rank matrix approximations based on the selection or sampling of Nystr"om centers. In this context, we propose a deterministic and a randomized adaptive algorithm for selecting landmark points within a training dataset, which are related to the minima of a sequence of Christoffel functions in Reproducing Kernel Hilbert Spaces. Beyond the known connection between Christoffel functions and leverage scores, a connection of our method with determinantal point processes (DPP) is also explained. Namely, our construction promotes diversity among important landmark points in a way similar to DPPs. |
| Tasks | Point Processes |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12346v2 |
| https://arxiv.org/pdf/1905.12346v2.pdf | |
| PWC | https://paperswithcode.com/paper/nystrom-landmark-sampling-and-regularized |
| Repo | |
| Framework | |
Transfer Learning for Algorithm Recommendation
| Title | Transfer Learning for Algorithm Recommendation |
| Authors | Gean Trindade Pereira, Moisés dos Santos, Edesio Alcobaça, Rafael Mantovani, André Carvalho |
| Abstract | Meta-Learning is a subarea of Machine Learning that aims to take advantage of prior knowledge to learn faster and with fewer data [1]. There are different scenarios where meta-learning can be applied, and one of the most common is algorithm recommendation, where previous experience on applying machine learning algorithms for several datasets can be used to learn which algorithm, from a set of options, would be more suitable for a new dataset [2]. Perhaps the most popular form of meta-learning is transfer learning, which consists of transferring knowledge acquired by a machine learning algorithm in a previous learning task to increase its performance faster in another and similar task [3]. Transfer Learning has been widely applied in a variety of complex tasks such as image classification, machine translation and, speech recognition, achieving remarkable results [4,5,6,7,8]. Although transfer learning is very used in traditional or base-learning, it is still unknown if it is useful in a meta-learning setup. For that purpose, in this paper, we investigate the effects of transferring knowledge in the meta-level instead of base-level. Thus, we train a neural network on meta-datasets related to algorithm recommendation, and then using transfer learning, we reuse the knowledge learned by the neural network in other similar datasets from the same domain, to verify how transferable is the acquired meta-knowledge. |
| Tasks | Image Classification, Machine Translation, Meta-Learning, Speech Recognition, Transfer Learning |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.07012v1 |
| https://arxiv.org/pdf/1910.07012v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-for-algorithm |
| Repo | |
| Framework | |
