Paper Group ANR 17
Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features. Autonomous Removal of Perspective Distortion for Robotic Elevator Button Recognition. Decoding Cosmological Information in Weak-Lensing Mass Maps with Generative Adversarial Networks. Breaking the cycle – Colleagues are all you need. C …
Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features
| Title | Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features |
| Authors | Alex Yang, Charlie T. Veal, Derek T. Anderson, Grant J. Scott |
| Abstract | Superpixel-based methodologies have become increasingly popular in computer vision, especially when the computation is too expensive in time or memory to perform with a large number of pixels or features. However, rarely is superpixel segmentation examined within the context of deep convolutional neural network architectures. This paper presents a novel neural architecture that exploits the superpixel feature space. The visual feature space is organized using superpixels to provide the neural network with a substructure of the images. As the superpixels associate the visual feature space with parts of the objects in an image, the visual feature space is transformed into a structured vector representation per superpixel. It is shown that it is feasible to learn superpixel features using capsules and it is potentially beneficial to perform image analysis in such a structured manner. This novel deep learning architecture is examined in the context of an image classification task, highlighting explicit interpretability (explainability) of the network’s decision making. The results are compared against a baseline deep neural model, as well as among superpixel capsule networks with a variety of hyperparameter settings. |
| Tasks | Decision Making, Image Classification |
| Published | 2019-08-02 |
| URL | https://arxiv.org/abs/1908.00669v1 |
| https://arxiv.org/pdf/1908.00669v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognizing-image-objects-by-relational |
| Repo | |
| Framework | |
Autonomous Removal of Perspective Distortion for Robotic Elevator Button Recognition
| Title | Autonomous Removal of Perspective Distortion for Robotic Elevator Button Recognition |
| Authors | Delong Zhu, Jianbang Liu, Nachuan Ma, Zhe Min, Max Q. -H. Meng |
| Abstract | Elevator button recognition is considered an indispensable function for enabling the autonomous elevator operation of mobile robots. However, due to unfavorable image conditions and various image distortions, the recognition accuracy remains to be improved. In this paper, we present a novel algorithm that can autonomously correct perspective distortions of elevator panel images. The algorithm first leverages the Gaussian Mixture Model (GMM) to conduct a grid fitting process based on button recognition results, then utilizes the estimated grid centers as reference features to estimate camera motions for correcting perspective distortions. The algorithm performs on a single image autonomously and does not need explicit feature detection or feature matching procedure, which is much more robust to noises and outliers than traditional feature-based geometric approaches. To verify the effectiveness of the algorithm, we collect an elevator panel dataset of 50 images captured from different angles of view. Experimental results show that the proposed algorithm can accurately estimate camera motions and effectively remove perspective distortions. |
| Tasks | |
| Published | 2019-12-26 |
| URL | https://arxiv.org/abs/1912.11774v1 |
| https://arxiv.org/pdf/1912.11774v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-removal-of-perspective-distortion |
| Repo | |
| Framework | |
Decoding Cosmological Information in Weak-Lensing Mass Maps with Generative Adversarial Networks
| Title | Decoding Cosmological Information in Weak-Lensing Mass Maps with Generative Adversarial Networks |
| Authors | Masato Shirasaki, Naoki Yoshida, Shiro Ikeda, Taira Oogi, Takahiro Nishimichi |
| Abstract | Galaxy imaging surveys enable us to map the cosmic matter density field through weak gravitational lensing analysis. The density reconstruction is compromised by a variety of noise originating from observational conditions, galaxy number density fluctuations, and intrinsic galaxy properties. We propose a deep-learning approach based on generative adversarial networks (GANs) to reduce the noise in the weak lensing map under realistic conditions. We perform image-to-image translation using conditional GANs in order to produce noiseless lensing maps using the first-year data of the Subaru Hyper Suprime-Cam (HSC) survey. We train the conditional GANs by using 30000 sets of mock HSC catalogs that directly incorporate observational effects. We show that an ensemble learning method with GANs can reproduce the one-point probability distribution function (PDF) of the lensing convergence map within a $0.5-1\sigma$ level. We use the reconstructed PDFs to estimate a cosmological parameter $S_{8} = \sigma_{8}\sqrt{\Omega_{\rm m0}/0.3}$, where $\Omega_{\rm m0}$ and $\sigma_{8}$ represent the mean and the scatter in the cosmic matter density. The reconstructed PDFs place tighter constraint, with the statistical uncertainty in $S_8$ reduced by a factor of $2$ compared to the noisy PDF. This is equivalent to increasing the survey area by $4$ without denoising by GANs. Finally, we apply our denoising method to the first-year HSC data, to place $2\sigma$-level cosmological constraints of $S_{8} < 0.777 , ({\rm stat}) + 0.105 , ({\rm sys})$ and $S_{8} < 0.633 , ({\rm stat}) + 0.114 , ({\rm sys})$ for the noisy and denoised data, respectively. |
| Tasks | Denoising, Image-to-Image Translation |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12890v1 |
| https://arxiv.org/pdf/1911.12890v1.pdf | |
| PWC | https://paperswithcode.com/paper/decoding-cosmological-information-in-weak |
| Repo | |
| Framework | |
Breaking the cycle – Colleagues are all you need
| Title | Breaking the cycle – Colleagues are all you need |
| Authors | Ori Nizan, Ayellet Tal |
| Abstract | This paper proposes a novel approach to performing image-to-image translation between unpaired domains. Rather than relying on a cycle constraint, our method takes advantage of collaboration between various GANs. This results in a multi-modal method, in which multiple optional and diverse images are produced for a given image. Our model addresses some of the shortcomings of classical GANs: (1) It is able to remove large objects, such as glasses. (2) Since it does not need to support the cycle constraint, no irrelevant traces of the input are left on the generated image. (3) It manages to translate between domains that require large shape modifications. Our results are shown to outperform those generated by state-of-the-art methods for several challenging applications on commonly-used datasets, both qualitatively and quantitatively. |
| Tasks | Image-to-Image Translation |
| Published | 2019-11-24 |
| URL | https://arxiv.org/abs/1911.10538v1 |
| https://arxiv.org/pdf/1911.10538v1.pdf | |
| PWC | https://paperswithcode.com/paper/breaking-the-cycle-colleagues-are-all-you |
| Repo | |
| Framework | |
Customer churn prediction in telecom using machine learning and social network analysis in big data platform
| Title | Customer churn prediction in telecom using machine learning and social network analysis in big data platform |
| Authors | Abdelrahim Kasem Ahmad, Assef Jafar, Kadan Aljoumaa |
| Abstract | Customer churn is a major problem and one of the most important concerns for large companies. Due to the direct effect on the revenues of the companies, especially in the telecom field, companies are seeking to develop means to predict potential customer to churn. Therefore, finding factors that increase customer churn is important to take necessary actions to reduce this churn. The main contribution of our work is to develop a churn prediction model which assists telecom operators to predict customers who are most likely subject to churn. The model developed in this work uses machine learning techniques on big data platform and builds a new way of features’ engineering and selection. In order to measure the performance of the model, the Area Under Curve (AUC) standard measure is adopted, and the AUC value obtained is 93.3%. Another main contribution is to use customer social network in the prediction model by extracting Social Network Analysis (SNA) features. The use of SNA enhanced the performance of the model from 84 to 93.3% against AUC standard. The model was prepared and tested through Spark environment by working on a large dataset created by transforming big raw data provided by SyriaTel telecom company. The dataset contained all customers’ information over 9 months, and was used to train, test, and evaluate the system at SyriaTel. The model experimented four algorithms: Decision Tree, Random Forest, Gradient Boosted Machine Tree “GBM” and Extreme Gradient Boosting “XGBOOST”. However, the best results were obtained by applying XGBOOST algorithm. This algorithm was used for classification in this churn predictive model. |
| Tasks | |
| Published | 2019-04-01 |
| URL | http://arxiv.org/abs/1904.00690v1 |
| http://arxiv.org/pdf/1904.00690v1.pdf | |
| PWC | https://paperswithcode.com/paper/customer-churn-prediction-in-telecom-using |
| Repo | |
| Framework | |
Audio-attention discriminative language model for ASR rescoring
| Title | Audio-attention discriminative language model for ASR rescoring |
| Authors | Ankur Gandhe, Ariya Rastrow |
| Abstract | End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these models typically require more data to achieve comparable results. Well-known model adaptation techniques, to account for domain and style adaptation, are not easily applicable to end-to-end systems. Conventional HMM-based systems, on the other hand, have been optimized for various production environments and use cases. In this work, we propose to combine the benefits of end-to-end approaches with a conventional system using an attention-based discriminative language model that learns to rescore the output of a first-pass ASR system. We show that learning to rescore a list of potential ASR outputs is much simpler than learning to generate the hypothesis. The proposed model results in 8% improvement in word error rate even when the amount of training data is a fraction of data used for training the first-pass system. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03363v2 |
| https://arxiv.org/pdf/1912.03363v2.pdf | |
| PWC | https://paperswithcode.com/paper/audio-attention-discriminative-language-model |
| Repo | |
| Framework | |
A Simple Proof of the Universality of Invariant/Equivariant Graph Neural Networks
| Title | A Simple Proof of the Universality of Invariant/Equivariant Graph Neural Networks |
| Authors | Takanori Maehara, Hoang NT |
| Abstract | We present a simple proof for the universality of invariant and equivariant tensorized graph neural networks. Our approach considers a restricted intermediate hypothetical model named Graph Homomorphism Model to reach the universality conclusions including an open case for higher-order output. We find that our proposed technique not only leads to simple proofs of the universality properties but also gives a natural explanation for the tensorization of the previously studied models. Finally, we give some remarks on the connection between our model and the continuous representation of graphs. |
| Tasks | |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.03802v1 |
| https://arxiv.org/pdf/1910.03802v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-proof-of-the-universality-of |
| Repo | |
| Framework | |
Quaternion Collaborative Filtering for Recommendation
| Title | Quaternion Collaborative Filtering for Recommendation |
| Authors | Shuai Zhang, Lina Yao, Lucas Vinh Tran, Aston Zhang, Yi Tay |
| Abstract | This paper proposes Quaternion Collaborative Filtering (QCF), a novel representation learning method for recommendation. Our proposed QCF relies on and exploits computation with Quaternion algebra, benefiting from the expressiveness and rich representation learning capability of Hamilton products. Quaternion representations, based on hypercomplex numbers, enable rich inter-latent dependencies between imaginary components. This encourages intricate relations to be captured when learning user-item interactions, serving as a strong inductive bias as compared with the real-space inner product. All in all, we conduct extensive experiments on six real-world datasets, demonstrating the effectiveness of Quaternion algebra in recommender systems. The results exhibit that QCF outperforms a wide spectrum of strong neural baselines on all datasets. Ablative experiments confirm the effectiveness of Hamilton-based composition over multi-embedding composition in real space. |
| Tasks | Recommendation Systems, Representation Learning |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02594v1 |
| https://arxiv.org/pdf/1906.02594v1.pdf | |
| PWC | https://paperswithcode.com/paper/quaternion-collaborative-filtering-for |
| Repo | |
| Framework | |
Latent Adversarial Defence with Boundary-guided Generation
| Title | Latent Adversarial Defence with Boundary-guided Generation |
| Authors | Xiaowei Zhou, Ivor W. Tsang, Jie Yin |
| Abstract | Deep Neural Networks (DNNs) have recently achieved great success in many tasks, which encourages DNNs to be widely used as a machine learning service in model sharing scenarios. However, attackers can easily generate adversarial examples with a small perturbation to fool the DNN models to predict wrong labels. To improve the robustness of shared DNN models against adversarial attacks, we propose a novel method called Latent Adversarial Defence (LAD). The proposed LAD method improves the robustness of a DNN model through adversarial training on generated adversarial examples. Different from popular attack methods which are carried in the input space and only generate adversarial examples of repeating patterns, LAD generates myriad of adversarial examples through adding perturbations to latent features along the normal of the decision boundary which is constructed by an SVM with an attention mechanism. Once adversarial examples are generated, we adversarially train the model through augmenting the training data with generated adversarial examples. Extensive experiments on the MNIST, SVHN, and CelebA dataset demonstrate the effectiveness of our model in defending against different types of adversarial attacks. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07001v1 |
| https://arxiv.org/pdf/1907.07001v1.pdf | |
| PWC | https://paperswithcode.com/paper/latent-adversarial-defence-with-boundary |
| Repo | |
| Framework | |
Detecting Local Community Structures in Social Networks Using Concept Interestingness
| Title | Detecting Local Community Structures in Social Networks Using Concept Interestingness |
| Authors | Mohamed-Hamza Ibrahim, Rokia Missaoui, Abir Messaoudi |
| Abstract | One key challenge in Social Network Analysis is to design an efficient and accurate community detection procedure as a means to discover intrinsic structures and extract relevant information. In this paper, we introduce a novel strategy called (COIN), which exploits COncept INterestingness measures to detect communities based on the concept lattice construction of the network. Thus, unlike off-the-shelf community detection algorithms, COIN leverages relevant conceptual characteristics inherited from Formal Concept Analysis to discover substantial local structures. On the first stage of COIN, we extract the formal concepts that capture all the cliques and bridges in the social network. On the second stage, we use the stability index to remove noisy bridges between communities and then percolate relevant adjacent cliques. Our experiments on several real-world social networks show that COIN can quickly detect communities more accurately than existing prominent algorithms such as Edge betweenness, Fast greedy modularity, and Infomap. |
| Tasks | Community Detection |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.03109v1 |
| http://arxiv.org/pdf/1902.03109v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-local-community-structures-in |
| Repo | |
| Framework | |
An Improving Framework of regularization for Network Compression
| Title | An Improving Framework of regularization for Network Compression |
| Authors | E Zhenqian, Gao Weiguo |
| Abstract | Deep Neural Networks have achieved remarkable success relying on the developing high computation capability of GPUs and large-scale datasets with increasing network depth and width in image recognition, object detection and many other applications. However, due to the expensive computation and intensive memory, researchers have concentrated on designing compression methods in recent years. In this paper, we briefly summarize the existing advanced techniques that are useful in model compression at first. After that, we give a detailed description on group lasso regularization and its variants. More importantly, we propose an improving framework of partial regularization based on the relationship between neurons and connections of adjacent layers. It is reasonable and feasible with the help of permutation property of neural network . Experiment results show that partial regularization methods brings improvements such as higher classification accuracy in both training and testing stages on multiple datasets. Since our regularizers contain the computation of less parameters, it shows competitive performances in terms of the total running time of experiments. Finally, we analysed the results and draw a conclusion that the optimal network structure must exist and depend on the input data. |
| Tasks | Model Compression, Object Detection |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05078v2 |
| https://arxiv.org/pdf/1912.05078v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-improving-framework-of-regularization-for |
| Repo | |
| Framework | |
Meta-Graph: Few Shot Link Prediction via Meta Learning
| Title | Meta-Graph: Few Shot Link Prediction via Meta Learning |
| Authors | Avishek Joey Bose, Ankit Jain, Piero Molino, William L. Hamilton |
| Abstract | We consider the task of few shot link prediction on graphs. The goal is to learn from a distribution over graphs so that a model is able to quickly infer missing edges in a new graph after a small amount of training. We show that current link prediction methods are generally ill-equipped to handle this task. They cannot effectively transfer learned knowledge from one graph to another and are unable to effectively learn from sparse samples of edges. To address this challenge, we introduce a new gradient-based meta learning framework, Meta-Graph. Our framework leverages higher-order gradients along with a learned graph signature function that conditionally generates a graph neural network initialization. Using a novel set of few shot link prediction benchmarks, we show that Meta-Graph can learn to quickly adapt to a new graph using only a small sample of true edges, enabling not only fast adaptation but also improved results at convergence. |
| Tasks | Link Prediction, Meta-Learning |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09867v2 |
| https://arxiv.org/pdf/1912.09867v2.pdf | |
| PWC | https://paperswithcode.com/paper/meta-graph-few-shot-link-prediction-via-meta-1 |
| Repo | |
| Framework | |
The Winning Solution to the IEEE CIG 2017 Game Data Mining Competition
| Title | The Winning Solution to the IEEE CIG 2017 Game Data Mining Competition |
| Authors | Anna Guitart, Pei Pei Chen, África Periáñez |
| Abstract | Machine learning competitions such as those organized by Kaggle or KDD represent a useful benchmark for data science research. In this work, we present our winning solution to the Game Data Mining competition hosted at the 2017 IEEE Conference on Computational Intelligence and Games (CIG 2017). The contest consisted of two tracks, and participants (more than 250, belonging to both industry and academia) were to predict which players would stop playing the game, as well as their remaining lifetime. The data were provided by a major worldwide video game company, NCSoft, and came from their successful massively multiplayer online game Blade and Soul. Here, we describe the long short-term memory approach and conditional inference survival ensemble model that made us win both tracks of the contest, as well as the validation procedure that we followed in order to prevent overfitting. In particular, choosing a survival method able to deal with censored data was crucial to accurately predict the moment in which each player would leave the game, as censoring is inherent in churn. The selected models proved to be robust against evolving conditions—since there was a change in the business model of the game (from subscription-based to free-to-play) between the two sample datasets provided—and efficient in terms of time cost. Thanks to these features and also to their a ability to scale to large datasets, our models could be readily implemented in real business settings. |
| Tasks | |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1901.05147v1 |
| http://arxiv.org/pdf/1901.05147v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-winning-solution-to-the-ieee-cig-2017 |
| Repo | |
| Framework | |
Split Deep Q-Learning for Robust Object Singulation
| Title | Split Deep Q-Learning for Robust Object Singulation |
| Authors | Iason Sarantopoulos, Marios Kiatos, Zoe Doulgeri, Sotiris Malassiotis |
| Abstract | Extracting a known target object from a pile of other objects in a cluttered environment is a challenging robotic manipulation task encountered in many robotic applications. In such conditions, the target object touches or is covered by adjacent obstacle objects, thus rendering traditional grasping techniques ineffective. In this paper, we propose a pushing policy aiming at singulating the target object from its surrounding clutter, by means of lateral pushing movements of both the neighboring objects and the target object until sufficient ‘grasping room’ has been achieved. To achieve the above goal we employ reinforcement learning and particularly Deep Q-learning (DQN) to learn optimal push policies by trial and error. A novel Split DQN is proposed to improve the learning rate and increase the modularity of the algorithm. Experiments show that although learning is performed in a simulated environment the transfer of learned policies to a real environment is effective thanks to robust feature selection. Finally, we demonstrate that the modularity of the algorithm allows the addition of extra primitives without retraining the model from scratch. |
| Tasks | Feature Selection, Q-Learning |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.08105v2 |
| https://arxiv.org/pdf/1909.08105v2.pdf | |
| PWC | https://paperswithcode.com/paper/split-deep-q-learning-for-robust-object |
| Repo | |
| Framework | |
Semi-supervised learning in unbalanced and heterogeneous networks
| Title | Semi-supervised learning in unbalanced and heterogeneous networks |
| Authors | Ting Li, Ningchen Ying, Xianshi Yu, Bin-Yi Jing |
| Abstract | Community detection was a hot topic on network analysis, where the main aim is to perform unsupervised learning or clustering in networks. Recently, semi-supervised learning has received increasing attention among researchers. In this paper, we propose a new algorithm, called weighted inverse Laplacian (WIL), for predicting labels in partially labeled networks. The idea comes from the first hitting time in random walk, and it also has nice explanations both in information propagation and the regularization framework. We propose a partially labeled degree-corrected block model (pDCBM) to describe the generation of partially labeled networks. We show that WIL ensures the misclassification rate is of order $O(\frac{1}{d})$ for the pDCBM with average degree $d=\Omega(\log n),$ and that it can handle situations with greater unbalanced than traditional Laplacian methods. WIL outperforms other state-of-the-art methods in most of our simulations and real datasets, especially in unbalanced networks and heterogeneous networks. |
| Tasks | Community Detection |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.01696v1 |
| http://arxiv.org/pdf/1901.01696v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-in-unbalanced-and |
| Repo | |
| Framework | |
