Paper Group ANR 1105
Benchmarking Surrogate-Assisted Genetic Recommender Systems. Text classification with pixel embedding. Frequentist Consistency of Gaussian Process Regression. Stochasticity and Robustness in Spiking Neural Networks. Benchmarking the Robustness of Semantic Segmentation Models. Two Birds, One Stone: A Simple, Unified Model for Text Generation from St …
Benchmarking Surrogate-Assisted Genetic Recommender Systems
| Title | Benchmarking Surrogate-Assisted Genetic Recommender Systems |
| Authors | Thomas Gabor, Philipp Altmann |
| Abstract | We propose a new approach for building recommender systems by adapting surrogate-assisted interactive genetic algorithms. A pool of user-evaluated items is used to construct an approximative model which serves as a surrogate fitness function in a genetic algorithm for optimizing new suggestions. The surrogate is used to recommend new items to the user, which are then evaluated according to the user’s liking and subsequently removed from the search space. By updating the surrogate model after new recommendations have been evaluated by the user, we enable the model itself to evolve towards the user’s preferences. In order to precisely evaluate the performance of that approach, the human’s subjective evaluation is replaced by common continuous objective benchmark functions for evolutionary algorithms. The system’s performance is compared to a conventional genetic algorithm and random search. We show that given a very limited amount of allowed evaluations on the true objective, our approach outperforms these baseline methods. |
| Tasks | Recommendation Systems |
| Published | 2019-08-08 |
| URL | https://arxiv.org/abs/1908.02880v1 |
| https://arxiv.org/pdf/1908.02880v1.pdf | |
| PWC | https://paperswithcode.com/paper/benchmarking-surrogate-assisted-genetic |
| Repo | |
| Framework | |
Text classification with pixel embedding
| Title | Text classification with pixel embedding |
| Authors | Bin Liu, Guosheng Yin, Wenbin Du |
| Abstract | We propose a novel framework to understand the text by converting sentences or articles into video-like 3-dimensional tensors. Each frame, corresponding to a slice of the tensor, is a word image that is rendered by the word’s shape. The length of the tensor equals to the number of words in the sentence or article. The proposed transformation from the text to a 3-dimensional tensor makes it very convenient to implement an $n$-gram model with convolutional neural networks for text analysis. Concretely, we impose a 3-dimensional convolutional kernel on the 3-dimensional text tensor. The first two dimensions of the convolutional kernel size equal the size of the word image and the last dimension of the kernel size is $n$. That is, every time when we slide the 3-dimensional kernel over a word sequence, the convolution covers $n$ word images and outputs a scalar. By iterating this process continuously for each $n$-gram along with the sentence or article with multiple kernels, we obtain a 2-dimensional feature map. A subsequent 1-dimensional max-over-time pooling is applied to this feature map, and three fully-connected layers are used for conducting text classification finally. Experiments of several text classification datasets demonstrate surprisingly superior performances using the proposed model in comparison with existing methods. |
| Tasks | Text Classification |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04115v2 |
| https://arxiv.org/pdf/1911.04115v2.pdf | |
| PWC | https://paperswithcode.com/paper/text-classification-with-pixel-embedding |
| Repo | |
| Framework | |
Frequentist Consistency of Gaussian Process Regression
| Title | Frequentist Consistency of Gaussian Process Regression |
| Authors | Valeriy Avanesov |
| Abstract | Gaussian Process Regression is a well-known and widely used approach to a problem of non-parametric regression. In the current study we obtain a minimax-optimal rate of convergence of its predictive mean to the true underlying function. We provide results for both random and deterministic designs. |
| Tasks | |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06689v1 |
| https://arxiv.org/pdf/1912.06689v1.pdf | |
| PWC | https://paperswithcode.com/paper/frequentist-consistency-of-gaussian-process |
| Repo | |
| Framework | |
Stochasticity and Robustness in Spiking Neural Networks
| Title | Stochasticity and Robustness in Spiking Neural Networks |
| Authors | Wilkie Olin-Ammentorp, Karsten Beckmann, Catherine D. Schuman, James S. Plank, Nathaniel C. Cady |
| Abstract | Artificial neural networks normally require precise weights to operate, despite their origins in biological systems, which can be highly variable and noisy. When implementing artificial networks which utilize analog ‘synaptic’ devices to encode weights, however, inherent limits are placed on the accuracy and precision with which these values can be encoded. In this work, we investigate the effects that inaccurate synapses have on spiking neurons and spiking neural networks. Starting with a mathematical analysis of integrate-and-fire (IF) neurons, including different non-idealities (such as leakage and channel noise), we demonstrate that noise can be used to make the behavior of IF neurons more robust to synaptic inaccuracy. We then train spiking networks which utilize IF neurons with and without noise and leakage, and experimentally confirm that the noisy networks are more robust. Lastly, we show that a noisy network can tolerate the inaccuracy expected when hafnium-oxide based resistive random-access memory is used to encode synaptic weights. |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02796v1 |
| https://arxiv.org/pdf/1906.02796v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochasticity-and-robustness-in-spiking |
| Repo | |
| Framework | |
Benchmarking the Robustness of Semantic Segmentation Models
| Title | Benchmarking the Robustness of Semantic Segmentation Models |
| Authors | Christoph Kamann, Carsten Rother |
| Abstract | When designing a semantic segmentation module for a practical application, such as autonomous driving, it is crucial to understand the robustness of the module with respect to a wide range of image corruptions. While there are recent robustness studies for full-image classification, we are the first to present an exhaustive study for semantic segmentation, based on the state-of-the-art model DeepLabv3+. To increase the realism of our study, we utilize almost 400,000 images generated from PASCAL VOC 2012, Cityscapes, and ADE20K. Based on the benchmark study, we gain several new insights. Firstly, model robustness increases with model performance, in most cases. Secondly, some architecture properties affect robustness significantly, such as a Dense Prediction Cell, which was designed to maximize performance on clean data only. |
| Tasks | Autonomous Driving, Image Classification, Semantic Segmentation |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05005v2 |
| https://arxiv.org/pdf/1908.05005v2.pdf | |
| PWC | https://paperswithcode.com/paper/benchmarking-the-robustness-of-semantic |
| Repo | |
| Framework | |
Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data
| Title | Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data |
| Authors | Hamidreza Shahidi, Ming Li, Jimmy Lin |
| Abstract | A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and unstructured data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and unstructured data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks. |
| Tasks | Question Generation, Table-to-Text Generation, Text Generation |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10158v1 |
| https://arxiv.org/pdf/1909.10158v1.pdf | |
| PWC | https://paperswithcode.com/paper/190910158 |
| Repo | |
| Framework | |
Diagnostic Image Quality Assessment and Classification in Medical Imaging: Opportunities and Challenges
| Title | Diagnostic Image Quality Assessment and Classification in Medical Imaging: Opportunities and Challenges |
| Authors | Jeffrey Ma, Ukash Nakarmi, Cedric Yue Sik Kin, Christopher Sandino, Joseph Y. Cheng, Ali B. Syed, Peter Wei, John M. Pauly, Shreyas Vasanawala |
| Abstract | Magnetic Resonance Imaging (MRI) suffers from several artifacts, the most common of which are motion artifacts. These artifacts often yield images that are of non-diagnostic quality. To detect such artifacts, images are prospectively evaluated by experts for their diagnostic quality, which necessitates patient-revisits and rescans whenever non-diagnostic quality scans are encountered. This motivates the need to develop an automated framework capable of accessing medical image quality and detecting diagnostic and non-diagnostic images. In this paper, we explore several convolutional neural network-based frameworks for medical image quality assessment and investigate several challenges therein. |
| Tasks | Image Quality Assessment |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02907v1 |
| https://arxiv.org/pdf/1912.02907v1.pdf | |
| PWC | https://paperswithcode.com/paper/diagnostic-image-quality-assessment-and |
| Repo | |
| Framework | |
Multi-Step Greedy and Approximate Real Time Dynamic Programming
| Title | Multi-Step Greedy and Approximate Real Time Dynamic Programming |
| Authors | Yonathan Efroni, Mohammad Ghavamzadeh, Shie Mannor |
| Abstract | Real Time Dynamic Programming (RTDP) is a well-known Dynamic Programming (DP) based algorithm that combines planning and learning to find an optimal policy for an MDP. It is a planning algorithm because it uses the MDP’s model (reward and transition functions) to calculate a 1-step greedy policy w.r.t.~an optimistic value function, by which it acts. It is a learning algorithm because it updates its value function only at the states it visits while interacting with the environment. As a result, unlike DP, RTDP does not require uniform access to the state space in each iteration, which makes it particularly appealing when the state space is large and simultaneously updating all the states is not computationally feasible. In this paper, we study a generalized multi-step greedy version of RTDP, which we call $h$-RTDP, in its exact form, as well as in three approximate settings: approximate model, approximate value updates, and approximate state abstraction. We analyze the sample, computation, and space complexities of $h$-RTDP and establish that increasing $h$ improves sample and space complexity, with the cost of additional offline computational operations. For the approximate cases, we prove that the asymptotic performance of $h$-RTDP is the same as that of a corresponding approximate DP – the best one can hope for without further assumptions on the approximation errors. $h$-RTDP is the first algorithm with a provably improved sample complexity when increasing the lookahead horizon. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04236v1 |
| https://arxiv.org/pdf/1909.04236v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-step-greedy-and-approximate-real-time |
| Repo | |
| Framework | |
High dimensional VAR with low rank transition
| Title | High dimensional VAR with low rank transition |
| Authors | Pierre Alquier, Karine Bertin, Paul Doukhan, Rémy Garnier |
| Abstract | We propose a vector auto-regressive (VAR) model with a low-rank constraint on the transition matrix. This new model is well suited to predict high-dimensional series that are highly correlated, or that are driven by a small number of hidden factors. We study estimation, prediction, and rank selection for this model in a very general setting. Our method shows excellent performances on a wide variety of simulated datasets. On macro-economic data from Giannone et al. (2015), our method is competitive with state-of-the-art methods in small dimension, and even improves on them in high dimension. |
| Tasks | |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.00959v2 |
| https://arxiv.org/pdf/1905.00959v2.pdf | |
| PWC | https://paperswithcode.com/paper/high-dimensional-var-with-low-rank-transition |
| Repo | |
| Framework | |
Hyper-Pairing Network for Multi-Phase Pancreatic Ductal Adenocarcinoma Segmentation
| Title | Hyper-Pairing Network for Multi-Phase Pancreatic Ductal Adenocarcinoma Segmentation |
| Authors | Yuyin Zhou, Yingwei Li, Zhishuai Zhang, Yan Wang, Angtian Wang, Elliot Fishman, Alan Yuille, Seyoun Park |
| Abstract | Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers with an overall five-year survival rate of 8%. Due to subtle texture changes of PDAC, pancreatic dual-phase imaging is recommended for better diagnosis of pancreatic disease. In this study, we aim at enhancing PDAC automatic segmentation by integrating multi-phase information (i.e., arterial phase and venous phase). To this end, we present Hyper-Pairing Network (HPN), a 3D fully convolution neural network which effectively integrates information from different phases. The proposed approach consists of a dual path network where the two parallel streams are interconnected with hyper-connections for intensive information exchange. Additionally, a pairing loss is added to encourage the commonality between high-level feature representations of different phases. Compared to prior arts which use single phase data, HPN reports a significant improvement up to 7.73% (from 56.21% to 63.94%) in terms of DSC. |
| Tasks | |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.00906v1 |
| https://arxiv.org/pdf/1909.00906v1.pdf | |
| PWC | https://paperswithcode.com/paper/hyper-pairing-network-for-multi-phase |
| Repo | |
| Framework | |
Multi-view PointNet for 3D Scene Understanding
| Title | Multi-view PointNet for 3D Scene Understanding |
| Authors | Maximilian Jaritz, Jiayuan Gu, Hao Su |
| Abstract | Fusion of 2D images and 3D point clouds is important because information from dense images can enhance sparse point clouds. However, fusion is challenging because 2D and 3D data live in different spaces. In this work, we propose MVPNet (Multi-View PointNet), where we aggregate 2D multi-view image features into 3D point clouds, and then use a point based network to fuse the features in 3D canonical space to predict 3D semantic labels. To this end, we introduce view selection along with a 2D-3D feature aggregation module. Extensive experiments show the benefit of leveraging features from dense images and reveal superior robustness to varying point cloud density compared to 3D-only methods. On the ScanNetV2 benchmark, our MVPNet significantly outperforms prior point cloud based approaches on the task of 3D Semantic Segmentation. It is much faster to train than the large networks of the sparse voxel approach. We provide solid ablation studies to ease the future design of 2D-3D fusion methods and their extension to other tasks, as we showcase for 3D instance segmentation. |
| Tasks | 3D Instance Segmentation, 3D Semantic Segmentation, Instance Segmentation, Scene Understanding, Semantic Segmentation |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13603v1 |
| https://arxiv.org/pdf/1909.13603v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-pointnet-for-3d-scene |
| Repo | |
| Framework | |
Bayesian Experimental Design for Finding Reliable Level Set under Input Uncertainty
| Title | Bayesian Experimental Design for Finding Reliable Level Set under Input Uncertainty |
| Authors | Shogo Iwazaki, Yu Inatsu, Ichiro Takeuchi |
| Abstract | In the manufacturing industry, it is often necessary to repeat expensive operational testing of machine in order to identify the range of input conditions under which the machine operates properly. Since it is often difficult to accurately control the input conditions during the actual usage of the machine, there is a need to guarantee the performance of the machine after properly incorporating the possible variation in input conditions. In this paper, we formulate this practical manufacturing scenario as an Input Uncertain Reliable Level Set Estimation (IU-rLSE) problem, and provide an efficient algorithm for solving it. The goal of IU-rLSE is to identify the input range in which the outputs smaller/greater than a desired threshold can be obtained with high probability when the input uncertainty is properly taken into consideration. We propose an active learning method to solve the IU-rLSE problem efficiently, theoretically analyze its accuracy and convergence, and illustrate its empirical performance through numerical experiments on artificial and real data. |
| Tasks | Active Learning |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1910.12043v1 |
| https://arxiv.org/pdf/1910.12043v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-experimental-design-for-finding |
| Repo | |
| Framework | |
SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection
| Title | SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection |
| Authors | Sanping Zhou, Jimuyang Zhang, Jinjun Wang, Fei Wang, Dong Huang |
| Abstract | Deep convolutional neural network significantly boosted the capability of salient object detection in handling large variations of scenes and object appearances. However, convolution operations seek to generate strong responses on individual pixels, while lack the ability to maintain the spatial structure of objects. Moreover, the down-sampling operations, such as pooling and striding, lose spatial details of the salient objects. In this paper, we propose a simple yet effective Siamese Edge-Enhancement Network (SE2Net) to preserve the edge structure for salient object detection. Specifically, a novel multi-stage siamese network is built to aggregate the low-level and high-level features, and parallelly estimate the salient maps of edges and regions. As a result, the predicted regions become more accurate by enhancing the responses at edges, and the predicted edges become more semantic by suppressing the false positives in background. After the refined salient maps of edges and regions are produced by the SE2Net, an edge-guided inference algorithm is designed to further improve the resulting salient masks along the predicted edges. Extensive experiments on several benchmark datasets have been conducted, which show that our method is superior than the state-of-the-art approaches. |
| Tasks | Object Detection, Salient Object Detection |
| Published | 2019-03-29 |
| URL | https://arxiv.org/abs/1904.00048v2 |
| https://arxiv.org/pdf/1904.00048v2.pdf | |
| PWC | https://paperswithcode.com/paper/se2net-siamese-edge-enhancement-network-for |
| Repo | |
| Framework | |
Network entity characterization and attack prediction
| Title | Network entity characterization and attack prediction |
| Authors | Vaclav Bartos, Martin Zadnik, Sheikh Mahbub Habib, Emmanouil Vasilomanolakis |
| Abstract | The devastating effects of cyber-attacks, highlight the need for novel attack detection and prevention techniques. Over the last years, considerable work has been done in the areas of attack detection as well as in collaborative defense. However, an analysis of the state of the art suggests that many challenges exist in prioritizing alert data and in studying the relation between a recently discovered attack and the probability of it occurring again. In this article, we propose a system that is intended for characterizing network entities and the likelihood that they will behave maliciously in the future. Our system, namely Network Entity Reputation Database System (NERDS), takes into account all the available information regarding a network entity (e. g. IP address) to calculate the probability that it will act maliciously. The latter part is achieved via the utilization of machine learning. Our experimental results show that it is indeed possible to precisely estimate the probability of future attacks from each entity using information about its previous malicious behavior and other characteristics. Ranking the entities by this probability has practical applications in alert prioritization, assembly of highly effective blacklists of a limited length and other use cases. |
| Tasks | |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07694v1 |
| https://arxiv.org/pdf/1909.07694v1.pdf | |
| PWC | https://paperswithcode.com/paper/network-entity-characterization-and-attack |
| Repo | |
| Framework | |
SAC-Net: Spatial Attenuation Context for Salient Object Detection
| Title | SAC-Net: Spatial Attenuation Context for Salient Object Detection |
| Authors | Xiaowei Hu, Chi-Wing Fu, Lei Zhu, Pheng-Ann Heng |
| Abstract | This paper presents a new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects. Our key idea is to adaptively propagate and aggregate the image context features with variable attenuation over the entire feature maps. To achieve this, we design the spatial attenuation context (SAC) module to recurrently translate and aggregate the context features independently with different attenuation factors and then to attentively learn the weights to adaptively integrate the aggregated context features. By further embedding the module to process individual layers in a deep network, namely SAC-Net, we can train the network end-to-end and optimize the context features for detecting salient objects. Compared with 29 state-of-the-art methods, experimental results show that our method performs favorably over all the others on six common benchmark data, both quantitatively and visually. |
| Tasks | Object Detection, Salient Object Detection |
| Published | 2019-03-25 |
| URL | https://arxiv.org/abs/1903.10152v2 |
| https://arxiv.org/pdf/1903.10152v2.pdf | |
| PWC | https://paperswithcode.com/paper/sac-net-spatial-attenuation-context-for |
| Repo | |
| Framework | |
