October 18, 2019

2937 words 14 mins read

Paper Group ANR 415

Does Haze Removal Help CNN-based Image Classification?. Efficient Subpixel Refinement with Symbolic Linear Predictors. Meta Multi-Task Learning for Sequence Modeling. Saccadic Predictive Vision Model with a Fovea. Discriminative but Not Discriminatory: A Comparison of Fairness Definitions under Different Worldviews. A classification point-of-view a …

Does Haze Removal Help CNN-based Image Classification?


Title	Does Haze Removal Help CNN-based Image Classification?
Authors	Yanting Pei, Yaping Huang, Qi Zou, Yuhang Lu, Song Wang
Abstract	Hazy images are common in real scenarios and many dehazing methods have been developed to automatically remove the haze from images. Typically, the goal of image dehazing is to produce clearer images from which human vision can better identify the object and structural details present in the images. When the ground-truth haze-free image is available for a hazy image, quantitative evaluation of image dehazing is usually based on objective metrics, such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM). However, in many applications, large-scale images are collected not for visual examination by human. Instead, they are used for many high-level vision tasks, such as automatic classification, recognition and categorization. One fundamental problem here is whether various dehazing methods can produce clearer images that can help improve the performance of the high-level tasks. In this paper, we empirically study this problem in the important task of image classification by using both synthetic and real hazy image datasets. From the experimental results, we find that the existing image-dehazing methods cannot improve much the image-classification performance and sometimes even reduce the image-classification performance.
Tasks	Image Classification, Image Dehazing
Published	2018-10-12
URL	http://arxiv.org/abs/1810.05716v1
PDF	http://arxiv.org/pdf/1810.05716v1.pdf
PWC	https://paperswithcode.com/paper/does-haze-removal-help-cnn-based-image
Repo
Framework


Title	Efficient Subpixel Refinement with Symbolic Linear Predictors
Authors	Vincent Lui, Jonathon Geeves, Winston Yii, Tom Drummond
Abstract	We present an efficient subpixel refinement method usinga learning-based approach called Linear Predictors. Two key ideas are shown in this paper. Firstly, we present a novel technique, called Symbolic Linear Predictors, which makes the learning step efficient for subpixel refinement. This makes our approach feasible for online applications without compromising accuracy, while taking advantage of the run-time efficiency of learning based approaches. Secondly, we show how Linear Predictors can be used to predict the expected alignment error, allowing us to use only the best keypoints in resource constrained applications. We show the efficiency and accuracy of our method through extensive experiments.
Tasks
Published	2018-04-28
URL	http://arxiv.org/abs/1804.10750v1
PDF	http://arxiv.org/pdf/1804.10750v1.pdf
PWC	https://paperswithcode.com/paper/efficient-subpixel-refinement-with-symbolic
Repo
Framework

Meta Multi-Task Learning for Sequence Modeling


Title	Meta Multi-Task Learning for Sequence Modeling
Authors	Junkun Chen, Xipeng Qiu, Pengfei Liu, Xuanjing Huang
Abstract	Semantic composition functions have been playing a pivotal role in neural representation learning of text sequences. In spite of their success, most existing models suffer from the underfitting problem: they use the same shared compositional function on all the positions in the sequence, thereby lacking expressive power due to incapacity to capture the richness of compositionality. Besides, the composition functions of different tasks are independent and learned from scratch. In this paper, we propose a new sharing scheme of composition function across multiple tasks. Specifically, we use a shared meta-network to capture the meta-knowledge of semantic composition and generate the parameters of the task-specific semantic composition models. We conduct extensive experiments on two types of tasks, text classification and sequence tagging, which demonstrate the benefits of our approach. Besides, we show that the shared meta-knowledge learned by our proposed model can be regarded as off-the-shelf knowledge and easily transferred to new tasks.
Tasks	Multi-Task Learning, Representation Learning, Semantic Composition, Text Classification
Published	2018-02-25
URL	http://arxiv.org/abs/1802.08969v1
PDF	http://arxiv.org/pdf/1802.08969v1.pdf
PWC	https://paperswithcode.com/paper/meta-multi-task-learning-for-sequence
Repo
Framework

Saccadic Predictive Vision Model with a Fovea


Title	Saccadic Predictive Vision Model with a Fovea
Authors	Michael Hazoglou, Todd Hylton
Abstract	We propose a model that emulates saccades, the rapid movements of the eye, called the Error Saccade Model, based on the prediction error of the Predictive Vision Model (PVM). The Error Saccade Model carries out movements of the model’s field of view to regions with the highest prediction error. Comparisons of the Error Saccade Model on Predictive Vision Models with and without a fovea show that a fovea-like structure in the input level of the PVM improves the Error Saccade Model’s ability to pursue detailed objects in its view. We hypothesize that the improvement is due to poorer resolution in the periphery causing higher prediction error when an object passes, triggering a saccade to the next location.
Tasks
Published	2018-08-01
URL	http://arxiv.org/abs/1808.00597v1
PDF	http://arxiv.org/pdf/1808.00597v1.pdf
PWC	https://paperswithcode.com/paper/saccadic-predictive-vision-model-with-a-fovea
Repo
Framework

Discriminative but Not Discriminatory: A Comparison of Fairness Definitions under Different Worldviews


Title	Discriminative but Not Discriminatory: A Comparison of Fairness Definitions under Different Worldviews
Authors	Samuel Yeom, Michael Carl Tschantz
Abstract	We mathematically compare three competing definitions of group-level nondiscrimination: demographic parity, equalized odds, and calibration. Using the theoretical framework of Friedler et al., we study the properties of each definition under various worldviews, which are assumptions about how, if at all, the observed data is biased. We argue that different worldviews call for different definitions of fairness, and we specify the worldviews that, when combined with the desire to avoid a criterion for discrimination that we call disparity amplification, motivate demographic parity and equalized odds. In addition, we show that calibration is insufficient for avoiding disparity amplification because it allows an arbitrarily large inter-group disparity. Finally, we define a worldview that is more realistic than the previously considered ones, and we introduce a new notion of fairness that corresponds to this worldview.
Tasks	Calibration
Published	2018-08-26
URL	https://arxiv.org/abs/1808.08619v4
PDF	https://arxiv.org/pdf/1808.08619v4.pdf
PWC	https://paperswithcode.com/paper/discriminative-but-not-discriminatory-a
Repo
Framework

A classification point-of-view about conditional Kendall’s tau


Title	A classification point-of-view about conditional Kendall’s tau
Authors	Alexis Derumigny, Jean-David Fermanian
Abstract	We show how the problem of estimating conditional Kendall’s tau can be rewritten as a classification task. Conditional Kendall’s tau is a conditional dependence parameter that is a characteristic of a given pair of random variables. The goal is to predict whether the pair is concordant (value of $1$) or discordant (value of $-1$) conditionally on some covariates. We prove the consistency and the asymptotic normality of a family of penalized approximate maximum likelihood estimators, including the equivalent of the logit and probit regressions in our framework. Then, we detail specific algorithms adapting usual machine learning techniques, including nearest neighbors, decision trees, random forests and neural networks, to the setting of the estimation of conditional Kendall’s tau. Finite sample properties of these estimators and their sensitivities to each component of the data-generating process are assessed in a simulation study. Finally, we apply all these estimators to a dataset of European stock indices.
Tasks
Published	2018-06-23
URL	http://arxiv.org/abs/1806.09048v3
PDF	http://arxiv.org/pdf/1806.09048v3.pdf
PWC	https://paperswithcode.com/paper/a-classification-point-of-view-about
Repo
Framework

3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model


Title	3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model
Authors	Jin Zeng, Gene Cheung, Michael Ng, Jiahao Pang, Cheng Yang
Abstract	3D point cloud - a new signal representation of volumetric objects - is a discrete collection of triples marking exterior object surface locations in 3D space. Conventional imperfect acquisition processes of 3D point cloud - e.g., stereo-matching from multiple viewpoint images or depth data acquired directly from active light sensors - imply non-negligible noise in the data. In this paper, we adopt a previously proposed low-dimensional manifold model for the surface patches in the point cloud and seek self-similar patches to denoise them simultaneously using the patch manifold prior. Due to discrete observations of the patches on the manifold, we approximate the manifold dimension computation defined in the continuous domain with a patch-based graph Laplacian regularizer and propose a new discrete patch distance measure to quantify the similarity between two same-sized surface patches for graph construction that is robust to noise. We show that our graph Laplacian regularizer has a natural graph spectral interpretation, and has desirable numerical stability properties via eigenanalysis. Extensive simulation results show that our proposed denoising scheme can outperform state-of-the-art methods in objective metrics and can better preserve visually salient structural features like edges.
Tasks	Denoising, graph construction, Stereo Matching, Stereo Matching Hand
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07252v2
PDF	http://arxiv.org/pdf/1803.07252v2.pdf
PWC	https://paperswithcode.com/paper/3d-point-cloud-denoising-using-graph
Repo
Framework

Towards Cooperation in Sequential Prisoner’s Dilemmas: a Deep Multiagent Reinforcement Learning Approach


Title	Towards Cooperation in Sequential Prisoner’s Dilemmas: a Deep Multiagent Reinforcement Learning Approach
Authors	Weixun Wang, Jianye Hao, Yixi Wang, Matthew Taylor
Abstract	The Iterated Prisoner’s Dilemma has guided research on social dilemmas for decades. However, it distinguishes between only two atomic actions: cooperate and defect. In real-world prisoner’s dilemmas, these choices are temporally extended and different strategies may correspond to sequences of actions, reflecting grades of cooperation. We introduce a Sequential Prisoner’s Dilemma (SPD) game to better capture the aforementioned characteristics. In this work, we propose a deep multiagent reinforcement learning approach that investigates the evolution of mutual cooperation in SPD games. Our approach consists of two phases. The first phase is offline: it synthesizes policies with different cooperation degrees and then trains a cooperation degree detection network. The second phase is online: an agent adaptively selects its policy based on the detected degree of opponent cooperation. The effectiveness of our approach is demonstrated in two representative SPD 2D games: the Apple-Pear game and the Fruit Gathering game. Experimental results show that our strategy can avoid being exploited by exploitative opponents and achieve cooperation with cooperative opponents.
Tasks
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00162v1
PDF	http://arxiv.org/pdf/1803.00162v1.pdf
PWC	https://paperswithcode.com/paper/towards-cooperation-in-sequential-prisoners
Repo
Framework

Accurate Kernel Learning for Linear Gaussian Markov Processes using a Scalable Likelihood Computation


Title	Accurate Kernel Learning for Linear Gaussian Markov Processes using a Scalable Likelihood Computation
Authors	Stijn de Waele
Abstract	We report an exact likelihood computation for Linear Gaussian Markov processes that is more scalable than existing algorithms for complex models and sparsely sampled signals. Better scaling is achieved through elimination of repeated computations in the Kalman likelihood, and by using the diagonalized form of the state transition equation. Using this efficient computation, we study the accuracy of kernel learning using maximum likelihood and the posterior mean in a simulation experiment. The posterior mean with a reference prior is more accurate for complex models and sparse sampling. Because of its lower computation load, the maximum likelihood estimator is an attractive option for more densely sampled signals and lower order models. We confirm estimator behavior in experimental data through their application to speleothem data.
Tasks
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07346v1
PDF	http://arxiv.org/pdf/1805.07346v1.pdf
PWC	https://paperswithcode.com/paper/accurate-kernel-learning-for-linear-gaussian
Repo
Framework

Chasing the Echo State Property


Title	Chasing the Echo State Property
Authors	Claudio Gallicchio
Abstract	Reservoir Computing (RC) provides an efficient way for designing dynamical recurrent neural models. While training is restricted to a simple output component, the recurrent connections are left untrained after initialization, subject to stability constraints specified by the Echo State Property (ESP). Literature conditions for the ESP typically fail to properly account for the effects of driving input signals, often limiting the potentialities of the RC approach. In this paper, we study the fundamental aspect of asymptotic stability of RC models in presence of driving input, introducing an empirical ESP index that enables to easily analyze the stability regimes of reservoirs. Results on two benchmark datasets reveal interesting insights on the dynamical properties of input-driven reservoirs, suggesting that the actual domain of ESP validity is much wider than what covered by literature conditions commonly used in RC practice.
Tasks
Published	2018-11-27
URL	https://arxiv.org/abs/1811.10892v2
PDF	https://arxiv.org/pdf/1811.10892v2.pdf
PWC	https://paperswithcode.com/paper/chasing-the-echo-state-property
Repo
Framework

Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks


Title	Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks
Authors	Jasper Linmans, Jim Winkens, Bastiaan S. Veeling, Taco S. Cohen, Max Welling
Abstract	We propose a semantic segmentation model that exploits rotation and reflection symmetries. We demonstrate significant gains in sample efficiency due to increased weight sharing, as well as improvements in robustness to symmetry transformations. The group equivariant CNN framework is extended for segmentation by introducing a new equivariant (G->Z2)-convolution that transforms feature maps on a group to planar feature maps. Also, equivariant transposed convolution is formulated for up-sampling in an encoder-decoder network. To demonstrate improvements in sample efficiency we evaluate on multiple data regimes of a rotation-equivariant segmentation task: cancer metastases detection in histopathology images. We further show the effectiveness of exploiting more symmetries by varying the size of the group.
Tasks	Semantic Segmentation
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00583v1
PDF	http://arxiv.org/pdf/1807.00583v1.pdf
PWC	https://paperswithcode.com/paper/sample-efficient-semantic-segmentation-using
Repo
Framework

Unsupervised Identification of Disease Marker Candidates in Retinal OCT Imaging Data


Title	Unsupervised Identification of Disease Marker Candidates in Retinal OCT Imaging Data
Authors	Philipp Seeböck, Sebastian M. Waldstein, Sophie Klimscha, Hrvoje Bogunovic, Thomas Schlegl, Bianca S. Gerendas, René Donner, Ursula Schmidt-Erfurth, Georg Langs
Abstract	The identification and quantification of markers in medical images is critical for diagnosis, prognosis, and disease management. Supervised machine learning enables the detection and exploitation of findings that are known a priori after annotation of training examples by experts. However, supervision does not scale well, due to the amount of necessary training examples, and the limitation of the marker vocabulary to known entities. In this proof-of-concept study, we propose unsupervised identification of anomalies as candidates for markers in retinal Optical Coherence Tomography (OCT) imaging data without a constraint to a priori definitions. We identify and categorize marker candidates occurring frequently in the data, and demonstrate that these markers show predictive value in the task of detecting disease. A careful qualitative analysis of the identified data driven markers reveals how their quantifiable occurrence aligns with our current understanding of disease course, in early- and late age-related macular degeneration (AMD) patients. A multi-scale deep denoising autoencoder is trained on healthy images, and a one-class support vector machine identifies anomalies in new data. Clustering in the anomalies identifies stable categories. Using these markers to classify healthy-, early AMD- and late AMD cases yields an accuracy of 81.40%. In a second binary classification experiment on a publicly available data set (healthy vs. intermediate AMD) the model achieves an area under the ROC curve of 0.944.
Tasks	Denoising
Published	2018-10-31
URL	http://arxiv.org/abs/1810.13404v1
PDF	http://arxiv.org/pdf/1810.13404v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-identification-of-disease-marker
Repo
Framework

EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching


Title	EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching
Authors	Xiao Song, Xu Zhao, Hanwen Hu, Liangji Fang
Abstract	Recent convolutional neural networks, especially end-to-end disparity estimation models, achieve remarkable performance on stereo matching task. However, existed methods, even with the complicated cascade structure, may fail in the regions of non-textures, boundaries and tiny details. Focus on these problems, we propose a multi-task network EdgeStereo that is composed of a backbone disparity network and an edge sub-network. Given a binocular image pair, our model enables end-to-end prediction of both disparity map and edge map. Basically, we design a context pyramid to encode multi-scale context information in disparity branch, followed by a compact residual pyramid for cascaded refinement. To further preserve subtle details, our EdgeStereo model integrates edge cues by feature embedding and edge-aware smoothness loss regularization. Comparative results demonstrates that stereo matching and edge detection can help each other in the unified model. Furthermore, our method achieves state-of-art performance on both KITTI Stereo and Scene Flow benchmarks, which proves the effectiveness of our design.
Tasks	Disparity Estimation, Edge Detection, Stereo Matching, Stereo Matching Hand
Published	2018-03-14
URL	http://arxiv.org/abs/1803.05196v3
PDF	http://arxiv.org/pdf/1803.05196v3.pdf
PWC	https://paperswithcode.com/paper/edgestereo-a-context-integrated-residual
Repo
Framework

Soft-Robust Actor-Critic Policy-Gradient


Title	Soft-Robust Actor-Critic Policy-Gradient
Authors	Esther Derman, Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor
Abstract	Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly conservative. Our soft-robust framework is an attempt to overcome this issue. In this paper, we present a novel Soft-Robust Actor-Critic algorithm (SR-AC). It learns an optimal policy with respect to a distribution over an uncertainty set and stays robust to model uncertainty but avoids the conservativeness of robust strategies. We show the convergence of SR-AC and test the efficiency of our approach on different domains by comparing it against regular learning methods and their robust formulations.
Tasks
Published	2018-03-11
URL	http://arxiv.org/abs/1803.04848v2
PDF	http://arxiv.org/pdf/1803.04848v2.pdf
PWC	https://paperswithcode.com/paper/soft-robust-actor-critic-policy-gradient
Repo
Framework

Single View Stereo Matching


Title	Single View Stereo Matching
Authors	Yue Luo, Jimmy Ren, Mude Lin, Jiahao Pang, Wenxiu Sun, Hongsheng Li, Liang Lin
Abstract	Previous monocular depth estimation methods take a single view and directly regress the expected results. Though recent advances are made by applying geometrically inspired loss functions during training, the inference procedure does not explicitly impose any geometrical constraint. Therefore these models purely rely on the quality of data and the effectiveness of learning to generalize. This either leads to suboptimal results or the demand of huge amount of expensive ground truth labelled data to generate reasonable results. In this paper, we show for the first time that the monocular depth estimation problem can be reformulated as two sub-problems, a view synthesis procedure followed by stereo matching, with two intriguing properties, namely i) geometrical constraints can be explicitly imposed during inference; ii) demand on labelled depth data can be greatly alleviated. We show that the whole pipeline can still be trained in an end-to-end fashion and this new formulation plays a critical role in advancing the performance. The resulting model outperforms all the previous monocular depth estimation methods as well as the stereo block matching method in the challenging KITTI dataset by only using a small number of real training data. The model also generalizes well to other monocular depth estimation benchmarks. We also discuss the implications and the advantages of solving monocular depth estimation using stereo methods.
Tasks	Depth Estimation, Monocular Depth Estimation, Stereo Matching, Stereo Matching Hand
Published	2018-03-07
URL	http://arxiv.org/abs/1803.02612v2
PDF	http://arxiv.org/pdf/1803.02612v2.pdf
PWC	https://paperswithcode.com/paper/single-view-stereo-matching
Repo
Framework