January 26, 2020

3343 words 16 mins read

Paper Group ANR 1367

User-Oriented Summaries Using a PSO Based Scoring Optimization Method. Risk-Aware Active Inverse Reinforcement Learning. When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation. Interpretable Complex-Valued Neural Networks for Privacy Protection. Dynamic optimization with side information. Prostate Segmentation from 3D MRI Us …

User-Oriented Summaries Using a PSO Based Scoring Optimization Method


Title	User-Oriented Summaries Using a PSO Based Scoring Optimization Method
Authors	Augusto Villa-Monte, Laura Lanzarini, Aurelio F. Bariviera, José A. Olivas
Abstract	Automatic text summarization tools have a great impact on many fields, such as medicine, law, and scientific research in general. As information overload increases, automatic summaries allow handling the growing volume of documents, usually by assigning weights to the extracted phrases based on their significance in the expected summary. Obtaining the main contents of any given document in less time than it would take to do that manually is still an issue of interest. In~this~ article, a new method is presented that allows automatically generating extractive summaries from documents by adequately weighting sentence scoring features using \textit{Particle Swarm Optimization}. The key feature of the proposed method is the identification of those features that are closest to the criterion used by the individual when summarizing. The proposed method combines a binary representation and a continuous one, using an original variation of the technique developed by the authors of this paper. Our paper shows that using user labeled information in the training set helps to find better metrics and weights. The empirical results yield an improved accuracy compared to previous methods used in this field
Tasks	Text Summarization
Published	2019-06-26
URL	https://arxiv.org/abs/1906.11290v1
PDF	https://arxiv.org/pdf/1906.11290v1.pdf
PWC	https://paperswithcode.com/paper/user-oriented-summaries-using-a-pso-based
Repo
Framework

Risk-Aware Active Inverse Reinforcement Learning


Title	Risk-Aware Active Inverse Reinforcement Learning
Authors	Daniel S. Brown, Yuchen Cui, Scott Niekum
Abstract	Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. Utilizing recent advances in performance bounds for inverse reinforcement learning, we propose a risk-aware active inverse reinforcement learning algorithm that focuses active queries on areas of the state space with the potential for large generalization error. We show that risk-aware active learning outperforms standard active IRL approaches on gridworld, simulated driving, and table setting tasks, while also providing a performance-based stopping criterion that allows a robot to know when it has received enough demonstrations to safely perform a task.
Tasks	Active Learning
Published	2019-01-08
URL	https://arxiv.org/abs/1901.02161v2
PDF	https://arxiv.org/pdf/1901.02161v2.pdf
PWC	https://paperswithcode.com/paper/risk-aware-active-inverse-reinforcement
Repo
Framework

When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation


Title	When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation
Authors	Ling Zhang, Xiaosong Wang, Dong Yang, Thomas Sanford, Stephanie Harmon, Baris Turkbey, Holger Roth, Andriy Myronenko, Daguang Xu, Ziyue Xu
Abstract	Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, in clinically realistic environments, such methods have marginal performance due to differences in image domains, including different imaging protocols, device vendors and patient populations. Here we consider the problem of domain generalization, when a model is trained once, and its performance generalizes to unseen domains. Intuitively, within a specific medical imaging modality the domain differences are smaller relative to natural images domain variability. We rethink data augmentation for medical 3D images and propose a deep stacked transformations (DST) approach for domain generalization. Specifically, a series of n stacked transformations are applied to each image in each mini-batch during network training to account for the contribution of domain-specific shifts in medical images. We comprehensively evaluate our method on three tasks: segmentation of whole prostate from 3D MRI, left atrial from 3D MRI, and left ventricle from 3D ultrasound. We demonstrate that when trained on a small source dataset, (i) on average, DST models on unseen datasets degrade only by 11% (Dice score change), compared to the conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%); (ii) when evaluation on the same domain, DST is also better albeit only marginally. (iii) When training on large-sized data, DST on unseen domains reaches performance of state-of-the-art fully supervised models. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of robust deep segmentation models for clinical deployment.
Tasks	Data Augmentation, Domain Adaptation, Domain Generalization, Medical Image Segmentation, Semantic Segmentation
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03347v2
PDF	https://arxiv.org/pdf/1906.03347v2.pdf
PWC	https://paperswithcode.com/paper/when-unseen-domain-generalization-is
Repo
Framework

Interpretable Complex-Valued Neural Networks for Privacy Protection


Title	Interpretable Complex-Valued Neural Networks for Privacy Protection
Authors	Liyao Xiang, Haotian Ma, Hao Zhang, Yifan Zhang, Jie Ren, Quanshi Zhang
Abstract	Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features. We study the possibility of preventing such adversarial inference, yet without too much accuracy degradation. We propose a generic method to revise the neural network to boost the challenge of inferring input attributes from features, while maintaining highly accurate outputs. In particular, the method transforms real-valued features into complex-valued ones, in which the input is hidden in a randomized phase of the transformed features. The knowledge of the phase acts like a key, with which any party can easily recover the output from the processing result, but without which the party can neither recover the output nor distinguish the original input. Preliminary experiments on various datasets and network structures have shown that our method significantly diminishes the adversary’s ability in inferring about the input while largely preserves the resulting accuracy.
Tasks
Published	2019-01-28
URL	https://arxiv.org/abs/1901.09546v2
PDF	https://arxiv.org/pdf/1901.09546v2.pdf
PWC	https://paperswithcode.com/paper/complex-valued-neural-networks-for-privacy
Repo
Framework

Dynamic optimization with side information


Title	Dynamic optimization with side information
Authors	Dimitris Bertsimas, Christopher McCord, Bradley Sturt
Abstract	We present a data-driven framework for incorporating side information in dynamic optimization under uncertainty. Specifically, our approach uses predictive machine learning methods (such as k-nearest neighbors, kernel regression, and random forests) to weight the relative importance of various data-driven uncertainty sets in a robust optimization formulation. Through a novel measure concentration result for local machine learning methods, we prove that the proposed framework is asymptotically optimal for stochastic dynamic optimization with covariates. We also describe a general-purpose approximation for the proposed framework, based on overlapping linear decision rules, which is computationally tractable and produces high-quality solutions for dynamic problems with many stages. Across a variety of examples in shipment planning, inventory management, and finance, our method achieves improvements of up to 15% over alternatives and requires less than one minute of computation time on problems with twelve stages.
Tasks
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07307v1
PDF	https://arxiv.org/pdf/1907.07307v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-optimization-with-side-information
Repo
Framework

Prostate Segmentation from 3D MRI Using a Two-Stage Model and Variable-Input Based Uncertainty Measure


Title	Prostate Segmentation from 3D MRI Using a Two-Stage Model and Variable-Input Based Uncertainty Measure
Authors	Huitong Pan, Yushan Feng, Quan Chen, Craig Meyer, Xue Feng
Abstract	This paper proposes a two-stage segmentation model, variable-input based uncertainty measures and an uncertainty-guided post-processing method for prostate segmentation on 3D magnetic resonance images (MRI). The two-stage model was based on 3D dilated U-Nets with the first stage to localize the prostate and the second stage to obtain an accurate segmentation from cropped images. For data augmentation, we proposed the variable-input method which crops the region of interest with additional random variations. Similar to other deep learning models, the proposed model also faced the challenge of suboptimal performance in certain testing cases due to varied training and testing image characteristics. Therefore, it is valuable to evaluate the confidence and performance of the network using uncertainty measures, which are often calculated from the probability maps or their standard deviations with multiple model outputs for the same testing case. However, few studies have quantitatively compared different methods of uncertainty calculation. Furthermore, unlike the commonly used Bayesian dropout during testing, we developed uncertainty measures based on the variable input images at the second stage and evaluated its performance by calculating the correlation with ground-truth-based performance metrics, such as Dice score. For performance estimation, we predicted Dice scores and Hausdorff distance with the most correlated uncertainty measure. For post-processing, we performed Gaussian filter on the underperformed slices to improve segmentation quality. Using PROMISE-12 data, we demonstrated the robustness of the two-stage model and showed high correlation of the proposed variable-input based uncertainty measures with GT-based performance. The uncertainty-guided post-processing method significantly improved label smoothness.
Tasks	Data Augmentation
Published	2019-03-06
URL	http://arxiv.org/abs/1903.02500v1
PDF	http://arxiv.org/pdf/1903.02500v1.pdf
PWC	https://paperswithcode.com/paper/prostate-segmentation-from-3d-mri-using-a-two
Repo
Framework

Unsupervised uncertainty estimation using spatiotemporal cues in video saliency detection


Title	Unsupervised uncertainty estimation using spatiotemporal cues in video saliency detection
Authors	Tariq Alshawi, Zhiling Long, Ghassan AlRegib
Abstract	In this paper, we address the problem of quantifying reliability of computational saliency for videos, which can be used to improve saliency-based video processing and enable more reliable performance and risk assessment of such processing. Our approach is twofold. First, we explore spatial correlations in both saliency map and eye-fixation map. Then, we learn spatiotemporal correlations that define a reliable saliency map. We first study spatiotemporal eye-fixation data from a public dataset and investigate a common feature in human visual attention, which dictates correlation in saliency between a pixel and its direct neighbors. Based on the study, we then develop an algorithm that estimates a pixel-wise uncertainty map that reflects our confidence in the associated computational saliency map by relating a pixel’s saliency to the saliency of its neighbors. To estimate such uncertainties, we measure the divergence of a pixel, in a saliency map, from its local neighborhood. Additionally, we propose a systematic procedure to evaluate the estimation performance by explicitly computing uncertainty ground truth as a function of a given saliency map and eye fixations of human subjects. In our experiments, we explore multiple definitions of locality and neighborhoods in spatiotemporal video signals. In addition, we examine the relationship between the parameters of our proposed algorithm and the content of the videos. The proposed algorithm is unsupervised, making it more suitable for generalization to most natural videos. Also, it is computationally efficient and flexible for customization to specific video content. Experiments using three publicly available video datasets show that the proposed algorithm outperforms state-of-the-art uncertainty estimation methods with improvement in accuracy up to 63% and offers efficiency and flexibility that make it more useful in practical situations.
Tasks	Saliency Detection, Video Saliency Detection
Published	2019-01-06
URL	http://arxiv.org/abs/1901.01550v1
PDF	http://arxiv.org/pdf/1901.01550v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-uncertainty-estimation-using
Repo
Framework

Image Restoration using Plug-and-Play CNN MAP Denoisers


Title	Image Restoration using Plug-and-Play CNN MAP Denoisers
Authors	Siavash Bigdeli, David Honzátko, Sabine Süsstrunk, L. Andrea Dunbar
Abstract	Plug-and-play denoisers can be used to perform generic image restoration tasks independent of the degradation type. These methods build on the fact that the Maximum a Posteriori (MAP) optimization can be solved using smaller sub-problems, including a MAP denoising optimization. We present the first end-to-end approach to MAP estimation for image denoising using deep neural networks. We show that our method is guaranteed to minimize the MAP denoising objective, which is then used in an optimization algorithm for generic image restoration. We provide theoretical analysis of our approach and show the quantitative performance of our method in several experiments. Our experimental results show that the proposed method can achieve 70x faster performance compared to the state-of-the-art, while maintaining the theoretical perspective of MAP.
Tasks	Denoising, Image Denoising, Image Restoration
Published	2019-12-18
URL	https://arxiv.org/abs/1912.09299v2
PDF	https://arxiv.org/pdf/1912.09299v2.pdf
PWC	https://paperswithcode.com/paper/image-restoration-using-plug-and-play-cnn-map
Repo
Framework

Quantifying the Chaos Level of Infants’ Environment via Unsupervised Learning


Title	Quantifying the Chaos Level of Infants’ Environment via Unsupervised Learning
Authors	Priyanka Khante, Mai Lee Chang, Domingo Martinez, Kaya de Barbaro, Edison Thomaz
Abstract	Acoustic environments vary dramatically within the home setting. They can be a source of comfort and tranquility or chaos that can lead to less optimal cognitive development in children. Research to date has only subjectively measured household chaos. In this work, we use three unsupervised machine learning techniques to quantify household chaos in infants’ homes. These unsupervised techniques include hierarchical clustering using K-Means, clustering using self-organizing map (SOM) and deep learning. We evaluated these techniques using data from 9 participants which is a total of 197 hours. Results show that these techniques are promising to quantify household chaos.
Tasks
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04844v1
PDF	https://arxiv.org/pdf/1912.04844v1.pdf
PWC	https://paperswithcode.com/paper/quantifying-the-chaos-level-of-infants
Repo
Framework

Distortion Estimation Through Explicit Modeling of the Refractive Surface


Title	Distortion Estimation Through Explicit Modeling of the Refractive Surface
Authors	Szabolcs Pável, Csanád Sándor, Lehel Csató
Abstract	Precise calibration is a must for high reliance 3D computer vision algorithms. A challenging case is when the camera is behind a protective glass or transparent object: due to refraction, the image is heavily distorted; the pinhole camera model alone can not be used and a distortion correction step is required. By directly modeling the geometry of the refractive media, we build the image generation process by tracing individual light rays from the camera to a target. Comparing the generated images to their distorted - observed - counterparts, we estimate the geometry parameters of the refractive surface via model inversion by employing an RBF neural network. We present an image collection methodology that produces data suited for finding the distortion parameters and test our algorithm on synthetic and real-world data. We analyze the results of the algorithm.
Tasks	Calibration, Image Generation
Published	2019-09-24
URL	https://arxiv.org/abs/1909.10820v1
PDF	https://arxiv.org/pdf/1909.10820v1.pdf
PWC	https://paperswithcode.com/paper/distortion-estimation-through-explicit
Repo
Framework

CRAD: Clustering with Robust Autocuts and Depth


Title	CRAD: Clustering with Robust Autocuts and Depth
Authors	Xin Huang, Yulia R. Gel
Abstract	We develop a new density-based clustering algorithm named CRAD which is based on a new neighbor searching function with a robust data depth as the dissimilarity measure. Our experiments prove that the new CRAD is highly competitive at detecting clusters with varying densities, compared with the existing algorithms such as DBSCAN, OPTICS and DBCA. Furthermore, a new effective parameter selection procedure is developed to select the optimal underlying parameter in the real-world clustering, when the ground truth is unknown. Lastly, we suggest a new clustering framework that extends CRAD from spatial data clustering to time series clustering without a-priori knowledge of the true number of clusters. The performance of CRAD is evaluated through extensive experimental studies.
Tasks	Time Series, Time Series Clustering
Published	2019-04-08
URL	http://arxiv.org/abs/1904.04020v1
PDF	http://arxiv.org/pdf/1904.04020v1.pdf
PWC	https://paperswithcode.com/paper/crad-clustering-with-robust-autocuts-and
Repo
Framework

Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers


Title	Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers
Authors	Ameya Joshi, Amitangshu Mukherjee, Soumik Sarkar, Chinmay Hegde
Abstract	Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the image pixel space. In this paper, we consider a different setting: what happens if the adversary could only alter specific attributes of the input image? These would generate inputs that might be perceptibly different, but still natural-looking and enough to fool a classifier. We propose a novel approach to generate such `semantic’ adversarial examples by optimizing a particular adversarial loss over the range-space of a parametric conditional generative model. We demonstrate implementations of our attacks on binary classifiers trained on face images, and show that such natural-looking semantic adversarial examples exist. We evaluate the effectiveness of our attack on synthetic and real data, and present detailed comparisons with existing attack methods. We supplement our empirical results with theoretical bounds that demonstrate the existence of such parametric adversarial examples. \|
Tasks
Published	2019-04-17
URL	https://arxiv.org/abs/1904.08489v2
PDF	https://arxiv.org/pdf/1904.08489v2.pdf
PWC	https://paperswithcode.com/paper/semantic-adversarial-attacks-parametric
Repo
Framework

Detection of Myocardial Infarction Based on Novel Deep Transfer Learning Methods for Urban Healthcare in Smart Cities


Title	Detection of Myocardial Infarction Based on Novel Deep Transfer Learning Methods for Urban Healthcare in Smart Cities
Authors	Ahmed Alghamdi, Mohamed Hammad, Hassan Ugail, Asmaa Abdel-Raheem, Khan Muhammad, Hany S. Khalifa, Ahmed A. Abd El-Latif
Abstract	. In this paper, an effective computer-aided diagnosis (CAD) system is presented to detect MI signals using the convolution neural network (CNN) for urban healthcare in smart cities. Two types of transfer learning techniques are employed to retrain the pre-trained VGG-Net (Fine-tuning and VGG-Net as fixed feature extractor) and obtained two new networks VGG-MI1 and VGG-MI2. In the VGG-MI1 model, the last layer of the VGG-Net model is replaced with a specific layer according to our requirements and various functions are optimized to reduce overfitting. In the VGG-MI2 model, one layer of the VGG-Net model is selected as a feature descriptor of the ECG images to describe it with informative features. Considering the limited availability of dataset, ECG data is augmented which has increased the classification performance. Physikalisch-technische bundesanstalt (PTB) Diagnostic ECG database is used for experimentation, which has been widely employed in MI detection studies. In case of using VGG-MI1, we achieved an accuracy, sensitivity, and specificity of 99.02%, 98.76%, and 99.17%, respectively and we achieved an accuracy of 99.22%, a sensitivity of 99.15%, and a specificity of 99.49% with VGG-MI2 model. Experimental results validate the efficiency of the proposed system in terms of accuracy sensitivity, and specificity.
Tasks	Data Augmentation, Transfer Learning
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09358v2
PDF	https://arxiv.org/pdf/1906.09358v2.pdf
PWC	https://paperswithcode.com/paper/a-novel-deep-transfer-learning-method-for
Repo
Framework

Intelligent image synthesis to attack a segmentation CNN using adversarial learning


Title	Intelligent image synthesis to attack a segmentation CNN using adversarial learning
Authors	Liang Chen, Paul Bentley, Kensaku Mori, Kazunari Misawa, Michitaka Fujiwara, Daniel Rueckert
Abstract	Deep learning approaches based on convolutional neural networks (CNNs) have been successful in solving a number of problems in medical imaging, including image segmentation. In recent years, it has been shown that CNNs are vulnerable to attacks in which the input image is perturbed by relatively small amounts of noise so that the CNN is no longer able to perform a segmentation of the perturbed image with sufficient accuracy. Therefore, exploring methods on how to attack CNN-based models as well as how to defend models against attacks have become a popular topic as this also provides insights into the performance and generalization abilities of CNNs. However, most of the existing work assumes unrealistic attack models, i.e. the resulting attacks were specified in advance. In this paper, we propose a novel approach for generating adversarial examples to attack CNN-based segmentation models for medical images. Our approach has three key features: 1) The generated adversarial examples exhibit anatomical variations (in form of deformations) as well as appearance perturbations; 2) The adversarial examples attack segmentation models so that the Dice scores decrease by a pre-specified amount; 3) The attack is not required to be specified beforehand. We have evaluated our approach on CNN-based approaches for the multi-organ segmentation problem in 2D CT images. We show that the proposed approach can be used to attack different CNN-based segmentation models.
Tasks	Image Generation, Semantic Segmentation
Published	2019-09-24
URL	https://arxiv.org/abs/1909.11167v1
PDF	https://arxiv.org/pdf/1909.11167v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-image-synthesis-to-attack-a
Repo
Framework

Human Synthesis and Scene Compositing


Title	Human Synthesis and Scene Compositing
Authors	Mihai Zanfir, Elisabeta Oneata, Alin-Ionut Popa, Andrei Zanfir, Cristian Sminchisescu
Abstract	Generating good quality and geometrically plausible synthetic images of humans with the ability to control appearance, pose and shape parameters, has become increasingly important for a variety of tasks ranging from photo editing, fashion virtual try-on, to special effects and image compression. In this paper, we propose HUSC, a HUman Synthesis and Scene Compositing framework for the realistic synthesis of humans with different appearance, in novel poses and scenes. Central to our formulation is 3d reasoning for both people and scenes, in order to produce realistic collages, by correctly modeling perspective effects and occlusion, by taking into account scene semantics and by adequately handling relative scales. Conceptually our framework consists of three components: (1) a human image synthesis model with controllable pose and appearance, based on a parametric representation, (2) a person insertion procedure that leverages the geometry and semantics of the 3d scene, and (3) an appearance compositing process to create a seamless blending between the colors of the scene and the generated human image, and avoid visual artifacts. The performance of our framework is supported by both qualitative and quantitative results, in particular state-of-the art synthesis scores for the DeepFashion dataset.
Tasks	Image Compression, Image Generation
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10307v2
PDF	https://arxiv.org/pdf/1909.10307v2.pdf
PWC	https://paperswithcode.com/paper/190910307
Repo
Framework