July 28, 2019

2745 words 13 mins read

Paper Group ANR 407

Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks. Eigenoption Discovery through the Deep Successor Representation. Evolutionary Multitasking for Multiobjective Continuous Optimization: Benchmark Problems, Performance Metrics and Baseline Results. Discovering Evolutionary Stepping Stones through Behavior Domination. …

Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks


Title	Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks
Authors	Manu Goyal, Moi Hoon Yap, Saeed Hassanpour
Abstract	Melanoma is clinically difficult to distinguish from common benign skin lesions, particularly melanocytic naevus and seborrhoeic keratosis. The dermoscopic appearance of these lesions has huge intra-class variations and high inter-class visual similarities. Most current research is focusing on single-class segmentation irrespective of classes of skin lesions. In this work, we evaluate the performance of deep learning on multi-class segmentation of ISIC-2017 challenge dataset, which consists of 2,750 dermoscopic images. We propose an end-to-end solution using fully convolutional networks (FCNs) for multi-class semantic segmentation to automatically segment the melanoma, seborrhoeic keratosis and naevus. To improve the performance of FCNs, transfer learning and a hybrid loss function are used. We evaluate the performance of the deep learning segmentation methods for multi-class segmentation and lesion diagnosis (with post-processing method) on the testing set of the ISIC-2017 challenge dataset. The results showed that the two-tier level transfer learning FCN-8s achieved the overall best result with \textit{Dice} score of 78.5% in a naevus category, 65.3% in melanoma, and 55.7% in seborrhoeic keratosis in multi-class segmentation and Accuracy of 84.62% for recognition of melanoma in lesion diagnosis.
Tasks	Semantic Segmentation, Transfer Learning
Published	2017-11-28
URL	https://arxiv.org/abs/1711.10449v2
PDF	https://arxiv.org/pdf/1711.10449v2.pdf
PWC	https://paperswithcode.com/paper/multi-class-semantic-segmentation-of-skin
Repo
Framework

Eigenoption Discovery through the Deep Successor Representation


Title	Eigenoption Discovery through the Deep Successor Representation
Authors	Marlos C. Machado, Clemens Rosenbaum, Xiaoxiao Guo, Miao Liu, Gerald Tesauro, Murray Campbell
Abstract	Options in reinforcement learning allow agents to hierarchically decompose a task into subtasks, having the potential to speed up learning and planning. However, autonomously learning effective sets of options is still a major challenge in the field. In this paper we focus on the recently introduced idea of using representation learning methods to guide the option discovery process. Specifically, we look at eigenoptions, options obtained from representations that encode diffusive information flow in the environment. We extend the existing algorithms for eigenoption discovery to settings with stochastic transitions and in which handcrafted features are not available. We propose an algorithm that discovers eigenoptions while learning non-linear state representations from raw pixels. It exploits recent successes in the deep reinforcement learning literature and the equivalence between proto-value functions and the successor representation. We use traditional tabular domains to provide intuition about our approach and Atari 2600 games to demonstrate its potential.
Tasks	Atari Games, Representation Learning
Published	2017-10-30
URL	http://arxiv.org/abs/1710.11089v3
PDF	http://arxiv.org/pdf/1710.11089v3.pdf
PWC	https://paperswithcode.com/paper/eigenoption-discovery-through-the-deep
Repo
Framework

Evolutionary Multitasking for Multiobjective Continuous Optimization: Benchmark Problems, Performance Metrics and Baseline Results


Title	Evolutionary Multitasking for Multiobjective Continuous Optimization: Benchmark Problems, Performance Metrics and Baseline Results
Authors	Yuan Yuan, Yew-Soon Ong, Liang Feng, A. K. Qin, Abhishek Gupta, Bingshui Da, Qingfu Zhang, Kay Chen Tan, Yaochu Jin, Hisao Ishibuchi
Abstract	In this report, we suggest nine test problems for multi-task multi-objective optimization (MTMOO), each of which consists of two multiobjective optimization tasks that need to be solved simultaneously. The relationship between tasks varies between different test problems, which would be helpful to have a comprehensive evaluation of the MO-MFO algorithms. It is expected that the proposed test problems will germinate progress the field of the MTMOO research.
Tasks	Multiobjective Optimization
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02766v1
PDF	http://arxiv.org/pdf/1706.02766v1.pdf
PWC	https://paperswithcode.com/paper/evolutionary-multitasking-for-multiobjective
Repo
Framework

Discovering Evolutionary Stepping Stones through Behavior Domination


Title	Discovering Evolutionary Stepping Stones through Behavior Domination
Authors	Elliot Meyerson, Risto Miikkulainen
Abstract	Behavior domination is proposed as a tool for understanding and harnessing the power of evolutionary systems to discover and exploit useful stepping stones. Novelty search has shown promise in overcoming deception by collecting diverse stepping stones, and several algorithms have been proposed that combine novelty with a more traditional fitness measure to refocus search and help novelty search scale to more complex domains. However, combinations of novelty and fitness do not necessarily preserve the stepping stone discovery that novelty search affords. In several existing methods, competition between solutions can lead to an unintended loss of diversity. Behavior domination defines a class of algorithms that avoid this problem, while inheriting theoretical guarantees from multiobjective optimization. Several existing algorithms are shown to be in this class, and a new algorithm is introduced based on fast non-dominated sorting. Experimental results show that this algorithm outperforms existing approaches in domains that contain useful stepping stones, and its advantage is sustained with scale. The conclusion is that behavior domination can help illuminate the complex dynamics of behavior-driven search, and can thus lead to the design of more scalable and robust algorithms.
Tasks	Multiobjective Optimization
Published	2017-04-18
URL	http://arxiv.org/abs/1704.05554v1
PDF	http://arxiv.org/pdf/1704.05554v1.pdf
PWC	https://paperswithcode.com/paper/discovering-evolutionary-stepping-stones
Repo
Framework

Generating Appealing Brand Names


Title	Generating Appealing Brand Names
Authors	Gaurush Hiranandani, Pranav Maneriker, Harsh Jhamtani
Abstract	Providing appealing brand names to newly launched products, newly formed companies or for renaming existing companies is highly important as it can play a crucial role in deciding its success or failure. In this work, we propose a computational method to generate appealing brand names based on the description of such entities. We use quantitative scores for readability, pronounceability, memorability and uniqueness of the generated names to rank order them. A set of diverse appealing names is recommended to the user for the brand naming task. Experimental results show that the names generated by our approach are more appealing than names which prior approaches and recruited humans could come up.
Tasks
Published	2017-06-28
URL	http://arxiv.org/abs/1706.09335v1
PDF	http://arxiv.org/pdf/1706.09335v1.pdf
PWC	https://paperswithcode.com/paper/generating-appealing-brand-names
Repo
Framework

Linear vs Nonlinear Extreme Learning Machine for Spectral-Spatial Classification of Hyperspectral Image


Title	Linear vs Nonlinear Extreme Learning Machine for Spectral-Spatial Classification of Hyperspectral Image
Authors	Faxian Cao, Zhijing Yang, Jinchang Ren, Mengying Jiang, Wing-Kuen Ling
Abstract	As a new machine learning approach, extreme learning machine (ELM) has received wide attentions due to its good performances. However, when directly applied to the hyperspectral image (HSI) classification, the recognition rate is too low. This is because ELM does not use the spatial information which is very important for HSI classification. In view of this, this paper proposes a new framework for spectral-spatial classification of HSI by combining ELM with loopy belief propagation (LBP). The original ELM is linear, and the nonlinear ELMs (or Kernel ELMs) are the improvement of linear ELM (LELM). However, based on lots of experiments and analysis, we found out that the LELM is a better choice than nonlinear ELM for spectral-spatial classification of HSI. Furthermore, we exploit the marginal probability distribution that uses the whole information in the HSI and learn such distribution using the LBP. The proposed method not only maintain the fast speed of ELM, but also greatly improves the accuracy of classification. The experimental results in the well-known HSI data sets, Indian Pines and Pavia University, demonstrate the good performances of the proposed method.
Tasks
Published	2017-09-05
URL	http://arxiv.org/abs/1709.02253v2
PDF	http://arxiv.org/pdf/1709.02253v2.pdf
PWC	https://paperswithcode.com/paper/linear-vs-nonlinear-extreme-learning-machine
Repo
Framework

On the Statistical Efficiency of Compositional Nonparametric Prediction


Title	On the Statistical Efficiency of Compositional Nonparametric Prediction
Authors	Yixi Xu, Jean Honorio, Xiao Wang
Abstract	In this paper, we propose a compositional nonparametric method in which a model is expressed as a labeled binary tree of $2k+1$ nodes, where each node is either a summation, a multiplication, or the application of one of the $q$ basis functions to one of the $p$ covariates. We show that in order to recover a labeled binary tree from a given dataset, the sufficient number of samples is $O(k\log(pq)+\log(k!))$, and the necessary number of samples is $\Omega(k\log (pq)-\log(k!))$. We further propose a greedy algorithm for regression in order to validate our theoretical findings through synthetic experiments.
Tasks
Published	2017-04-06
URL	http://arxiv.org/abs/1704.01896v4
PDF	http://arxiv.org/pdf/1704.01896v4.pdf
PWC	https://paperswithcode.com/paper/on-the-statistical-efficiency-of
Repo
Framework

SAR Image Despeckling Using a Convolutional Neural Network


Title	SAR Image Despeckling Using a Convolutional Neural Network
Authors	Puyang Wang, He Zhang, Vishal M. Patel
Abstract	Synthetic Aperture Radar (SAR) images are often contaminated by a multiplicative noise known as speckle. Speckle makes the processing and interpretation of SAR images difficult. We propose a deep learning-based approach called, Image Despeckling Convolutional Neural Network (ID-CNN), for automatically removing speckle from the input noisy images. In particular, ID-CNN uses a set of convolutional layers along with batch normalization and rectified linear unit (ReLU) activation function and a component-wise division residual layer to estimate speckle and it is trained in an end-to-end fashion using a combination of Euclidean loss and Total Variation (TV) loss. Extensive experiments on synthetic and real SAR images show that the proposed method achieves significant improvements over the state-of-the-art speckle reduction methods.
Tasks	Sar Image Despeckling
Published	2017-06-02
URL	http://arxiv.org/abs/1706.00552v2
PDF	http://arxiv.org/pdf/1706.00552v2.pdf
PWC	https://paperswithcode.com/paper/sar-image-despeckling-using-a-convolutional
Repo
Framework

Learning Deeply Supervised Good Features to Match for Dense Monocular Reconstruction


Title	Learning Deeply Supervised Good Features to Match for Dense Monocular Reconstruction
Authors	Chamara Saroj Weerasekera, Ravi Garg, Yasir Latif, Ian Reid
Abstract	Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images. These features, while suitable for sparse mapping, often lead to ambiguous matches in texture-less regions when performing dense reconstruction due to the aperture problem. In this work, we explore the use of learned features for the matching task in dense monocular reconstruction. We propose a novel convolutional neural network (CNN) architecture along with a deeply supervised feature learning scheme for pixel-wise regression of visual descriptors from an image which are best suited for dense monocular SLAM. In particular, our learning scheme minimizes a multi-view matching cost-volume loss with respect to the regressed features at multiple stages within the network, for explicitly learning contextual features that are suitable for dense matching between images captured by a moving monocular camera along the epipolar line. We integrate the learned features from our model for depth estimation inside a real-time dense monocular SLAM framework, where photometric error is replaced by our learned descriptor error. Our extensive evaluation on several challenging indoor datasets demonstrate greatly improved accuracy in dense reconstructions of the well celebrated dense SLAM systems like DTAM, without compromising their real-time performance.
Tasks	Depth Estimation, Simultaneous Localization and Mapping
Published	2017-11-16
URL	http://arxiv.org/abs/1711.05919v2
PDF	http://arxiv.org/pdf/1711.05919v2.pdf
PWC	https://paperswithcode.com/paper/learning-deeply-supervised-good-features-to
Repo
Framework

Realizing an optimization approach inspired from Piagets theory on cognitive development


Title	Realizing an optimization approach inspired from Piagets theory on cognitive development
Authors	Utku Kose, Ahmet Arslan
Abstract	The objective of this paper is to introduce an artificial intelligence based optimization approach, which is inspired from Piagets theory on cognitive development. The approach has been designed according to essential processes that an individual may experience while learning something new or improving his / her knowledge. These processes are associated with the Piagets ideas on an individuals cognitive development. The approach expressed in this paper is a simple algorithm employing swarm intelligence oriented tasks in order to overcome single-objective optimization problems. For evaluating effectiveness of this early version of the algorithm, test operations have been done via some benchmark functions. The obtained results show that the approach / algorithm can be an alternative to the literature in terms of single-objective optimization. The authors have suggested the name: Cognitive Development Optimization Algorithm (CoDOA) for the related intelligent optimization approach.
Tasks
Published	2017-04-03
URL	http://arxiv.org/abs/1704.05904v1
PDF	http://arxiv.org/pdf/1704.05904v1.pdf
PWC	https://paperswithcode.com/paper/realizing-an-optimization-approach-inspired
Repo
Framework

Fast Approximate Spectral Clustering for Dynamic Networks


Title	Fast Approximate Spectral Clustering for Dynamic Networks
Authors	Lionel Martin, Andreas Loukas, Pierre Vandergheynst
Abstract	Spectral clustering is a widely studied problem, yet its complexity is prohibitive for dynamic graphs of even modest size. We claim that it is possible to reuse information of past cluster assignments to expedite computation. Our approach builds on a recent idea of sidestepping the main bottleneck of spectral clustering, i.e., computing the graph eigenvectors, by using fast Chebyshev graph filtering of random signals. We show that the proposed algorithm achieves clustering assignments with quality approximating that of spectral clustering and that it can yield significant complexity benefits when the graph dynamics are appropriately bounded.
Tasks
Published	2017-06-12
URL	http://arxiv.org/abs/1706.03591v1
PDF	http://arxiv.org/pdf/1706.03591v1.pdf
PWC	https://paperswithcode.com/paper/fast-approximate-spectral-clustering-for
Repo
Framework

Defense against Universal Adversarial Perturbations


Title	Defense against Universal Adversarial Perturbations
Authors	Naveed Akhtar, Jian Liu, Ajmal Mian
Abstract	Recent advances in Deep Learning show the existence of image-agnostic quasi-imperceptible perturbations that when applied to `any' image can fool a state-of-the-art network classifier to change its prediction about the image label. These` Universal Adversarial Perturbations’ pose a serious threat to the success of Deep Learning in practice. We present the first dedicated framework to effectively defend the networks against such perturbations. Our approach learns a Perturbation Rectifying Network (PRN) as `pre-input’ layers to a targeted model, such that the targeted model needs no modification. The PRN is learned from real and synthetic image-agnostic perturbations, where an efficient method to compute the latter is also proposed. A perturbation detector is separately trained on the Discrete Cosine Transform of the input-output difference of the PRN. A query image is first passed through the PRN and verified by the detector. If a perturbation is detected, the output of the PRN is used for label prediction instead of the actual image. A rigorous evaluation shows that our framework can defend the network classifiers against unseen adversarial perturbations in the real-world scenarios with up to 97.5% success rate. The PRN also generalizes well in the sense that training for one targeted network defends another network with a comparable success rate. \|
Tasks
Published	2017-11-16
URL	http://arxiv.org/abs/1711.05929v3
PDF	http://arxiv.org/pdf/1711.05929v3.pdf
PWC	https://paperswithcode.com/paper/defense-against-universal-adversarial
Repo
Framework

Evidential supplier selection based on interval data fusion


Title	Evidential supplier selection based on interval data fusion
Authors	Zichang He, Wen Jiang
Abstract	Supplier selection is a typical multi-criteria decision making (MCDM) problem and lots of uncertain information exist inevitably. To address this issue, a new method was proposed based on interval data fusion. Our method follows the original way to generate classical basic probability assignment(BPA) determined by the distance among the evidences. However, the weights of criteria are kept as interval numbers to generate interval BPAs and do the fusion of interval BPAs. Finally, the order is ranked and the decision is made according to the obtained interval BPAs. In this paper, a numerical example of supplier selection is applied to verify the feasibility and validity of our method. The new method is presented aiming at solving multiple-criteria decision-making problems in which the weights of criteria or experts are described in fuzzy data like linguistic terms or interval data.
Tasks	Decision Making
Published	2017-03-06
URL	http://arxiv.org/abs/1703.01971v1
PDF	http://arxiv.org/pdf/1703.01971v1.pdf
PWC	https://paperswithcode.com/paper/evidential-supplier-selection-based-on
Repo
Framework

Deriving Verb Predicates By Clustering Verbs with Arguments


Title	Deriving Verb Predicates By Clustering Verbs with Arguments
Authors	Joao Sedoc, Derry Wijaya, Masoud Rouhizadeh, Andy Schwartz, Lyle Ungar
Abstract	Hand-built verb clusters such as the widely used Levin classes (Levin, 1993) have proved useful, but have limited coverage. Verb classes automatically induced from corpus data such as those from VerbKB (Wijaya, 2016), on the other hand, can give clusters with much larger coverage, and can be adapted to specific corpora such as Twitter. We present a method for clustering the outputs of VerbKB: verbs with their multiple argument types, e.g. “marry(person, person)", “feel(person, emotion).” We make use of a novel low-dimensional embedding of verbs and their arguments to produce high quality clusters in which the same verb can be in different clusters depending on its argument type. The resulting verb clusters do a better job than hand-built clusters of predicting sarcasm, sentiment, and locus of control in tweets.
Tasks
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00416v1
PDF	http://arxiv.org/pdf/1708.00416v1.pdf
PWC	https://paperswithcode.com/paper/deriving-verb-predicates-by-clustering-verbs
Repo
Framework

An Image Analysis Approach to the Calligraphy of Books


Title	An Image Analysis Approach to the Calligraphy of Books
Authors	Henrique F. de Arruda, Vanessa Q. Marinho, Thales S. Lima, Diego R. Amancio, Luciano da F. Costa
Abstract	Text network analysis has received increasing attention as a consequence of its wide range of applications. In this work, we extend a previous work founded on the study of topological features of mesoscopic networks. Here, the geometrical properties of visualized networks are quantified in terms of several image analysis techniques and used as subsidies for authorship attribution. It was found that the visual features account for performance similar to that achieved by using topological measurements. In addition, the combination of these two types of features improved the performance.
Tasks
Published	2017-08-24
URL	http://arxiv.org/abs/1708.07265v1
PDF	http://arxiv.org/pdf/1708.07265v1.pdf
PWC	https://paperswithcode.com/paper/an-image-analysis-approach-to-the-calligraphy
Repo
Framework