July 28, 2019

2948 words 14 mins read

Paper Group ANR 406

Deep Learning for Tumor Classification in Imaging Mass Spectrometry. Random Forests and VGG-NET: An Algorithm for the ISIC 2017 Skin Lesion Classification Challenge. Learned Multi-Patch Similarity. Detecting Cross-Lingual Plagiarism Using Simulated Word Embeddings. Araguaia Medical Vision Lab at ISIC 2017 Skin Lesion Classification Challenge. Time …

Deep Learning for Tumor Classification in Imaging Mass Spectrometry


Title	Deep Learning for Tumor Classification in Imaging Mass Spectrometry
Authors	Jens Behrmann, Christian Etmann, Tobias Boskamp, Rita Casadonte, Jörg Kriegsmann, Peter Maass
Abstract	Motivation: Tumor classification using Imaging Mass Spectrometry (IMS) data has a high potential for future applications in pathology. Due to the complexity and size of the data, automated feature extraction and classification steps are required to fully process the data. Deep learning offers an approach to learn feature extraction and classification combined in a single model. Commonly these steps are handled separately in IMS data analysis, hence deep learning offers an alternative strategy worthwhile to explore. Results: Methodologically, we propose an adapted architecture based on deep convolutional networks to handle the characteristics of mass spectrometry data, as well as a strategy to interpret the learned model in the spectral domain based on a sensitivity analysis. The proposed methods are evaluated on two challenging tumor classification tasks and compared to a baseline approach. Competitiveness of the proposed methods are shown on both tasks by studying the performance via cross-validation. Moreover, the learned models are analyzed by the proposed sensitivity analysis revealing biologically plausible effects as well as confounding factors of the considered task. Thus, this study may serve as a starting point for further development of deep learning approaches in IMS classification tasks.
Tasks
Published	2017-05-02
URL	http://arxiv.org/abs/1705.01015v3
PDF	http://arxiv.org/pdf/1705.01015v3.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-tumor-classification-in
Repo
Framework

Random Forests and VGG-NET: An Algorithm for the ISIC 2017 Skin Lesion Classification Challenge


Title	Random Forests and VGG-NET: An Algorithm for the ISIC 2017 Skin Lesion Classification Challenge
Authors	Songtao Guo, Yixin Luo, Yanzhi Song
Abstract	This manuscript briefly describes an algorithm developed for the ISIC 2017 Skin Lesion Classification Competition. In this task, participants are asked to complete two independent binary image classification tasks that involve three unique diagnoses of skin lesions (melanoma, nevus, and seborrheic keratosis). In the first binary classification task, participants are asked to distinguish between (a) melanoma and (b) nevus and seborrheic keratosis. In the second binary classification task, participants are asked to distinguish between (a) seborrheic keratosis and (b) nevus and melanoma. The other phases of the competition are not considered. Our proposed algorithm consists of three steps: preprocessing, classification using VGG-NET and Random Forests, and calculation of a final score.
Tasks	Image Classification, Skin Lesion Classification
Published	2017-03-15
URL	http://arxiv.org/abs/1703.05148v1
PDF	http://arxiv.org/pdf/1703.05148v1.pdf
PWC	https://paperswithcode.com/paper/random-forests-and-vgg-net-an-algorithm-for
Repo
Framework

Learned Multi-Patch Similarity


Title	Learned Multi-Patch Similarity
Authors	Wilfried Hartmann, Silvano Galliani, Michal Havlena, Luc Van Gool, Konrad Schindler
Abstract	Estimating a depth map from multiple views of a scene is a fundamental task in computer vision. As soon as more than two viewpoints are available, one faces the very basic question how to measure similarity across >2 image patches. Surprisingly, no direct solution exists, instead it is common to fall back to more or less robust averaging of two-view similarities. Encouraged by the success of machine learning, and in particular convolutional neural networks, we propose to learn a matching function which directly maps multiple image patches to a scalar similarity score. Experiments on several multi-view datasets demonstrate that this approach has advantages over methods based on pairwise patch similarity.
Tasks
Published	2017-03-26
URL	http://arxiv.org/abs/1703.08836v2
PDF	http://arxiv.org/pdf/1703.08836v2.pdf
PWC	https://paperswithcode.com/paper/learned-multi-patch-similarity
Repo
Framework

Detecting Cross-Lingual Plagiarism Using Simulated Word Embeddings


Title	Detecting Cross-Lingual Plagiarism Using Simulated Word Embeddings
Authors	Victor Thompson
Abstract	Cross-lingual plagiarism (CLP) occurs when texts written in one language are translated into a different language and used without acknowledging the original sources. One of the most common methods for detecting CLP requires online machine translators (such as Google or Microsoft translate) which are not always available, and given that plagiarism detection typically involves large document comparison, the amount of translations required would overwhelm an online machine translator, especially when detecting plagiarism over the web. In addition, when translated texts are replaced with their synonyms, using online machine translators to detect CLP would result in poor performance. This paper addresses the problem of cross-lingual plagiarism detection (CLPD) by proposing a model that uses simulated word embeddings to reproduce the predictions of an online machine translator (Google translate) when detecting CLP. The simulated embeddings comprise of translated words in different languages mapped in a common space, and replicated to increase the prediction probability of retrieving the translations of a word (and their synonyms) from the model. Unlike most existing models, the proposed model does not require parallel corpora, and accommodates multiple languages (multi-lingual). We demonstrated the effectiveness of the proposed model in detecting CLP in standard datasets that contain CLP cases, and evaluated its performance against a state-of-the-art baseline that relies on online machine translator (T+MA model). Evaluation results revealed that the proposed model is not only effective in detecting CLP, it outperformed the baseline. The results indicate that CLP could be detected with state-of-the-art performances by leveraging the prediction accuracy of an internet translator with word embeddings, without relying on internet translators.
Tasks	Word Embeddings
Published	2017-12-29
URL	http://arxiv.org/abs/1712.10190v2
PDF	http://arxiv.org/pdf/1712.10190v2.pdf
PWC	https://paperswithcode.com/paper/detecting-cross-lingual-plagiarism-using
Repo
Framework

Araguaia Medical Vision Lab at ISIC 2017 Skin Lesion Classification Challenge


Title	Araguaia Medical Vision Lab at ISIC 2017 Skin Lesion Classification Challenge
Authors	Rafael Teixeira Sousa, Larissa Vasconcellos de Moraes
Abstract	This paper describes the participation of Araguaia Medical Vision Lab at the International Skin Imaging Collaboration 2017 Skin Lesion Challenge. We describe the use of deep convolutional neural networks in attempt to classify images of Melanoma and Seborrheic Keratosis lesions. With use of finetuned GoogleNet and AlexNet we attained results of 0.950 and 0.846 AUC on Seborrheic Keratosis and Melanoma respectively.
Tasks	Skin Lesion Classification
Published	2017-03-02
URL	http://arxiv.org/abs/1703.00856v1
PDF	http://arxiv.org/pdf/1703.00856v1.pdf
PWC	https://paperswithcode.com/paper/araguaia-medical-vision-lab-at-isic-2017-skin
Repo
Framework

Time Stretch Inspired Computational Imaging


Title	Time Stretch Inspired Computational Imaging
Authors	Bahram Jalali, Madhuri Suthar, Mohamad Asghari, Ata Mahjoubfar
Abstract	We show that dispersive propagation of light followed by phase detection has properties that can be exploited for extracting features from the waveforms. This discovery is spearheading development of a new class of physics-inspired algorithms for feature extraction from digital images with unique properties and superior dynamic range compared to conventional algorithms. In certain cases, these algorithms have the potential to be an energy efficient and scalable substitute to synthetically fashioned computational techniques in practice today.
Tasks
Published	2017-06-07
URL	http://arxiv.org/abs/1706.07841v1
PDF	http://arxiv.org/pdf/1706.07841v1.pdf
PWC	https://paperswithcode.com/paper/time-stretch-inspired-computational-imaging
Repo
Framework

How regularization affects the critical points in linear networks


Title	How regularization affects the critical points in linear networks
Authors	Amirhossein Taghvaei, Jin W. Kim, Prashant G. Mehta
Abstract	This paper is concerned with the problem of representing and learning a linear transformation using a linear neural network. In recent years, there has been a growing interest in the study of such networks in part due to the successes of deep learning. The main question of this body of research and also of this paper pertains to the existence and optimality properties of the critical points of the mean-squared loss function. The primary concern here is the robustness of the critical points with regularization of the loss function. An optimal control model is introduced for this purpose and a learning algorithm (regularized form of backprop) derived for the same using the Hamilton’s formulation of optimal control. The formulation is used to provide a complete characterization of the critical points in terms of the solutions of a nonlinear matrix-valued equation, referred to as the characteristic equation. Analytical and numerical tools from bifurcation theory are used to compute the critical points via the solutions of the characteristic equation. The main conclusion is that the critical point diagram can be fundamentally different even with arbitrary small amounts of regularization.
Tasks
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09625v1
PDF	http://arxiv.org/pdf/1709.09625v1.pdf
PWC	https://paperswithcode.com/paper/how-regularization-affects-the-critical
Repo
Framework

A Study on Neural Network Language Modeling


Title	A Study on Neural Network Language Modeling
Authors	Dengliang Shi
Abstract	An exhaustive study on neural network language modeling (NNLM) is performed in this paper. Different architectures of basic neural network language models are described and examined. A number of different improvements over basic neural network language models, including importance sampling, word classes, caching and bidirectional recurrent neural network (BiRNN), are studied separately, and the advantages and disadvantages of every technique are evaluated. Then, the limits of neural network language modeling are explored from the aspects of model architecture and knowledge representation. Part of the statistical information from a word sequence will loss when it is processed word by word in a certain order, and the mechanism of training neural network by updating weight matrixes and vectors imposes severe restrictions on any significant enhancement of NNLM. For knowledge representation, the knowledge represented by neural network language models is the approximate probabilistic distribution of word sequences from a certain training data set rather than the knowledge of a language itself or the information conveyed by word sequences in a natural language. Finally, some directions for improving neural network language modeling further is discussed.
Tasks	Language Modelling
Published	2017-08-24
URL	http://arxiv.org/abs/1708.07252v1
PDF	http://arxiv.org/pdf/1708.07252v1.pdf
PWC	https://paperswithcode.com/paper/a-study-on-neural-network-language-modeling
Repo
Framework

Cooperating with Machines


Title	Cooperating with Machines
Authors	Jacob W. Crandall, Mayada Oudah, Tennom, Fatimah Ishowo-Oloko, Sherief Abdallah, Jean-François Bonnefon, Manuel Cebrian, Azim Shariff, Michael A. Goodrich, Iyad Rahwan
Abstract	Since Alan Turing envisioned Artificial Intelligence (AI) [1], a major driving force behind technical progress has been competition with human cognition. Historical milestones have been frequently associated with computers matching or outperforming humans in difficult cognitive tasks (e.g. face recognition [2], personality classification [3], driving cars [4], or playing video games [5]), or defeating humans in strategic zero-sum encounters (e.g. Chess [6], Checkers [7], Jeopardy! [8], Poker [9], or Go [10]). In contrast, less attention has been given to developing autonomous machines that establish mutually cooperative relationships with people who may not share the machine’s preferences. A main challenge has been that human cooperation does not require sheer computational power, but rather relies on intuition [11], cultural norms [12], emotions and signals [13, 14, 15, 16], and pre-evolved dispositions toward cooperation [17], common-sense mechanisms that are difficult to encode in machines for arbitrary contexts. Here, we combine a state-of-the-art machine-learning algorithm with novel mechanisms for generating and acting on signals to produce a new learning algorithm that cooperates with people and other machines at levels that rival human cooperation in a variety of two-player repeated stochastic games. This is the first general-purpose algorithm that is capable, given a description of a previously unseen game environment, of learning to cooperate with people within short timescales in scenarios previously unanticipated by algorithm designers. This is achieved without complex opponent modeling or higher-order theories of mind, thus showing that flexible, fast, and general human-machine cooperation is computationally achievable using a non-trivial, but ultimately simple, set of algorithmic mechanisms.
Tasks	Common Sense Reasoning, Face Recognition
Published	2017-03-17
URL	http://arxiv.org/abs/1703.06207v5
PDF	http://arxiv.org/pdf/1703.06207v5.pdf
PWC	https://paperswithcode.com/paper/cooperating-with-machines
Repo
Framework

Learning a Neural Semantic Parser from User Feedback


Title	Learning a Neural Semantic Parser from User Feedback
Authors	Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, Jayant Krishnamurthy, Luke Zettlemoyer
Abstract	We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal intervention. To achieve this, we adapt neural sequence models to map utterances directly to SQL with its full expressivity, bypassing any intermediate meaning representations. These models are immediately deployed online to solicit feedback from real users to flag incorrect queries. Finally, the popularity of SQL facilitates gathering annotations for incorrect predictions using the crowd, which is directly used to improve our models. This complete feedback loop, without intermediate representations or database specific engineering, opens up new ways of building high quality semantic parsers. Experiments suggest that this approach can be deployed quickly for any new target domain, as we show by learning a semantic parser for an online academic database from scratch.
Tasks
Published	2017-04-27
URL	http://arxiv.org/abs/1704.08760v1
PDF	http://arxiv.org/pdf/1704.08760v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-neural-semantic-parser-from-user
Repo
Framework

Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation


Title	Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation
Authors	Omid Hosseini Jafari, Oliver Groth, Alexander Kirillov, Michael Ying Yang, Carsten Rother
Abstract	This paper addresses the task of designing a modular neural network architecture that jointly solves different tasks. As an example we use the tasks of depth estimation and semantic segmentation given a single RGB image. The main focus of this work is to analyze the cross-modality influence between depth and semantic prediction maps on their joint refinement. While most previous works solely focus on measuring improvements in accuracy, we propose a way to quantify the cross-modality influence. We show that there is a relationship between final accuracy and cross-modality influence, although not a simple linear one. Hence a larger cross-modality influence does not necessarily translate into an improved accuracy. We find that a beneficial balance between the cross-modality influences can be achieved by network architecture and conjecture that this relationship can be utilized to understand different network design choices. Towards this end we propose a Convolutional Neural Network (CNN) architecture that fuses the state of the state-of-the-art results for depth estimation and semantic labeling. By balancing the cross-modality influences between depth and semantic prediction, we achieve improved results for both tasks using the NYU-Depth v2 benchmark.
Tasks	Depth Estimation, Semantic Segmentation
Published	2017-02-26
URL	http://arxiv.org/abs/1702.08009v1
PDF	http://arxiv.org/pdf/1702.08009v1.pdf
PWC	https://paperswithcode.com/paper/analyzing-modular-cnn-architectures-for-joint
Repo
Framework

Concurrent Segmentation and Localization for Tracking of Surgical Instruments


Title	Concurrent Segmentation and Localization for Tracking of Surgical Instruments
Authors	Iro Laina, Nicola Rieke, Christian Rupprecht, Josué Page Vizcaíno, Abouzar Eslami, Federico Tombari, Nassir Navab
Abstract	Real-time instrument tracking is a crucial requirement for various computer-assisted interventions. In order to overcome problems such as specular reflections and motion blur, we propose a novel method that takes advantage of the interdependency between localization and segmentation of the surgical tool. In particular, we reformulate the 2D instrument pose estimation as heatmap regression and thereby enable a concurrent, robust and near real-time regression of both tasks via deep learning. As demonstrated by our experimental results, this modeling leads to a significantly improved performance than directly regressing the tool position and allows our method to outperform the state of the art on a Retinal Microsurgery benchmark and the MICCAI EndoVis Challenge 2015.
Tasks	Pose Estimation
Published	2017-03-30
URL	http://arxiv.org/abs/1703.10701v2
PDF	http://arxiv.org/pdf/1703.10701v2.pdf
PWC	https://paperswithcode.com/paper/concurrent-segmentation-and-localization-for
Repo
Framework

Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks


Title	Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks
Authors	Hui Li, Peng Wang, Chunhua Shen
Abstract	In this work, we tackle the problem of car license plate detection and recognition in natural scene images. We propose a unified deep neural network which can localize license plates and recognize the letters simultaneously in a single forward pass. The whole network can be trained end-to-end. In contrast to existing approaches which take license plate detection and recognition as two separate tasks and settle them step by step, our method jointly solves these two tasks by a single network. It not only avoids intermediate error accumulation, but also accelerates the processing speed. For performance evaluation, three datasets including images captured from various scenes under different conditions are tested. Extensive experiments show the effectiveness and efficiency of our proposed approach.
Tasks
Published	2017-09-26
URL	http://arxiv.org/abs/1709.08828v1
PDF	http://arxiv.org/pdf/1709.08828v1.pdf
PWC	https://paperswithcode.com/paper/towards-end-to-end-car-license-plates
Repo
Framework

What do Neural Machine Translation Models Learn about Morphology?


Title	What do Neural Machine Translation Models Learn about Morphology?
Authors	Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, Hassan Sajjad, James Glass
Abstract	Neural machine translation (MT) models obtain state-of-the-art performance while maintaining a simple, end-to-end architecture. However, little is known about what these models learn about source and target languages during the training process. In this work, we analyze the representations learned by neural MT models at various levels of granularity and empirically evaluate the quality of the representations for learning morphology through extrinsic part-of-speech and morphological tagging tasks. We conduct a thorough investigation along several parameters: word-based vs. character-based representations, depth of the encoding layer, the identity of the target language, and encoder vs. decoder representations. Our data-driven, quantitative evaluation sheds light on important aspects in the neural MT system and its ability to capture word structure.
Tasks	Machine Translation, Morphological Tagging
Published	2017-04-11
URL	http://arxiv.org/abs/1704.03471v3
PDF	http://arxiv.org/pdf/1704.03471v3.pdf
PWC	https://paperswithcode.com/paper/what-do-neural-machine-translation-models
Repo
Framework

Improved Fixed-Rank Nyström Approximation via QR Decomposition: Practical and Theoretical Aspects


Title	Improved Fixed-Rank Nyström Approximation via QR Decomposition: Practical and Theoretical Aspects
Authors	Farhad Pourkamali-Anaraki, Stephen Becker
Abstract	The Nystrom method is a popular technique that uses a small number of landmark points to compute a fixed-rank approximation of large kernel matrices that arise in machine learning problems. In practice, to ensure high quality approximations, the number of landmark points is chosen to be greater than the target rank. However, for simplicity the standard Nystrom method uses a sub-optimal procedure for rank reduction. In this paper, we examine the drawbacks of the standard Nystrom method in terms of poor performance and lack of theoretical guarantees. To address these issues, we present an efficient modification for generating improved fixed-rank Nystrom approximations. Theoretical analysis and numerical experiments are provided to demonstrate the advantages of the modified method over the standard Nystrom method. Overall, the aim of this paper is to convince researchers to use the modified method, as it has nearly identical computational complexity, is easy to code, has greatly improved accuracy in many cases, and is optimal in a sense that we make precise.
Tasks
Published	2017-08-08
URL	https://arxiv.org/abs/1708.03218v2
PDF	https://arxiv.org/pdf/1708.03218v2.pdf
PWC	https://paperswithcode.com/paper/improved-fixed-rank-nystrom-approximation-via
Repo
Framework