October 18, 2019

2717 words 13 mins read

Paper Group ANR 440

Paper Group ANR 440

PoTrojan: powerful neural-level trojan designs in deep learning models. Deep LOGISMOS: Deep Learning Graph-based 3D Segmentation of Pancreatic Tumors on CT scans. Ensemble of Learning Project Productivity in Software Effort Based on Use Case Points. AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects. Delta Embe …

PoTrojan: powerful neural-level trojan designs in deep learning models

Title PoTrojan: powerful neural-level trojan designs in deep learning models
Authors Minhui Zou, Yang Shi, Chengliang Wang, Fangyu Li, WenZhan Song, Yu Wang
Abstract With the popularity of deep learning (DL), artificial intelligence (AI) has been applied in many areas of human life. Neural network or artificial neural network (NN), the main technique behind DL, has been extensively studied to facilitate computer vision and natural language recognition. However, the more we rely on information technology, the more vulnerable we are. That is, malicious NNs could bring huge threat in the so-called coming AI era. In this paper, for the first time in the literature, we propose a novel approach to design and insert powerful neural-level trojans or PoTrojan in pre-trained NN models. Most of the time, PoTrojans remain inactive, not affecting the normal functions of their host NN models. PoTrojans could only be triggered in very rare conditions. Once activated, however, the PoTrojans could cause the host NN models to malfunction, either falsely predicting or classifying, which is a significant threat to human society of the AI era. We would explain the principles of PoTrojans and the easiness of designing and inserting them in pre-trained deep learning models. PoTrojans doesn’t modify the existing architecture or parameters of the pre-trained models, without re-training. Hence, the proposed method is very efficient.
Tasks
Published 2018-02-08
URL https://arxiv.org/abs/1802.03043v2
PDF https://arxiv.org/pdf/1802.03043v2.pdf
PWC https://paperswithcode.com/paper/potrojan-powerful-neural-level-trojan-designs
Repo
Framework

Deep LOGISMOS: Deep Learning Graph-based 3D Segmentation of Pancreatic Tumors on CT scans

Title Deep LOGISMOS: Deep Learning Graph-based 3D Segmentation of Pancreatic Tumors on CT scans
Authors Zhihui Guo, Ling Zhang, Le Lu, Mohammadhadi Bagheri, Ronald M. Summers, Milan Sonka, Jianhua Yao
Abstract This paper reports Deep LOGISMOS approach to 3D tumor segmentation by incorporating boundary information derived from deep contextual learning to LOGISMOS - layered optimal graph image segmentation of multiple objects and surfaces. Accurate and reliable tumor segmentation is essential to tumor growth analysis and treatment selection. A fully convolutional network (FCN), UNet, is first trained using three adjacent 2D patches centered at the tumor, providing contextual UNet segmentation and probability map for each 2D patch. The UNet segmentation is then refined by Gaussian Mixture Model (GMM) and morphological operations. The refined UNet segmentation is used to provide the initial shape boundary to build a segmentation graph. The cost for each node of the graph is determined by the UNet probability maps. Finally, a max-flow algorithm is employed to find the globally optimal solution thus obtaining the final segmentation. For evaluation, we applied the method to pancreatic tumor segmentation on a dataset of 51 CT scans, among which 30 scans were used for training and 21 for testing. With Deep LOGISMOS, DICE Similarity Coefficient (DSC) and Relative Volume Difference (RVD) reached 83.2+-7.8% and 18.6+-17.4% respectively, both are significantly improved (p<0.05) compared with contextual UNet and/or LOGISMOS alone.
Tasks Semantic Segmentation
Published 2018-01-25
URL http://arxiv.org/abs/1801.08599v1
PDF http://arxiv.org/pdf/1801.08599v1.pdf
PWC https://paperswithcode.com/paper/deep-logismos-deep-learning-graph-based-3d
Repo
Framework

Ensemble of Learning Project Productivity in Software Effort Based on Use Case Points

Title Ensemble of Learning Project Productivity in Software Effort Based on Use Case Points
Authors Mohammad Azzeh, Ali Bou Nassif, Shadi Banitaan, Cuauhtemoc Lopez-Martin
Abstract It is well recognized that the project productivity is a key driver in estimating software project effort from Use Case Point size metric at early software development stages. Although, there are few proposed models for predicting productivity, there is no consistent conclusion regarding which model is the superior. Therefore, instead of building a new productivity prediction model, this paper presents a new ensemble construction mechanism applied for software project productivity prediction. Ensemble is an effective technique when performance of base models is poor. We proposed a weighted mean method to aggregate predicted productivities based on average of errors produced by training model. The obtained results show that the using ensemble is a good alternative approach when accuracies of base models are not consistently accurate over different datasets, and when models behave diversely.
Tasks
Published 2018-12-16
URL http://arxiv.org/abs/1812.06459v1
PDF http://arxiv.org/pdf/1812.06459v1.pdf
PWC https://paperswithcode.com/paper/ensemble-of-learning-project-productivity-in
Repo
Framework

AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects

Title AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects
Authors Christian Wilms, Simone Frintrop
Abstract We propose a novel approach for class-agnostic object proposal generation, which is efficient and especially well-suited to detect small objects. Efficiency is achieved by scale-specific objectness attention maps which focus the processing on promising parts of the image and reduce the amount of sampled windows strongly. This leads to a system, which is $33%$ faster than the state-of-the-art and clearly outperforming state-of-the-art in terms of average recall. Secondly, we add a module for detecting small objects, which are often missed by recent models. We show that this module improves the average recall for small objects by about $53%$.
Tasks Object Proposal Generation
Published 2018-11-21
URL http://arxiv.org/abs/1811.08728v1
PDF http://arxiv.org/pdf/1811.08728v1.pdf
PWC https://paperswithcode.com/paper/attentionmask-attentive-efficient-object
Repo
Framework

Delta Embedding Learning

Title Delta Embedding Learning
Authors Xiao Zhang, Ji Wu, Dejing Dou
Abstract Unsupervised word embeddings have become a popular approach of word representation in NLP tasks. However there are limitations to the semantics represented by unsupervised embeddings, and inadequate fine-tuning of embeddings can lead to suboptimal performance. We propose a novel learning technique called Delta Embedding Learning, which can be applied to general NLP tasks to improve performance by optimized tuning of the word embeddings. A structured regularization is applied to the embeddings to ensure they are tuned in an incremental way. As a result, the tuned word embeddings become better word representations by absorbing semantic information from supervision without “forgetting.” We apply the method to various NLP tasks and see a consistent improvement in performance. Evaluation also confirms the tuned word embeddings have better semantic properties.
Tasks Reading Comprehension, Word Embeddings
Published 2018-12-11
URL https://arxiv.org/abs/1812.04160v2
PDF https://arxiv.org/pdf/1812.04160v2.pdf
PWC https://paperswithcode.com/paper/delta-embedding-learning
Repo
Framework

ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion

Title ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion
Authors Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo
Abstract This paper proposes a voice conversion method based on fully convolutional sequence-to-sequence (seq2seq) learning. The present method, which we call “ConvS2S-VC”, learns the mapping between source and target speech feature sequences using a fully convolutional seq2seq model with an attention mechanism. Owing to the nature of seq2seq learning, our method is particularly noteworthy in that it allows the flexible conversion of not only the voice characteristics but also the pitch contour and duration of the input speech. The current model consists of six networks, namely source and target encoders, a target decoder, source and target reconstructors and a postnet, which are designed using dilated causal convolution networks with gated linear units. Subjective evaluation experiments revealed that the proposed method obtained higher sound quality and speaker similarity than a baseline method.
Tasks Voice Conversion
Published 2018-11-05
URL http://arxiv.org/abs/1811.01609v2
PDF http://arxiv.org/pdf/1811.01609v2.pdf
PWC https://paperswithcode.com/paper/convs2s-vc-fully-convolutional-sequence-to
Repo
Framework

New Ideas for Brain Modelling 5

Title New Ideas for Brain Modelling 5
Authors Kieran Greer
Abstract This paper describes an automatic process for combining patterns and features, to guide a search process and make predictions. It is based on the functionality that a human brain might have, which is a highly distributed network of simple neuronal components that can apply some level of matching and cross-referencing over retrieved patterns. The process uses memory in a dynamic way and it is directed through the pattern matching. The first half of the paper describes the mechanisms for neuronal search, memory and prediction. The second half of the paper then presents a formal language for defining cognitive processes, that is, pattern-based sequences and transitions. The language can define an outer framework for nested pattern sets that can be linked to perform the cognitive act. The language also has a mathematical basis, allowing for the rule construction process to be systematic and consistent. The new information can be used to integrate the cognitive model together. A theory about linking can suggest that only (mostly) nodes that represent the same thing link together.
Tasks
Published 2018-03-05
URL https://arxiv.org/abs/1803.01690v9
PDF https://arxiv.org/pdf/1803.01690v9.pdf
PWC https://paperswithcode.com/paper/new-ideas-for-brain-modelling-5
Repo
Framework

Primal path algorithm for compositional data analysis

Title Primal path algorithm for compositional data analysis
Authors Jong-June Jeon, Yongdai Kim, Sungho Won, Hosik Choi
Abstract Compositional data have two unique characteristics compared to typical multivariate data: the observed values are nonnegative and their summand is exactly one. To reflect these characteristics, a specific regularized regression model with linear constraints is commonly used. However, linear constraints incur additional computational time, which becomes severe in high-dimensional cases. As such, we propose an efficient solution path algorithm for a $l_1$ regularized regression with compositional data. The algorithm is then extended to a classification model with compositional predictors. We also compare its computational speed with that of previously developed algorithms and apply the proposed algorithm to analyze human gut microbiome data.
Tasks
Published 2018-12-21
URL http://arxiv.org/abs/1812.08954v1
PDF http://arxiv.org/pdf/1812.08954v1.pdf
PWC https://paperswithcode.com/paper/primal-path-algorithm-for-compositional-data
Repo
Framework

Spectrogram-channels u-net: a source separation model viewing each channel as the spectrogram of each source

Title Spectrogram-channels u-net: a source separation model viewing each channel as the spectrogram of each source
Authors Jaehoon Oh, Duyeon Kim, Se-Young Yun
Abstract Sound source separation has attracted attention from Music Information Retrieval(MIR) researchers, since it is related to many MIR tasks such as automatic lyric transcription, singer identification, and voice conversion. In this paper, we propose an intuitive spectrogram-based model for source separation by adapting U-Net. We call it Spectrogram-Channels U-Net, which means each channel of the output corresponds to the spectrogram of separated source itself. The proposed model can be used for not only singing voice separation but also multi-instrument separation by changing only the number of output channels. In addition, we propose a loss function that balances volumes between different sources. Finally, we yield performance that is state-of-the-art on both separation tasks.
Tasks Information Retrieval, Music Information Retrieval, Voice Conversion
Published 2018-10-26
URL http://arxiv.org/abs/1810.11520v2
PDF http://arxiv.org/pdf/1810.11520v2.pdf
PWC https://paperswithcode.com/paper/spectrogram-channels-u-net-a-source
Repo
Framework

On Markov Chain Gradient Descent

Title On Markov Chain Gradient Descent
Authors Tao Sun, Yuejiao Sun, Wotao Yin
Abstract Stochastic gradient methods are the workhorse (algorithms) of large-scale optimization problems in machine learning, signal processing, and other computational sciences and engineering. This paper studies Markov chain gradient descent, a variant of stochastic gradient descent where the random samples are taken on the trajectory of a Markov chain. Existing results of this method assume convex objectives and a reversible Markov chain and thus have their limitations. We establish new non-ergodic convergence under wider step sizes, for nonconvex problems, and for non-reversible finite-state Markov chains. Nonconvexity makes our method applicable to broader problem classes. Non-reversible finite-state Markov chains, on the other hand, can mix substatially faster. To obtain these results, we introduce a new technique that varies the mixing levels of the Markov chains. The reported numerical results validate our contributions.
Tasks
Published 2018-09-12
URL http://arxiv.org/abs/1809.04216v1
PDF http://arxiv.org/pdf/1809.04216v1.pdf
PWC https://paperswithcode.com/paper/on-markov-chain-gradient-descent
Repo
Framework

Automated Multi-Label Classification based on ML-Plan

Title Automated Multi-Label Classification based on ML-Plan
Authors Marcel Wever, Felix Mohr, Eyke Hüllermeier
Abstract Automated machine learning (AutoML) has received increasing attention in the recent past. While the main tools for AutoML, such as Auto-WEKA, TPOT, and auto-sklearn, mainly deal with single-label classification and regression, there is very little work on other types of machine learning tasks. In particular, there is almost no work on automating the engineering of machine learning applications for multi-label classification. This paper makes two contributions. First, it discusses the usefulness and feasibility of an AutoML approach for multi-label classification. Second, we show how the scope of ML-Plan, an AutoML-tool for multi-class classification, can be extended towards multi-label classification using MEKA, which is a multi-label extension of the well-known Java library WEKA. The resulting approach recursively refines MEKA’s multi-label classifiers, which sometimes nest another multi-label classifier, up to the selection of a single-label base learner provided by WEKA. In our evaluation, we find that the proposed approach yields superb results and performs significantly better than a set of baselines.
Tasks AutoML, Multi-Label Classification
Published 2018-11-09
URL http://arxiv.org/abs/1811.04060v1
PDF http://arxiv.org/pdf/1811.04060v1.pdf
PWC https://paperswithcode.com/paper/automated-multi-label-classification-based-on
Repo
Framework

Sidekick Policy Learning for Active Visual Exploration

Title Sidekick Policy Learning for Active Visual Exploration
Authors Santhosh K. Ramakrishnan, Kristen Grauman
Abstract We consider an active visual exploration scenario, where an agent must intelligently select its camera motions to efficiently reconstruct the full environment from only a limited set of narrow field-of-view glimpses. While the agent has full observability of the environment during training, it has only partial observability once deployed, being constrained by what portions it has seen and what camera motions are permissible. We introduce sidekick policy learning to capitalize on this imbalance of observability. The main idea is a preparatory learning phase that attempts simplified versions of the eventual exploration task, then guides the agent via reward shaping or initial policy supervision. To support interpretation of the resulting policies, we also develop a novel policy visualization technique. Results on active visual exploration tasks with 360 scenes and 3D objects show that sidekicks consistently improve performance and convergence rates over existing methods. Code, data and demos are available.
Tasks
Published 2018-07-29
URL http://arxiv.org/abs/1807.11010v1
PDF http://arxiv.org/pdf/1807.11010v1.pdf
PWC https://paperswithcode.com/paper/sidekick-policy-learning-for-active-visual
Repo
Framework

OriNet: A Fully Convolutional Network for 3D Human Pose Estimation

Title OriNet: A Fully Convolutional Network for 3D Human Pose Estimation
Authors Chenxu Luo, Xiao Chu, Alan Yuille
Abstract In this paper, we propose a fully convolutional network for 3D human pose estimation from monocular images. We use limb orientations as a new way to represent 3D poses and bind the orientation together with the bounding box of each limb region to better associate images and predictions. The 3D orientations are modeled jointly with 2D keypoint detections. Without additional constraints, this simple method can achieve good results on several large-scale benchmarks. Further experiments show that our method can generalize well to novel scenes and is robust to inaccurate bounding boxes.
Tasks 3D Human Pose Estimation, Pose Estimation
Published 2018-11-12
URL http://arxiv.org/abs/1811.04989v1
PDF http://arxiv.org/pdf/1811.04989v1.pdf
PWC https://paperswithcode.com/paper/orinet-a-fully-convolutional-network-for-3d
Repo
Framework

HomeGuard: A Smart System to Deal with the Emergency Response of Domestic Violence Victims

Title HomeGuard: A Smart System to Deal with the Emergency Response of Domestic Violence Victims
Authors Anik Islam, Arifa Akter, Bayzid Ashik Hossain
Abstract Domestic violence is a silent crisis in the developing and underdeveloped countries, though developed countries also remain drowned in the curse of it. In developed countries, victims can easily report and ask help on the contrary in developing and underdeveloped countries victims hardly report the crimes and when it’s noticed by the authority it’s become too late to save or support the victim. If this kind of problems can be identified at the very beginning of the event and proper actions can be taken, it’ll not only help the victim but also reduce the domestic violence crimes. This paper proposed a smart system which can extract victim’s situation and provide help according to it. Among of the developing and underdeveloped countries Bangladesh has been chosen though the rate of reporting of domestic violence is low, the extreme report collected by authorities is too high. Case studies collected by different NGO’s relating to domestic violence have been studied and applied to extract possible condition for the victims.
Tasks
Published 2018-03-26
URL http://arxiv.org/abs/1803.09401v1
PDF http://arxiv.org/pdf/1803.09401v1.pdf
PWC https://paperswithcode.com/paper/homeguard-a-smart-system-to-deal-with-the
Repo
Framework

Random Euler Complex-Valued Nonlinear Filters

Title Random Euler Complex-Valued Nonlinear Filters
Authors Jiashu Zhang, Sheng Zhang, Defang Li
Abstract Over the last decade, both the neural network and kernel adaptive filter have successfully been used for nonlinear signal processing. However, they suffer from high computational cost caused by their complex/growing network structures. In this paper, we propose two random Euler filters for complex-valued nonlinear filtering problem, i.e., linear random Euler complex-valued filter (LRECF) and its widely-linear version (WLRECF), which possess a simple and fixed network structure. The transient and steady-state performances are studied in a non-stationary environment. The analytical minimum mean square error (MSE) and optimum step-size are derived. Finally, numerical simulations on complex-valued nonlinear system identification and nonlinear channel equalization are presented to show the effectiveness of the proposed methods.
Tasks
Published 2018-01-02
URL http://arxiv.org/abs/1801.00668v1
PDF http://arxiv.org/pdf/1801.00668v1.pdf
PWC https://paperswithcode.com/paper/random-euler-complex-valued-nonlinear-filters
Repo
Framework
comments powered by Disqus