Paper Group ANR 725
On Configurable Defense against Adversarial Example Attacks. Probabilistic Graphical Modeling approach to dynamic PET direct parametric map estimation and image reconstruction. HCqa: Hybrid and Complex Question Answering on Textual Corpus and Knowledge Graph. PCAS: Pruning Channels with Attention Statistics for Deep Network Compression. Improving D …
On Configurable Defense against Adversarial Example Attacks
| Title | On Configurable Defense against Adversarial Example Attacks |
| Authors | Bo Luo, Min Li, Yu Li, Qiang Xu |
| Abstract | Machine learning systems based on deep neural networks (DNNs) have gained mainstream adoption in many applications. Recently, however, DNNs are shown to be vulnerable to adversarial example attacks with slight perturbations on the inputs. Existing defense mechanisms against such attacks try to improve the overall robustness of the system, but they do not differentiate different targeted attacks even though the corresponding impacts may vary significantly. To tackle this problem, we propose a novel configurable defense mechanism in this work, wherein we are able to flexibly tune the robustness of the system against different targeted attacks to satisfy application requirements. This is achieved by refining the DNN loss function with an attack sensitive matrix to represent the impacts of different targeted attacks. Experimental results on CIFAR-10 and GTSRB data sets demonstrate the efficacy of the proposed solution. |
| Tasks | |
| Published | 2018-12-06 |
| URL | http://arxiv.org/abs/1812.02737v1 |
| http://arxiv.org/pdf/1812.02737v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-configurable-defense-against-adversarial |
| Repo | |
| Framework | |
Probabilistic Graphical Modeling approach to dynamic PET direct parametric map estimation and image reconstruction
| Title | Probabilistic Graphical Modeling approach to dynamic PET direct parametric map estimation and image reconstruction |
| Authors | Michele Scipioni, Stefano Pedemonte, Maria Filomena Santarelli, Luigi Landini |
| Abstract | In the context of dynamic emission tomography, the conventional processing pipeline consists of independent image reconstruction of single time frames, followed by the application of a suitable kinetic model to time activity curves (TACs) at the voxel or region-of-interest level. The relatively new field of 4D PET direct reconstruction, by contrast, seeks to move beyond this scheme and incorporate information from multiple time frames within the reconstruction task. Existing 4D direct models are based on a deterministic description of voxels’ TACs, captured by the chosen kinetic model, considering the photon counting process the only source of uncertainty. In this work, we introduce a new probabilistic modeling strategy based on the key assumption that activity time course would be subject to uncertainty even if the parameters of the underlying dynamic process were known. This leads to a hierarchical Bayesian model, which we formulate using the formalism of Probabilistic Graphical Modeling (PGM). The inference of the joint probability density function arising from PGM is addressed using a new gradient-based iterative algorithm, which presents several advantages compared to existing direct methods: it is flexible to an arbitrary choice of linear and nonlinear kinetic model; it enables the inclusion of arbitrary (sub)differentiable priors for parametric maps; it is simpler to implement and suitable to integration in computing frameworks for machine learning. Computer simulations and an application to real patient scan showed how the proposed approach allows us to weight the importance of the kinetic model, providing a bridge between indirect and deterministic direct methods. |
| Tasks | Image Reconstruction |
| Published | 2018-08-24 |
| URL | http://arxiv.org/abs/1808.08286v1 |
| http://arxiv.org/pdf/1808.08286v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-graphical-modeling-approach-to |
| Repo | |
| Framework | |
HCqa: Hybrid and Complex Question Answering on Textual Corpus and Knowledge Graph
| Title | HCqa: Hybrid and Complex Question Answering on Textual Corpus and Knowledge Graph |
| Authors | Somayeh Asadifar, Mohsen Kahani, Saeedeh Shekarpour |
| Abstract | Question Answering (QA) systems provide easy access to the vast amount of knowledge without having to know the underlying complex structure of the knowledge. The research community has provided ad hoc solutions to the key QA tasks, including named entity recognition and disambiguation, relation extraction and query building. Furthermore, some have integrated and composed these components to implement many tasks automatically and efficiently. However, in general, the existing solutions are limited to simple and short questions and still do not address complex questions composed of several sub-questions. Exploiting the answer to complex questions is further challenged if it requires integrating knowledge from unstructured data sources, i.e., textual corpus, as well as structured data sources, i.e., knowledge graphs. In this paper, an approach (HCqa) is introduced for dealing with complex questions requiring federating knowledge from a hybrid of heterogeneous data sources (structured and unstructured). We contribute in developing (i) a decomposition mechanism which extracts sub-questions from potentially long and complex input questions, (ii) a novel comprehensive schema, first of its kind, for extracting and annotating relations, and (iii) an approach for executing and aggregating the answers of sub-questions. The evaluation of HCqa showed a superior accuracy in the fundamental tasks, such as relation extraction, as well as the federation task. |
| Tasks | Knowledge Graphs, Named Entity Recognition, Question Answering, Relation Extraction |
| Published | 2018-11-24 |
| URL | https://arxiv.org/abs/1811.10986v5 |
| https://arxiv.org/pdf/1811.10986v5.pdf | |
| PWC | https://paperswithcode.com/paper/hcqa-hybrid-and-complex-question-answering-on |
| Repo | |
| Framework | |
PCAS: Pruning Channels with Attention Statistics for Deep Network Compression
| Title | PCAS: Pruning Channels with Attention Statistics for Deep Network Compression |
| Authors | Kohei Yamamoto, Kurato Maeno |
| Abstract | Compression techniques for deep neural networks are important for implementing them on small embedded devices. In particular, channel-pruning is a useful technique for realizing compact networks. However, many conventional methods require manual setting of compression ratios in each layer. It is difficult to analyze the relationships between all layers, especially for deeper models. To address these issues, we propose a simple channel-pruning technique based on attention statistics that enables to evaluate the importance of channels. We improved the method by means of a criterion for automatic channel selection, using a single compression ratio for the entire model in place of per-layer model analysis. The proposed approach achieved superior performance over conventional methods with respect to accuracy and the computational costs for various models and datasets. We provide analysis results for behavior of the proposed criterion on different datasets to demonstrate its favorable properties for channel pruning. |
| Tasks | |
| Published | 2018-06-14 |
| URL | https://arxiv.org/abs/1806.05382v3 |
| https://arxiv.org/pdf/1806.05382v3.pdf | |
| PWC | https://paperswithcode.com/paper/pcas-pruning-channels-with-attention |
| Repo | |
| Framework | |
Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector
| Title | Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector |
| Authors | Shanchan Wu, Kai Fan, Qiong Zhang |
| Abstract | Distant supervised relation extraction has been successfully applied to large corpus with thousands of relations. However, the inevitable wrong labeling problem by distant supervision will hurt the performance of relation extraction. In this paper, we propose a method with neural noise converter to alleviate the impact of noisy data, and a conditional optimal selector to make proper prediction. Our noise converter learns the structured transition matrix on logit level and captures the property of distant supervised relation extraction dataset. The conditional optimal selector on the other hand helps to make proper prediction decision of an entity pair even if the group of sentences is overwhelmed by no-relation sentences. We conduct experiments on a widely used dataset and the results show significant improvement over competitive baseline methods. |
| Tasks | Relation Extraction |
| Published | 2018-11-14 |
| URL | http://arxiv.org/abs/1811.05616v1 |
| http://arxiv.org/pdf/1811.05616v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-distantly-supervised-relation |
| Repo | |
| Framework | |
Kernel Machines With Missing Responses
| Title | Kernel Machines With Missing Responses |
| Authors | Tiantian Liu, Yair Goldberg |
| Abstract | Missing responses is a missing data format in which outcomes are not always observed. In this work we develop kernel machines that can handle missing responses. First, we propose a kernel machine family that uses mainly the complete cases. For the quadratic loss, we then propose a family of doubly-robust kernel machines. The proposed kernel-machine estimators can be applied to both regression and classification problems. We prove oracle inequalities for the finite-sample differences between the kernel machine risk and Bayes risk. We use these oracle inequalities to prove consistency and to calculate convergence rates. We demonstrate the performance of the two proposed kernel machine families using both a simulation study and a real-world data analysis. |
| Tasks | |
| Published | 2018-06-07 |
| URL | http://arxiv.org/abs/1806.02865v1 |
| http://arxiv.org/pdf/1806.02865v1.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-machines-with-missing-responses |
| Repo | |
| Framework | |
Multimodal Named Entity Recognition for Short Social Media Posts
| Title | Multimodal Named Entity Recognition for Short Social Media Posts |
| Authors | Seungwhan Moon, Leonardo Neves, Vitor Carvalho |
| Abstract | We introduce a new task called Multimodal Named Entity Recognition (MNER) for noisy user-generated data such as tweets or Snapchat captions, which comprise short text with accompanying images. These social media posts often come in inconsistent or incomplete syntax and lexical notations with very limited surrounding textual contexts, bringing significant challenges for NER. To this end, we create a new dataset for MNER called SnapCaptions (Snapchat image-caption pairs submitted to public and crowd-sourced stories with fully annotated named entities). We then build upon the state-of-the-art Bi-LSTM word/character based NER models with 1) a deep image network which incorporates relevant visual context to augment textual information, and 2) a generic modality-attention module which learns to attenuate irrelevant modalities while amplifying the most informative ones to extract contexts from, adaptive to each sample and token. The proposed MNER model with modality attention significantly outperforms the state-of-the-art text-only NER models by successfully leveraging provided visual contexts, opening up potential applications of MNER on myriads of social media platforms. |
| Tasks | Named Entity Recognition |
| Published | 2018-02-22 |
| URL | http://arxiv.org/abs/1802.07862v1 |
| http://arxiv.org/pdf/1802.07862v1.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-named-entity-recognition-for-short |
| Repo | |
| Framework | |
Genetic-Gated Networks for Deep Reinforcement
| Title | Genetic-Gated Networks for Deep Reinforcement |
| Authors | Simyung Chang, John Yang, Jaeseok Choi, Nojun Kwak |
| Abstract | We introduce the Genetic-Gated Networks (G2Ns), simple neural networks that combine a gate vector composed of binary genetic genes in the hidden layer(s) of networks. Our method can take both advantages of gradient-free optimization and gradient-based optimization methods, of which the former is effective for problems with multiple local minima, while the latter can quickly find local minima. In addition, multiple chromosomes can define different models, making it easy to construct multiple models and can be effectively applied to problems that require multiple models. We show that this G2N can be applied to typical reinforcement learning algorithms to achieve a large improvement in sample efficiency and performance. |
| Tasks | |
| Published | 2018-11-26 |
| URL | http://arxiv.org/abs/1903.01886v1 |
| http://arxiv.org/pdf/1903.01886v1.pdf | |
| PWC | https://paperswithcode.com/paper/genetic-gated-networks-for-deep-reinforcement |
| Repo | |
| Framework | |
Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization
| Title | Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization |
| Authors | Dmitry Shalyga, Pavel Filonov, Andrey Lavrentyev |
| Abstract | We continue to develop our neural network (NN) based forecasting approach to anomaly detection (AD) using the Secure Water Treatment (SWaT) industrial control system (ICS) testbed dataset. We propose genetic algorithms (GA) to find the best NN architecture for a given dataset, using the NAB metric to assess the quality of different architectures. The drawbacks of the F1-metric are analyzed. Several techniques are proposed to improve the quality of AD: exponentially weighted smoothing, mean p-powered error measure, individual error weight for each variable, disjoint prediction windows. Based on the techniques used, an approach to anomaly interpretation is introduced. |
| Tasks | Anomaly Detection |
| Published | 2018-07-19 |
| URL | http://arxiv.org/abs/1807.07282v1 |
| http://arxiv.org/pdf/1807.07282v1.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-for-water-treatment-system |
| Repo | |
| Framework | |
ClaimRank: Detecting Check-Worthy Claims in Arabic and English
| Title | ClaimRank: Detecting Check-Worthy Claims in Arabic and English |
| Authors | Israa Jaradat, Pepa Gencheva, Alberto Barron-Cedeno, Lluis Marquez, Preslav Nakov |
| Abstract | We present ClaimRank, an online system for detecting check-worthy claims. While originally trained on political debates, the system can work for any kind of text, e.g., interviews or regular news articles. Its aim is to facilitate manual fact-checking efforts by prioritizing the claims that fact-checkers should consider first. ClaimRank supports both Arabic and English, it is trained on actual annotations from nine reputable fact-checking organizations (PolitiFact, FactCheck, ABC, CNN, NPR, NYT, Chicago Tribune, The Guardian, and Washington Post), and thus it can mimic the claim selection strategies for each and any of them, as well as for the union of them all. |
| Tasks | |
| Published | 2018-04-20 |
| URL | http://arxiv.org/abs/1804.07587v1 |
| http://arxiv.org/pdf/1804.07587v1.pdf | |
| PWC | https://paperswithcode.com/paper/claimrank-detecting-check-worthy-claims-in |
| Repo | |
| Framework | |
Focus Group on Artificial Intelligence for Health
| Title | Focus Group on Artificial Intelligence for Health |
| Authors | Marcel Salathé, Thomas Wiegand, Markus Wenzel |
| Abstract | Artificial Intelligence (AI) - the phenomenon of machines being able to solve problems that require human intelligence - has in the past decade seen an enormous rise of interest due to significant advances in effectiveness and use. The health sector, one of the most important sectors for societies and economies worldwide, is particularly interesting for AI applications, given the ongoing digitalisation of all types of health information. The potential for AI assistance in the health domain is immense, because AI can support medical decision making at reduced costs, everywhere. However, due to the complexity of AI algorithms, it is difficult to distinguish good from bad AI-based solutions and to understand their strengths and weaknesses, which is crucial for clarifying responsibilities and for building trust. For this reason, the International Telecommunication Union (ITU) has established a new Focus Group on “Artificial Intelligence for Health” (FG-AI4H) in partnership with the World Health Organization (WHO). Health and care services are usually the responsibility of a government - even when provided through private insurance systems - and thus under the responsibility of WHO/ITU member states. FG-AI4H will identify opportunities for international standardization, which will foster the application of AI to health issues on a global scale. In particular, it will establish a standardized assessment framework with open benchmarks for the evaluation of AI-based methods for health, such as AI-based diagnosis, triage or treatment decisions. |
| Tasks | Decision Making |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.04797v1 |
| http://arxiv.org/pdf/1809.04797v1.pdf | |
| PWC | https://paperswithcode.com/paper/focus-group-on-artificial-intelligence-for |
| Repo | |
| Framework | |
SmartTennisTV: Automatic indexing of tennis videos
| Title | SmartTennisTV: Automatic indexing of tennis videos |
| Authors | Anurag Ghosh, C. V. Jawahar |
| Abstract | In this paper, we demonstrate a score based indexing approach for tennis videos. Given a broadcast tennis video (BTV), we index all the video segments with their scores to create a navigable and searchable match. Our approach temporally segments the rallies in the video and then recognizes the scores from each of the segments, before refining the scores using the knowledge of the tennis scoring system. We finally build an interface to effortlessly retrieve and view the relevant video segments by also automatically tagging the segmented rallies with human accessible tags such as ‘fault’ and ‘deuce’. The efficiency of our approach is demonstrated on BTV’s from two major tennis tournaments. |
| Tasks | |
| Published | 2018-01-04 |
| URL | http://arxiv.org/abs/1801.01430v1 |
| http://arxiv.org/pdf/1801.01430v1.pdf | |
| PWC | https://paperswithcode.com/paper/smarttennistv-automatic-indexing-of-tennis |
| Repo | |
| Framework | |
Nonparametric Feature Extraction from Dendrograms
| Title | Nonparametric Feature Extraction from Dendrograms |
| Authors | Morteza Haghir Chehreghani, Mostafa Haghir Chehreghani |
| Abstract | We propose feature extraction from dendrograms in a nonparametric way. The Minimax distance measures correspond to building a dendrogram with single linkage criterion, with defining specific forms of a level function and a distance function over that. Therefore, we extend this method to arbitrary dendrograms. We develop a generalized framework wherein different distance measures can be inferred from different types of dendrograms, level functions and distance functions. Via an appropriate embedding, we compute a vector-based representation of the inferred distances, in order to enable many numerical machine learning algorithms to employ such distances. Then, to address the model selection problem, we study the aggregation of different dendrogram-based distances respectively in solution space and in representation space in the spirit of deep representations. In the first approach, for example for the clustering problem, we build a graph with positive and negative edge weights according to the consistency of the clustering labels of different objects among different solutions, in the context of ensemble methods. Then, we use an efficient variant of correlation clustering to produce the final clusters. In the second approach, we investigate the sequential combination of different distances and features sequentially in the spirit of multi-layered architectures to obtain the final features. Finally, we demonstrate the effectiveness of our approach via several numerical studies. |
| Tasks | Model Selection |
| Published | 2018-12-21 |
| URL | https://arxiv.org/abs/1812.09225v3 |
| https://arxiv.org/pdf/1812.09225v3.pdf | |
| PWC | https://paperswithcode.com/paper/nonparametric-feature-extraction-from |
| Repo | |
| Framework | |
Towards a new system for drowsiness detection based on eye blinking and head posture estimation
| Title | Towards a new system for drowsiness detection based on eye blinking and head posture estimation |
| Authors | M. Ben Dkhil, A. Wali, Adel M. Alimi |
| Abstract | Driver drowsiness problem is considered as one of the most important reasons that increases road accidents number. We propose in this paper a new approach for realtime driver drowsiness in order to prevent road accidents. The system uses a smart video camera that takes drivers faces images and supervises the eye blink (open and close) state and head posture to detect the different drowsiness states. Face and eye detection are done by Viola and Jones technique. |
| Tasks | |
| Published | 2018-05-31 |
| URL | http://arxiv.org/abs/1806.00360v1 |
| http://arxiv.org/pdf/1806.00360v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-new-system-for-drowsiness-detection |
| Repo | |
| Framework | |
Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog
| Title | Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog |
| Authors | Jiaping Zhang, Tiancheng Zhao, Zhou Yu |
| Abstract | Creating an intelligent conversational system that understands vision and language is one of the ultimate goals in Artificial Intelligence (AI)~\cite{winograd1972understanding}. Extensive research has focused on vision-to-language generation, however, limited research has touched on combining these two modalities in a goal-driven dialog context. We propose a multimodal hierarchical reinforcement learning framework that dynamically integrates vision and language for task-oriented visual dialog. The framework jointly learns the multimodal dialog state representation and the hierarchical dialog policy to improve both dialog task success and efficiency. We also propose a new technique, state adaptation, to integrate context awareness in the dialog state representation. We evaluate the proposed framework and the state adaptation technique in an image guessing game and achieve promising results. |
| Tasks | Hierarchical Reinforcement Learning, Text Generation, Visual Dialog |
| Published | 2018-05-08 |
| URL | http://arxiv.org/abs/1805.03257v1 |
| http://arxiv.org/pdf/1805.03257v1.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-hierarchical-reinforcement |
| Repo | |
| Framework | |
