October 17, 2019

2922 words 14 mins read

Paper Group ANR 753

Deep learning based supervised semantic segmentation of Electron Cryo-Subtomograms. Security Consideration For Deep Learning-Based Image Forensics. Chemical Structure Elucidation from Mass Spectrometry by Matching Substructures. A Neural Model of Adaptation in Reading. Legible Normativity for AI Alignment: The Value of Silly Rules. Robust Deformati …

Deep learning based supervised semantic segmentation of Electron Cryo-Subtomograms


Title	Deep learning based supervised semantic segmentation of Electron Cryo-Subtomograms
Authors	Chang Liu, Xiangrui Zeng, Ruogu Lin, Xiaodan Liang, Zachary Freyberg, Eric Xing, Min Xu
Abstract	Cellular Electron Cryo-Tomography (CECT) is a powerful imaging technique for the 3D visualization of cellular structure and organization at submolecular resolution. It enables analyzing the native structures of macromolecular complexes and their spatial organization inside single cells. However, due to the high degree of structural complexity and practical imaging limitations, systematic macromolecular structural recovery inside CECT images remains challenging. Particularly, the recovery of a macromolecule is likely to be biased by its neighbor structures due to the high molecular crowding. To reduce the bias, here we introduce a novel 3D convolutional neural network inspired by Fully Convolutional Network and Encoder-Decoder Architecture for the supervised segmentation of macromolecules of interest in subtomograms. The tests of our models on realistically simulated CECT data demonstrate that our new approach has significantly improved segmentation performance compared to our baseline approach. Also, we demonstrate that the proposed model has generalization ability to segment new structures that do not exist in training data.
Tasks	Semantic Segmentation
Published	2018-02-12
URL	http://arxiv.org/abs/1802.04087v1
PDF	http://arxiv.org/pdf/1802.04087v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-supervised-semantic
Repo
Framework

Security Consideration For Deep Learning-Based Image Forensics


Title	Security Consideration For Deep Learning-Based Image Forensics
Authors	Wei Zhao, Pengpeng Yang, Rongrong Ni, Yao Zhao, Haorui Wu
Abstract	Recently, image forensics community has paied attention to the research on the design of effective algorithms based on deep learning technology and facts proved that combining the domain knowledge of image forensics and deep learning would achieve more robust and better performance than the traditional schemes. Instead of improving it, in this paper, the safety of deep learning based methods in the field of image forensics is taken into account. To the best of our knowledge, this is a first work focusing on this topic. Specifically, we experimentally find that the method using deep learning would fail when adding the slight noise into the images (adversarial images). Furthermore, two kinds of strategys are proposed to enforce security of deep learning-based method. Firstly, an extra penalty term to the loss function is added, which is referred to the 2-norm of the gradient of the loss with respect to the input images, and then an novel training method are adopt to train the model by fusing the normal and adversarial images. Experimental results show that the proposed algorithm can achieve good performance even in the case of adversarial images and provide a safety consideration for deep learning-based image forensics
Tasks
Published	2018-03-29
URL	http://arxiv.org/abs/1803.11157v2
PDF	http://arxiv.org/pdf/1803.11157v2.pdf
PWC	https://paperswithcode.com/paper/security-consideration-for-deep-learning
Repo
Framework

Chemical Structure Elucidation from Mass Spectrometry by Matching Substructures


Title	Chemical Structure Elucidation from Mass Spectrometry by Matching Substructures
Authors	Jing Lim, Joshua Wong, Minn Xuan Wong, Lee Han Eric Tan, Hai Leong Chieu, Davin Choo, Neng Kai Nigel Neo
Abstract	Chemical structure elucidation is a serious bottleneck in analytical chemistry today. We address the problem of identifying an unknown chemical threat given its mass spectrum and its chemical formula, a task which might take well trained chemists several days to complete. Given a chemical formula, there could be over a million possible candidate structures. We take a data driven approach to rank these structures by using neural networks to predict the presence of substructures given the mass spectrum, and matching these substructures to the candidate structures. Empirically, we evaluate our approach on a data set of chemical agents built for unknown chemical threat identification. We show that our substructure classifiers can attain over 90% micro F1-score, and we can find the correct structure among the top 20 candidates in 88% and 71% of test cases for two compound classes.
Tasks
Published	2018-11-17
URL	http://arxiv.org/abs/1811.07886v1
PDF	http://arxiv.org/pdf/1811.07886v1.pdf
PWC	https://paperswithcode.com/paper/chemical-structure-elucidation-from-mass
Repo
Framework

A Neural Model of Adaptation in Reading


Title	A Neural Model of Adaptation in Reading
Authors	Marten van Schijndel, Tal Linzen
Abstract	It has been argued that humans rapidly adapt their lexical and syntactic expectations to match the statistics of the current linguistic context. We provide further support to this claim by showing that the addition of a simple adaptation mechanism to a neural language model improves our predictions of human reading times compared to a non-adaptive model. We analyze the performance of the model on controlled materials from psycholinguistic experiments and show that it adapts not only to lexical items but also to abstract syntactic structures.
Tasks	Language Modelling
Published	2018-08-29
URL	http://arxiv.org/abs/1808.09930v2
PDF	http://arxiv.org/pdf/1808.09930v2.pdf
PWC	https://paperswithcode.com/paper/a-neural-model-of-adaptation-in-reading
Repo
Framework

Legible Normativity for AI Alignment: The Value of Silly Rules


Title	Legible Normativity for AI Alignment: The Value of Silly Rules
Authors	Dylan Hadfield-Menell, McKane Andrus, Gillian K. Hadfield
Abstract	It has become commonplace to assert that autonomous agents will have to be built to follow human rules of behavior–social norms and laws. But human laws and norms are complex and culturally varied systems, in many cases agents will have to learn the rules. This requires autonomous agents to have models of how human rule systems work so that they can make reliable predictions about rules. In this paper we contribute to the building of such models by analyzing an overlooked distinction between important rules and what we call silly rules–rules with no discernible direct impact on welfare. We show that silly rules render a normative system both more robust and more adaptable in response to shocks to perceived stability. They make normativity more legible for humans, and can increase legibility for AI systems as well. For AI systems to integrate into human normative systems, we suggest, it may be important for them to have models that include representations of silly rules.
Tasks
Published	2018-11-03
URL	http://arxiv.org/abs/1811.01267v1
PDF	http://arxiv.org/pdf/1811.01267v1.pdf
PWC	https://paperswithcode.com/paper/legible-normativity-for-ai-alignment-the
Repo
Framework

Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow


Title	Robust Deformation Estimation in Wood-Composite Materials using Variational Optical Flow
Authors	Markus Hofinger, Thomas Pock, Thomas Moosbrugger
Abstract	Wood-composite materials are widely used today as they homogenize humidity related directional deformations. Quantification of these deformations as coefficients is important for construction and engineering and topic of current research but still a manual process. This work introduces a novel computer vision approach that automatically extracts these properties directly from scans of the wooden specimens, taken at different humidity levels during the long lasting humidity conditioning process. These scans are used to compute a humidity dependent deformation field for each pixel, from which the desired coefficients can easily be calculated. The overall method includes automated registration of the wooden blocks, numerical optimization to compute a variational optical flow field which is further used to calculate dense strain fields and finally the engineering coefficients and their variance throughout the wooden blocks. The methods regularization is fully parameterizable which allows to model and suppress artifacts due to surface appearance changes of the specimens from mold, cracks, etc. that typically arise in the conditioning process.
Tasks	Optical Flow Estimation
Published	2018-02-13
URL	http://arxiv.org/abs/1802.04546v1
PDF	http://arxiv.org/pdf/1802.04546v1.pdf
PWC	https://paperswithcode.com/paper/robust-deformation-estimation-in-wood
Repo
Framework

Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis


Title	Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis
Authors	Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee
Abstract	Conventional seq2seq chatbot models only try to find the sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. Some research works trying to modify the sentiment of the output sequences were reported. In this paper, we propose five models to scale or adjust the sentiment of the chatbot response: persona-based model, reinforcement learning, plug and play model, sentiment transformation network and cycleGAN, all based on the conventional seq2seq model. We also develop two evaluation metrics to estimate if the responses are reasonable given the input. These metrics together with other two popularly used metrics were used to analyze the performance of the five proposed models on different aspects, and reinforcement learning and cycleGAN were shown to be very attractive. The evaluation metrics were also found to be well correlated with human evaluation.
Tasks	Chatbot
Published	2018-04-07
URL	http://arxiv.org/abs/1804.02504v1
PDF	http://arxiv.org/pdf/1804.02504v1.pdf
PWC	https://paperswithcode.com/paper/scalable-sentiment-for-sequence-to-sequence
Repo
Framework

Fashion and Apparel Classification using Convolutional Neural Networks


Title	Fashion and Apparel Classification using Convolutional Neural Networks
Authors	Alexander Schindler, Thomas Lidy, Stephan Karner, Matthias Hecker
Abstract	We present an empirical study of applying deep Convolutional Neural Networks (CNN) to the task of fashion and apparel image classification to improve meta-data enrichment of e-commerce applications. Five different CNN architectures were analyzed using clean and pre-trained models. The models were evaluated in three different tasks person detection, product and gender classification, on two small and large scale datasets.
Tasks	Human Detection, Image Classification
Published	2018-11-11
URL	http://arxiv.org/abs/1811.04374v1
PDF	http://arxiv.org/pdf/1811.04374v1.pdf
PWC	https://paperswithcode.com/paper/fashion-and-apparel-classification-using
Repo
Framework

MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization


Title	MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization
Authors	Zengyi Qin, Jinglu Wang, Yan Lu
Abstract	Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object detection from a monocular RGB image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet is a single, unified network composed of four task-specific subnetworks, responsible for 2D object detection, instance depth estimation (IDE), 3D localization and local corner regression. Unlike the pixel-level depth estimation that needs per-pixel annotations, we propose a novel IDE method that directly predicts the depth of the targeting 3D bounding box’s center using sparse supervision. The 3D localization is further achieved by estimating the position in the horizontal and vertical dimensions. Finally, MonoGRNet is jointly learned by optimizing the locations and poses of the 3D bounding boxes in the global context. We demonstrate that MonoGRNet achieves state-of-the-art performance on challenging datasets.
Tasks	3D Object Detection, Depth Estimation, Monocular 3D Object Localization, Object Detection, Object Localization, Scene Understanding
Published	2018-11-26
URL	https://arxiv.org/abs/1811.10247v2
PDF	https://arxiv.org/pdf/1811.10247v2.pdf
PWC	https://paperswithcode.com/paper/monogrnet-a-geometric-reasoning-network-for
Repo
Framework

Task-Free Continual Learning


Title	Task-Free Continual Learning
Authors	Rahaf Aljundi, Klaas Kelchtermans, Tinne Tuytelaars
Abstract	Methods proposed in the literature towards continual deep learning typically operate in a task-based sequential learning setup. A sequence of tasks is learned, one at a time, with all data of current task available but not of previous or future tasks. Task boundaries and identities are known at all times. This setup, however, is rarely encountered in practical applications. Therefore we investigate how to transform continual learning to an online setup. We develop a system that keeps on learning over time in a streaming fashion, with data distributions gradually changing and without the notion of separate tasks. To this end, we build on the work on Memory Aware Synapses, and show how this method can be made online by providing a protocol to decide i) when to update the importance weights, ii) which data to use to update them, and iii) how to accumulate the importance weights at each update step. Experimental results show the validity of the approach in the context of two applications: (self-)supervised learning of a face recognition model by watching soap series and learning a robot to avoid collisions.
Tasks	Continual Learning, Face Recognition
Published	2018-12-10
URL	https://arxiv.org/abs/1812.03596v3
PDF	https://arxiv.org/pdf/1812.03596v3.pdf
PWC	https://paperswithcode.com/paper/task-free-continual-learning
Repo
Framework

A Comparison of the Taguchi Method and Evolutionary Optimization in Multivariate Testing


Title	A Comparison of the Taguchi Method and Evolutionary Optimization in Multivariate Testing
Authors	Jingbo Jiang, Diego Legrand, Robert Severn, Risto Miikkulainen
Abstract	Multivariate testing has recently emerged as a promising technique in web interface design. In contrast to the standard A/B testing, multivariate approach aims at evaluating a large number of values in a few key variables systematically. The Taguchi method is a practical implementation of this idea, focusing on orthogonal combinations of values. This paper evaluates an alternative method: population-based search, i.e. evolutionary optimization. Its performance is compared to that of the Taguchi method in several simulated conditions, including an orthogonal one designed to favor the Taguchi method, and two realistic conditions with dependences between variables. Evolutionary optimization is found to perform significantly better especially in the realistic conditions, suggesting that it forms a good approach for web interface design in the future.
Tasks
Published	2018-08-25
URL	https://arxiv.org/abs/1808.08347v2
PDF	https://arxiv.org/pdf/1808.08347v2.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-the-taguchi-method-and
Repo
Framework

Network Classification in Temporal Networks Using Motifs


Title	Network Classification in Temporal Networks Using Motifs
Authors	Kun Tu, Jian Li, Don Towsley, Dave Braines, Liam D. Turner
Abstract	Network classification has a variety of applications, such as detecting communities within networks and finding similarities between those representing different aspects of the real world. However, most existing work in this area focus on examining static undirected networks without considering directed edges or temporality. In this paper, we propose a new methodology that utilizes feature representation for network classification based on the temporal motif distribution of the network and a null model for comparing against random graphs. Experimental results show that our method improves accuracy by up $10%$ compared to the state-of-the-art embedding method in network classification, for tasks such as classifying network type, identifying communities in email exchange network, and identifying users given their app-switching behaviors.
Tasks
Published	2018-07-10
URL	http://arxiv.org/abs/1807.03733v2
PDF	http://arxiv.org/pdf/1807.03733v2.pdf
PWC	https://paperswithcode.com/paper/network-classification-in-temporal-networks
Repo
Framework

Continual Occlusions and Optical Flow Estimation


Title	Continual Occlusions and Optical Flow Estimation
Authors	Michal Neoral, Jan Šochman, Jiří Matas
Abstract	Two optical flow estimation problems are addressed: i) occlusion estimation and handling, and ii) estimation from image sequences longer than two frames. The proposed ContinualFlow method estimates occlusions before flow, avoiding the use of flow corrupted by occlusions for their estimation. We show that providing occlusion masks as an additional input to flow estimation improves the standard performance metric by more than 25% on both KITTI and Sintel. As a second contribution, a novel method for incorporating information from past frames into flow estimation is introduced. The previous frame flow serves as an input to occlusion estimation and as a prior in occluded regions, i.e. those without visual correspondences. By continually using the previous frame flow, ContinualFlow performance improves further by 18% on KITTI and 7% on Sintel, achieving top performance on KITTI and Sintel.
Tasks	Optical Flow Estimation
Published	2018-11-05
URL	http://arxiv.org/abs/1811.01602v1
PDF	http://arxiv.org/pdf/1811.01602v1.pdf
PWC	https://paperswithcode.com/paper/continual-occlusions-and-optical-flow
Repo
Framework

POIReviewQA: A Semantically Enriched POI Retrieval and Question Answering Dataset


Title	POIReviewQA: A Semantically Enriched POI Retrieval and Question Answering Dataset
Authors	Gengchen Mai, Krzysztof Janowicz, Cheng He, Sumang Liu, Ni Lao
Abstract	Many services that perform information retrieval for Points of Interest (POI) utilize a Lucene-based setup with spatial filtering. While this type of system is easy to implement it does not make use of semantics but relies on direct word matches between a query and reviews leading to a loss in both precision and recall. To study the challenging task of semantically enriching POIs from unstructured data in order to support open-domain search and question answering (QA), we introduce a new dataset POIReviewQA. It consists of 20k questions (e.g.“is this restaurant dog friendly?") for 1022 Yelp business types. For each question we sampled 10 reviews, and annotated each sentence in the reviews whether it answers the question and what the corresponding answer is. To test a system’s ability to understand the text we adopt an information retrieval evaluation by ranking all the review sentences for a question based on the likelihood that they answer this question. We build a Lucene-based baseline model, which achieves 77.0% AUC and 48.8% MAP. A sentence embedding-based model achieves 79.2% AUC and 41.8% MAP, indicating that the dataset presents a challenging problem for future research by the GIR community. The result technology can help exploit the thematic content of web documents and social media for characterisation of locations.
Tasks	Information Retrieval, Question Answering, Sentence Embedding
Published	2018-10-05
URL	http://arxiv.org/abs/1810.02802v1
PDF	http://arxiv.org/pdf/1810.02802v1.pdf
PWC	https://paperswithcode.com/paper/poireviewqa-a-semantically-enriched-poi
Repo
Framework

Boosting Model Performance through Differentially Private Model Aggregation


Title	Boosting Model Performance through Differentially Private Model Aggregation
Authors	Sophia Collet, Robert Dadashi, Zahi N. Karam, Chang Liu, Parinaz Sobhani, Yevgeniy Vahlis, Ji Chao Zhang
Abstract	A key factor in developing high performing machine learning models is the availability of sufficiently large datasets. This work is motivated by applications arising in Software as a Service (SaaS) companies where there exist numerous similar yet disjoint datasets from multiple client companies. To overcome the challenges of insufficient data without explicitly aggregating the clients’ datasets due to privacy concerns, one solution is to collect more data for each individual client, another is to privately aggregate information from models trained on each client’s data. In this work, two approaches for private model aggregation are proposed that enable the transfer of knowledge from existing models trained on other companies’ datasets to a new company with limited labeled data while protecting each client company’s underlying individual sensitive information. The two proposed approaches are based on state-of-the-art private learning algorithms: Differentially Private Permutation-based Stochastic Gradient Descent and Approximate Minima Perturbation. We empirically show that by leveraging differentially private techniques, we can enable private model aggregation and augment data utility while providing provable mathematical guarantees on privacy. The proposed methods thus provide significant business value for SaaS companies and their clients, specifically as a solution for the cold-start problem.
Tasks
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04911v2
PDF	http://arxiv.org/pdf/1811.04911v2.pdf
PWC	https://paperswithcode.com/paper/boosting-model-performance-through
Repo
Framework