January 30, 2020

3012 words 15 mins read

Paper Group ANR 281

Exploring AI Futures Through Role Play. Discriminating Original Region from Duplicated One in Copy-Move Forgery. Discourse Behavior of Older Adults Interacting With a Dialogue Agent Competent in Multiple Topics. Bridging Disentanglement with Independence and Conditional Independence via Mutual Information for Representation Learning. An Inception I …

Exploring AI Futures Through Role Play


Title	Exploring AI Futures Through Role Play
Authors	Shahar Avin, Ross Gruetzemacher, James Fox
Abstract	We present an innovative methodology for studying and teaching the impacts of AI through a role play game. The game serves two primary purposes: 1) training AI developers and AI policy professionals to reflect on and prepare for future social and ethical challenges related to AI and 2) exploring possible futures involving AI technology development, deployment, social impacts, and governance. While the game currently focuses on the inter relations between short –, mid and long term impacts of AI, it has potential to be adapted for a broad range of scenarios, exploring in greater depths issues of AI policy research and affording training within organizations. The game presented here has undergone two years of development and has been tested through over 30 events involving between 3 and 70 participants. The game is under active development, but preliminary findings suggest that role play is a promising methodology for both exploring AI futures and training individuals and organizations in thinking about, and reflecting on, the impacts of AI and strategic mistakes that can be avoided today.
Tasks
Published	2019-12-19
URL	https://arxiv.org/abs/1912.08964v1
PDF	https://arxiv.org/pdf/1912.08964v1.pdf
PWC	https://paperswithcode.com/paper/exploring-ai-futures-through-role-play
Repo
Framework

Discriminating Original Region from Duplicated One in Copy-Move Forgery


Title	Discriminating Original Region from Duplicated One in Copy-Move Forgery
Authors	Saba Salehi, Ahmad Mahmoodi-Aznaveh
Abstract	Since images are used as evidence in many cases, validation of digital images is essential. Copy-move forgery is a special kind of manipulation in which some parts of an image is copied and pasted into another part of the same image. Various methods have been proposed to detect copy-move forgery, which have achieved promising results. In previous methods, a binary mask determining the original and forged region is presented as the final result. However, it is not specified which part of the mask is the forged region. It should be noted that discriminating the original region from the duplicated one is not usually feasible by human visual system(HVS). On the other hand, exact localizing the forged region can be helpful for automatic forgery detection especially in combined forgeries. In real-world forgeries, some manipulations are performed in order to provide a visibly realistic scene. These modifications are usually applied on the boundary of the duplicated snippets. In this research, the texture information of the border regions of both the original and copied patches have been statistically investigated. Based on this analysis, we propose a method to discriminated copied snippets from original ones. In order to validate our method, GRIP dataset is utilized since it contains more realistic forged images which are not easily recognizable by HVS.
Tasks
Published	2019-03-17
URL	http://arxiv.org/abs/1903.07044v1
PDF	http://arxiv.org/pdf/1903.07044v1.pdf
PWC	https://paperswithcode.com/paper/discriminating-original-region-from
Repo
Framework

Discourse Behavior of Older Adults Interacting With a Dialogue Agent Competent in Multiple Topics


Title	Discourse Behavior of Older Adults Interacting With a Dialogue Agent Competent in Multiple Topics
Authors	S. Zahra Razavi, Lenhart K. Schubert, Kimberly A. Van Orden, Mohammad Rafayet Ali
Abstract	We present some results concerning the dialogue behavior and inferred sentiment of a group of older adults interacting with a computer-based avatar. Our avatar is unique in its ability to hold natural dialogues on a wide range of everyday topics—27 topics in three groups, developed with the help of gerontologists. The three groups vary in ``degrees of intimacy”, and as such in degrees of difficulty for the user. Each participant interacted with the avatar for 7-9 sessions over a period of 3-4 weeks; analysis of the dialogues reveals correlations such as greater verbosity for more difficult topics, increasing verbosity with successive sessions, especially for more difficult topics, stronger sentiment on topics concerned with life goals rather than routine activities, and stronger self-disclosure for more intimate topics. In addition to their intrinsic interest, these results also reflect positively on the sophistication of our dialogue system. \|
Tasks
Published	2019-07-14
URL	https://arxiv.org/abs/1907.06279v1
PDF	https://arxiv.org/pdf/1907.06279v1.pdf
PWC	https://paperswithcode.com/paper/discourse-behavior-of-older-adults
Repo
Framework

Bridging Disentanglement with Independence and Conditional Independence via Mutual Information for Representation Learning


Title	Bridging Disentanglement with Independence and Conditional Independence via Mutual Information for Representation Learning
Authors	Xiaojiang Yang, Wendong Bi, Yu Cheng, Junchi Yan
Abstract	Existing works on disentangled representation learning usually lie on a common assumption: all factors in disentangled representations should be independent. This assumption is about the inner property of disentangled representations, while ignoring their relation with external data. To tackle this problem, we propose another assumption to establish an important relation between data and its disentangled representations via mutual information: the mutual information between each factor of disentangled representations and data should be invariant to other factors. We formulate this assumption into mathematical equations, and theoretically bridge it with independence and conditional independence of factors. Meanwhile, we show that conditional independence is satisfied in encoders of VAEs due to factorized noise in reparameterization. To highlight the importance of our proposed assumption, we show in experiments that violating the assumption leads to dramatic decline of disentanglement. Based on this assumption, we further propose to split the deeper layers in encoder to ensure parameters in these layers are not shared for different factors. The proposed encoder, called Split Encoder, can be applied into models that penalize total correlation, and shows significant improvement in unsupervised learning of disentangled representations and reconstructions.
Tasks	Representation Learning
Published	2019-11-25
URL	https://arxiv.org/abs/1911.10922v2
PDF	https://arxiv.org/pdf/1911.10922v2.pdf
PWC	https://paperswithcode.com/paper/bridging-disentanglement-with-independence
Repo
Framework

An Inception Inspired Deep Network to Analyse Fundus Images


Title	An Inception Inspired Deep Network to Analyse Fundus Images
Authors	Fatmatulzehra Uslu
Abstract	A fundus image usually contains the optic disc, pathologies and other structures in addition to vessels to be segmented. This study proposes a deep network for vessel segmentation, whose architecture is inspired by inception modules. The network contains three sub-networks, each with a different filter size, which are connected in the last layer of the proposed network. According to experiments conducted in the DRIVE and IOSTAR, the performance of our network is found to be better than or comparable to that of the previous methods. We also observe that the sub-networks pay attention to different parts of an input image when producing an output map in the last layer of the proposed network; though, training of the proposed network is not constrained for this purpose.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08715v1
PDF	https://arxiv.org/pdf/1911.08715v1.pdf
PWC	https://paperswithcode.com/paper/an-inception-inspired-deep-network-to-analyse
Repo
Framework

Multilingual, Multi-scale and Multi-layer Visualization of Intermediate Representations


Title	Multilingual, Multi-scale and Multi-layer Visualization of Intermediate Representations
Authors	Carlos Escolano, Marta R. Costa-jussà, Elora Lacroux, Pere-Pau Vázquez
Abstract	The main alternatives nowadays to deal with sequences are Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN) architectures and the Transformer. In this context, RNN’s, CNN’s and Transformer have most commonly been used as an encoder-decoder architecture with multiple layers in each module. Far beyond this, these architectures are the basis for the contextual word embeddings which are revolutionizing most natural language downstream applications. However, intermediate layer representations in sequence-based architectures can be difficult to interpret. To make each layer representation within these architectures more accessible and meaningful, we introduce a web-based tool that visualizes them both at the sentence and token level. We present three use cases. The first analyses gender issues in contextual word embeddings. The second and third are showing multilingual intermediate representations for sentences and tokens and the evolution of these intermediate representations along the multiple layers of the decoder and in the context of multilingual machine translation.
Tasks	Machine Translation, Word Embeddings
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00810v1
PDF	https://arxiv.org/pdf/1907.00810v1.pdf
PWC	https://paperswithcode.com/paper/multilingual-multi-scale-and-multi-layer
Repo
Framework

Deep Exemplar-based Video Colorization


Title	Deep Exemplar-based Video Colorization
Authors	Bo Zhang, Mingming He, Jing Liao, Pedro V. Sander, Lu Yuan, Amine Bermak, Dong Chen
Abstract	This paper presents the first end-to-end network for exemplar-based video colorization. The main challenge is to achieve temporal consistency while remaining faithful to the reference style. To address this issue, we introduce a recurrent framework that unifies the semantic correspondence and color propagation steps. Both steps allow a provided reference image to guide the colorization of every frame, thus reducing accumulated propagation errors. Video frames are colorized in sequence based on the colorization history, and its coherency is further enforced by the temporal consistency loss. All of these components, learned end-to-end, help produce realistic videos with good temporal stability. Experiments show our result is superior to the state-of-the-art methods both quantitatively and qualitatively.
Tasks	Colorization
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09909v1
PDF	https://arxiv.org/pdf/1906.09909v1.pdf
PWC	https://paperswithcode.com/paper/deep-exemplar-based-video-colorization-1
Repo
Framework

The CNN-based Coronary Occlusion Site Localization with Effective Preprocessing Method


Title	The CNN-based Coronary Occlusion Site Localization with Effective Preprocessing Method
Authors	YeongHyeon Park, Il Dong Yun, Si-Hyuck Kang
Abstract	The Coronary Artery Occlusion (CAO) acutely comes to human, and it highly threats the human’s life. When CAO detected, Percutaneous Coronary Intervention (PCI) should be conducted timely. Before PCI, localizing the CAO is needed firstly, because the heart is covered with various arteries. We handle the three kinds of CAO in this paper and our purpose is not only localization of CAO but also improving the localizing performance via preprocessing method. We improve localization performance from a minimum of 0.150 to a maximum of 0.372 via our noise reduction and pulse extraction based method.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08375v2
PDF	https://arxiv.org/pdf/1912.08375v2.pdf
PWC	https://paperswithcode.com/paper/the-cnn-based-coronary-occlusion-site
Repo
Framework

Query Optimization Properties of Modified VBS


Title	Query Optimization Properties of Modified VBS
Authors	Mieczysław A. Kłopotek, Sławomir T. Wierzchoń
Abstract	Valuation-Based~System can represent knowledge in different domains including probability theory, Dempster-Shafer theory and possibility theory. More recent studies show that the framework of VBS is also appropriate for representing and solving Bayesian decision problems and optimization problems. In this paper after introducing the valuation based system (VBS) framework, we present Markov-like properties of VBS and a method for resolving queries to VBS.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12032v1
PDF	https://arxiv.org/pdf/1909.12032v1.pdf
PWC	https://paperswithcode.com/paper/query-optimization-properties-of-modified-vbs
Repo
Framework

GANPOP: Generative Adversarial Network Prediction of Optical Properties from Single Snapshot Wide-field Images


Title	GANPOP: Generative Adversarial Network Prediction of Optical Properties from Single Snapshot Wide-field Images
Authors	Mason T. Chen, Faisal Mahmood, Jordan A. Sweer, Nicholas J. Durr
Abstract	We present a deep learning framework for wide-field, content-aware estimation of absorption and scattering coefficients of tissues, called Generative Adversarial Network Prediction of Optical Properties (GANPOP). Spatial frequency domain imaging is used to obtain ground-truth optical properties from in vivo human hands, freshly resected human esophagectomy samples and homogeneous tissue phantoms. Images of objects with either flat-field or structured illumination are paired with registered optical property maps and are used to train conditional generative adversarial networks that estimate optical properties from a single input image. We benchmark this approach by comparing GANPOP to a single-snapshot optical property (SSOP) technique, using a normalized mean absolute error (NMAE) metric. In human gastrointestinal specimens, GANPOP estimates both reduced scattering and absorption coefficients at 660 nm from a single 0.2/mm spatial frequency illumination image with 58% higher accuracy than SSOP. When applied to both in vivo and ex vivo swine tissues, a GANPOP model trained solely on human specimens and phantoms estimates optical properties with approximately 43% improvement over SSOP, indicating adaptability to sample variety. Moreover, we demonstrate that GANPOP estimates optical properties from flat-field illumination images with similar error to SSOP, which requires structured-illumination. Given a training set that appropriately spans the target domain, GANPOP has the potential to enable rapid and accurate wide-field measurements of optical properties, even from conventional imaging systems with flat-field illumination.
Tasks
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05360v2
PDF	https://arxiv.org/pdf/1906.05360v2.pdf
PWC	https://paperswithcode.com/paper/ganpop-generative-adversarial-network
Repo
Framework

The lexical and grammatical sources of neg-raising inferences


Title	The lexical and grammatical sources of neg-raising inferences
Authors	Hannah Youngeun An, Aaron Steven White
Abstract	We investigate neg(ation)-raising inferences, wherein negation on a predicate can be interpreted as though in that predicate’s subordinate clause. To do this, we collect a large-scale dataset of neg-raising judgments for effectively all English clause-embedding verbs and develop a model to jointly induce the semantic types of verbs and their subordinate clauses and the relationship of these types to neg-raising inferences. We find that some neg-raising inferences are attributable to properties of particular predicates, while others are attributable to subordinate clause structure.
Tasks
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05253v3
PDF	https://arxiv.org/pdf/1908.05253v3.pdf
PWC	https://paperswithcode.com/paper/the-lexical-and-grammatical-sources-of-neg
Repo
Framework

Dense Feature Aggregation and Pruning for RGBT Tracking


Title	Dense Feature Aggregation and Pruning for RGBT Tracking
Authors	Yabin Zhu, Chenglong Li, Bin Luo, Jin Tang, Xiao Wang
Abstract	How to perform effective information fusion of different modalities is a core factor in boosting the performance of RGBT tracking. This paper presents a novel deep fusion algorithm based on the representations from an end-to-end trained convolutional neural network. To deploy the complementarity of features of all layers, we propose a recursive strategy to densely aggregate these features that yield robust representations of target objects in each modality. In different modalities, we propose to prune the densely aggregated features of all modalities in a collaborative way. In a specific, we employ the operations of global average pooling and weighted random selection to perform channel scoring and selection, which could remove redundant and noisy features to achieve more robust feature representation. Experimental results on two RGBT tracking benchmark datasets suggest that our tracker achieves clear state-of-the-art against other RGB and RGBT tracking methods.
Tasks
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10451v1
PDF	https://arxiv.org/pdf/1907.10451v1.pdf
PWC	https://paperswithcode.com/paper/dense-feature-aggregation-and-pruning-for
Repo
Framework

Risks of Using Non-verified Open Data: A case study on using Machine Learning techniques for predicting Pregnancy Outcomes in India


Title	Risks of Using Non-verified Open Data: A case study on using Machine Learning techniques for predicting Pregnancy Outcomes in India
Authors	Anusua Trivedi, Sumit Mukherjee, Edmund Tse, Anne Ewing, Juan Lavista Ferres
Abstract	Artificial intelligence (AI) has evolved considerably in the last few years. While applications of AI is now becoming more common in fields like retail and marketing, application of AI in solving problems related to developing countries is still an emerging topic. Specially, AI applications in resource-poor settings remains relatively nascent. There is a huge scope of AI being used in such settings. For example, researchers have started exploring AI applications to reduce poverty and deliver a broad range of critical public services. However, despite many promising use cases, there are many dataset related challenges that one has to overcome in such projects. These challenges often take the form of missing data, incorrectly collected data and improperly labeled variables, among other factors. As a result, we can often end up using data that is not representative of the problem we are trying to solve. In this case study, we explore the challenges of using such an open dataset from India, to predict an important health outcome. We highlight how the use of AI without proper understanding of reporting metrics can lead to erroneous conclusions.
Tasks
Published	2019-10-04
URL	https://arxiv.org/abs/1910.02136v2
PDF	https://arxiv.org/pdf/1910.02136v2.pdf
PWC	https://paperswithcode.com/paper/risks-of-using-non-verified-open-data-a-case
Repo
Framework

A Complementary Learning Systems Approach to Temporal Difference Learning


Title	A Complementary Learning Systems Approach to Temporal Difference Learning
Authors	Sam Blakeman, Denis Mareschal
Abstract	Complementary Learning Systems (CLS) theory suggests that the brain uses a ‘neocortical’ and a ‘hippocampal’ learning system to achieve complex behavior. These two systems are complementary in that the ‘neocortical’ system relies on slow learning of distributed representations while the ‘hippocampal’ system relies on fast learning of pattern-separated representations. Both of these systems project to the striatum, which is a key neural structure in the brain’s implementation of Reinforcement Learning (RL). Current deep RL approaches share similarities with a ‘neocortical’ system because they slowly learn distributed representations through backpropagation in Deep Neural Networks (DNNs). An ongoing criticism of such approaches is that they are data inefficient and lack flexibility. CLS theory suggests that the addition of a ‘hippocampal’ system could address these criticisms. In the present study we propose a novel algorithm known as Complementary Temporal Difference Learning (CTDL), which combines a DNN with a Self-Organising Map (SOM) to obtain the benefits of both a ‘neocortical’ and a ‘hippocampal’ system. Key features of CTDL include the use of Temporal Difference (TD) error to update a SOM and the combination of a SOM and DNN to calculate action values. We evaluate CTDL on grid worlds and the Cart-Pole environment, and show several benefits over the classic Deep Q-Network (DQN) approach. These results demonstrate (1) the utility of complementary learning systems for the evaluation of actions, (2) that the TD error signal is a useful form of communication between the two systems and (3) the biological plausibility of the proposed approach.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02636v1
PDF	https://arxiv.org/pdf/1905.02636v1.pdf
PWC	https://paperswithcode.com/paper/a-complementary-learning-systems-approach-to
Repo
Framework

E-Gotsky: Sequencing Content using the Zone of Proximal Development


Title	E-Gotsky: Sequencing Content using the Zone of Proximal Development
Authors	Oded Vainas, Ori Bar-Ilan, Yossi Ben-David, Ran Gilad-Bachrach, Galit Lukin, Meitar Ronen, Roi Shillo, Daniel Sitton
Abstract	Vygotsky’s notions of Zone of Proximal Development and Dynamic Assessment emphasize the importance of personalized learning that adapts to the needs and abilities of the learners and enables more efficient learning. In this work we introduce a novel adaptive learning engine called E-gostky that builds on these concepts to personalize the learning path within an e-learning system. E-gostky uses machine learning techniques to select the next content item that will challenge the student but will not be overwhelming, keeping students in their Zone of Proximal Development. To evaluate the system, we conducted an experiment where hundreds of students from several different elementary schools used our engine to learn fractions for five months. Our results show that using E-gostky can significantly reduce the time required to reach similar mastery. Specifically, in our experiment, it took students who were using the adaptive learning engine $17%$ less time to reach a similar level of mastery as of those who didn’t. Moreover, students made greater efforts to find the correct answer rather than guessing and class teachers reported that even students with learning disabilities showed higher engagement.
Tasks
Published	2019-04-28
URL	http://arxiv.org/abs/1904.12268v1
PDF	http://arxiv.org/pdf/1904.12268v1.pdf
PWC	https://paperswithcode.com/paper/e-gotsky-sequencing-content-using-the-zone-of
Repo
Framework