January 29, 2020

3279 words 16 mins read

Paper Group ANR 499

The effect of scene context on weakly supervised semantic segmentation. Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives. Suspicion-Free Adversarial Attacks on Clustering Algorithms. Semantic Hypergraphs. Investigating the Effect of Attributes on User Trust in Social Media. An Analysis of Att …

The effect of scene context on weakly supervised semantic segmentation


Title	The effect of scene context on weakly supervised semantic segmentation
Authors	Mohammad Kamalzare, Reza Kahani, Alireza Talebpour, Ahmad Mahmoudi-Aznaveh
Abstract	Image semantic segmentation is parsing image into several partitions in such a way that each region of which involves a semantic concept. In a weakly supervised manner, since only image-level labels are available, discriminating objects from the background is challenging, and in some cases, much more difficult. More specifically, some objects which are commonly seen in one specific scene (e.g. ‘train’ typically is seen on ‘railroad track’) are much more likely to be confused. In this paper, we propose a method to add the target-specific scenes in order to overcome the aforementioned problem. Actually, we propose a scene recommender which suggests to add some specific scene contexts to the target dataset in order to train the model more accurately. It is notable that this idea could be a complementary part of the baselines of many other methods. The experiments validate the effectiveness of the proposed method for the objects for which the scene context is added.
Tasks	Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2019-02-12
URL	https://arxiv.org/abs/1902.04356v2
PDF	https://arxiv.org/pdf/1902.04356v2.pdf
PWC	https://paperswithcode.com/paper/the-effect-of-scene-context-on-weakly
Repo
Framework

Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives


Title	Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
Authors	Yi Tay, Shuohang Wang, Luu Anh Tuan, Jie Fu, Minh C. Phan, Xingdi Yuan, Jinfeng Rao, Siu Cheung Hui, Aston Zhang
Abstract	This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty. This can be interpreted as a form of domain randomization and/or generative pretraining during training. To this end, the usage of the Pointer-Generator softens the requirement of having the answer within the context, enabling us to construct diverse training samples for learning. Additionally, we propose a new Introspective Alignment Layer (IAL), which reasons over decomposed alignments using block-based self-attention. We evaluate our proposed method on the NarrativeQA reading comprehension benchmark, achieving state-of-the-art performance, improving existing baselines by $51%$ relative improvement on BLEU-4 and $17%$ relative improvement on Rouge-L. Extensive ablations confirm the effectiveness of our proposed IAL and CL components.
Tasks	Reading Comprehension
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10847v1
PDF	https://arxiv.org/pdf/1905.10847v1.pdf
PWC	https://paperswithcode.com/paper/simple-and-effective-curriculum-pointer
Repo
Framework

Suspicion-Free Adversarial Attacks on Clustering Algorithms


Title	Suspicion-Free Adversarial Attacks on Clustering Algorithms
Authors	Anshuman Chhabra, Abhishek Roy, Prasant Mohapatra
Abstract	Clustering algorithms are used in a large number of applications and play an important role in modern machine learning– yet, adversarial attacks on clustering algorithms seem to be broadly overlooked unlike supervised learning. In this paper, we seek to bridge this gap by proposing a black-box adversarial attack for clustering models for linearly separable clusters. Our attack works by perturbing a single sample close to the decision boundary, which leads to the misclustering of multiple unperturbed samples, named spill-over adversarial samples. We theoretically show the existence of such adversarial samples for the K-Means clustering. Our attack is especially strong as (1) we ensure the perturbed sample is not an outlier, hence not detectable, and (2) the exact metric used for clustering is not known to the attacker. We theoretically justify that the attack can indeed be successful without the knowledge of the true metric. We conclude by providing empirical results on a number of datasets, and clustering algorithms. To the best of our knowledge, this is the first work that generates spill-over adversarial samples without the knowledge of the true metric ensuring that the perturbed sample is not an outlier, and theoretically proves the above.
Tasks	Adversarial Attack
Published	2019-11-16
URL	https://arxiv.org/abs/1911.07015v1
PDF	https://arxiv.org/pdf/1911.07015v1.pdf
PWC	https://paperswithcode.com/paper/suspicion-free-adversarial-attacks-on
Repo
Framework

Semantic Hypergraphs


Title	Semantic Hypergraphs
Authors	Telmo Menezes, Camille Roth
Abstract	Existing computational methods for the analysis of corpora of text in natural language are still far from approaching a human level of understanding. We attempt to advance the state of the art by introducing a model and algorithmic framework to transform text into recursively structured data. We apply this to the analysis of news titles extracted from a social news aggregation website. We show that a recursive ordered hypergraph is a sufficiently generic structure to represent significant number of fundamental natural language constructs, with advantages over conventional approaches such as semantic graphs. We present a pipeline of transformations from the output of conventional NLP algorithms to such hypergraphs, which we denote as semantic hypergraphs. The features of these transformations include the creation of new concepts from existing ones, the organisation of statements into regular structures of predicates followed by an arbitrary number of entities and the ability to represent statements about other statements. We demonstrate knowledge inference from the hypergraph, identifying claims and expressions of conflicts, along with their participating actors and topics. We show how this enables the actor-centric summarization of conflicts, comparison of topics of claims between actors and networks of conflicts between actors in the context of a given topic. On the whole, we propose a hypergraphic knowledge representation model that can be used to provide effective overviews of a large corpus of text in natural language.
Tasks
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10784v1
PDF	https://arxiv.org/pdf/1908.10784v1.pdf
PWC	https://paperswithcode.com/paper/semantic-hypergraphs
Repo
Framework


Title	Investigating the Effect of Attributes on User Trust in Social Media
Authors	Jamal Al Qundus, Adrian Paschke
Abstract	One main challenge in social media is to identify trustworthy information. If we cannot recognize information as trustworthy, that information may become useless or be lost. Opposite, we could consume wrong or fake information with major consequences. How does a user handle the information provided before consuming it? Are the comments on a post, the author or votes essential for taking such a decision? Are these attributes considered together and which attribute is more important? To answer these questions, we developed a trust model to support knowledge sharing of user content in social media. This trust model is based on the dimensions of stability, quality, and credibility. Each dimension contains metrics (user role, user IQ, votes, etc.) that are important to the user based on data analysis. We present in this paper, an evaluation of the proposed trust model using conjoint analysis (CA) as an evaluation method. The results obtained from 348 responses, validate the trust model. A trust degree translator interprets the content as very trusted, trusted, untrusted, and very untrusted based on the calculated value of trust. Furthermore, the results show different importance for each dimension: stability 24%, credibility 35% and quality 41%.
Tasks
Published	2019-04-16
URL	http://arxiv.org/abs/1904.07569v1
PDF	http://arxiv.org/pdf/1904.07569v1.pdf
PWC	https://paperswithcode.com/paper/investigating-the-effect-of-attributes-on
Repo
Framework

An Analysis of Attention over Clinical Notes for Predictive Tasks


Title	An Analysis of Attention over Clinical Notes for Predictive Tasks
Authors	Sarthak Jain, Ramin Mohammadi, Byron C. Wallace
Abstract	The shift to electronic medical records (EMRs) has engendered research into machine learning and natural language technologies to analyze patient records, and to predict from these clinical outcomes of interest. Two observations motivate our aims here. First, unstructured notes contained within EMR often contain key information, and hence should be exploited by models. Second, while strong predictive performance is important, interpretability of models is perhaps equally so for applications in this domain. Together, these points suggest that neural models for EMR may benefit from incorporation of attention over notes, which one may hope will both yield performance gains and afford transparency in predictions. In this work we perform experiments to explore this question using two EMR corpora and four different predictive tasks, that: (i) inclusion of attention mechanisms is critical for neural encoder modules that operate over notes fields in order to yield competitive performance, but, (ii) unfortunately, while these boost predictive performance, it is decidedly less clear whether they provide meaningful support for predictions.
Tasks
Published	2019-04-05
URL	http://arxiv.org/abs/1904.03244v1
PDF	http://arxiv.org/pdf/1904.03244v1.pdf
PWC	https://paperswithcode.com/paper/an-analysis-of-attention-over-clinical-notes
Repo
Framework

Improving Outfit Recommendation with Co-supervision of Fashion Generation


Title	Improving Outfit Recommendation with Co-supervision of Fashion Generation
Authors	Yujie Lin, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Jun Ma, Maarten de Rijke
Abstract	The task of fashion recommendation includes two main challenges: visual understanding and visual matching. Visual understanding aims to extract effective visual features. Visual matching aims to model a human notion of compatibility to compute a match between fashion items. Most previous studies rely on recommendation loss alone to guide visual understanding and matching. Although the features captured by these methods describe basic characteristics (e.g., color, texture, shape) of the input items, they are not directly related to the visual signals of the output items (to be recommended). This is problematic because the aesthetic characteristics (e.g., style, design), based on which we can directly infer the output items, are lacking. Features are learned under the recommendation loss alone, where the supervision signal is simply whether the given two items are matched or not. To address this problem, we propose a neural co-supervision learning framework, called the FAshion Recommendation Machine (FARM). FARM improves visual understanding by incorporating the supervision of generation loss, which we hypothesize to be able to better encode aesthetic information. FARM enhances visual matching by introducing a novel layer-to-layer matching mechanism to fuse aesthetic information more effectively, and meanwhile avoiding paying too much attention to the generation quality and ignoring the recommendation performance. Extensive experiments on two publicly available datasets show that FARM outperforms state-of-the-art models on outfit recommendation, in terms of AUC and MRR. Detailed analyses of generated and recommended items demonstrate that FARM can encode better features and generate high quality images as references to improve recommendation performance.
Tasks
Published	2019-08-24
URL	https://arxiv.org/abs/1908.09104v1
PDF	https://arxiv.org/pdf/1908.09104v1.pdf
PWC	https://paperswithcode.com/paper/improving-outfit-recommendation-with-co
Repo
Framework

Novel Artificial Human Optimization Field Algorithms - The Beginning


Title	Novel Artificial Human Optimization Field Algorithms - The Beginning
Authors	Satish Gajawada, Hassan Mustafa
Abstract	New Artificial Human Optimization (AHO) Field Algorithms can be created from scratch or by adding the concept of Artificial Humans into other existing Optimization Algorithms. Particle Swarm Optimization (PSO) has been very popular for solving complex optimization problems due to its simplicity. In this work, new Artificial Human Optimization Field Algorithms are created by modifying existing PSO algorithms with AHO Field Concepts. These Hybrid PSO Algorithms comes under PSO Field as well as AHO Field. There are Hybrid PSO research articles based on Human Behavior, Human Cognition and Human Thinking etc. But there are no Hybrid PSO articles which based on concepts like Human Disease, Human Kindness and Human Relaxation. This paper proposes new AHO Field algorithms based on these research gaps. Some existing Hybrid PSO algorithms are given a new name in this work so that it will be easy for future AHO researchers to find these novel Artificial Human Optimization Field Algorithms. A total of 6 Artificial Human Optimization Field algorithms titled “Human Safety Particle Swarm Optimization (HuSaPSO)", “Human Kindness Particle Swarm Optimization (HKPSO)", “Human Relaxation Particle Swarm Optimization (HRPSO)", “Multiple Strategy Human Particle Swarm Optimization (MSHPSO)", “Human Thinking Particle Swarm Optimization (HTPSO)” and “Human Disease Particle Swarm Optimization (HDPSO)” are tested by applying these novel algorithms on Ackley, Beale, Bohachevsky, Booth and Three-Hump Camel Benchmark Functions. Results obtained are compared with PSO algorithm.
Tasks
Published	2019-03-26
URL	http://arxiv.org/abs/1903.12011v1
PDF	http://arxiv.org/pdf/1903.12011v1.pdf
PWC	https://paperswithcode.com/paper/novel-artificial-human-optimization-field
Repo
Framework

Towards a Unified Evaluation of Explanation Methods without Ground Truth


Title	Towards a Unified Evaluation of Explanation Methods without Ground Truth
Authors	Hao Zhang, Jiayi Chen, Haotian Xue, Quanshi Zhang
Abstract	This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges. The core challenge is that people usually cannot obtain ground-truth explanations of the neural network. To this end, we design four metrics to evaluate explanation results without ground-truth explanations. Our metrics can be broadly applied to nine benchmark methods of interpreting neural networks, which provides new insights of explanation methods.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.09017v1
PDF	https://arxiv.org/pdf/1911.09017v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-unified-evaluation-of-explanation
Repo
Framework

Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey


Title	Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
Authors	Görkem Algan, Ilkay Ulusoy
Abstract	Image classification systems recently made a big leap with the advancement of deep neural networks. However, these systems require excessive amount of labeled data in order to be trained properly. This is not always feasible due to several factors, such as expensiveness of labeling process or difficulty of correctly classifying data even for the experts. Because of these practical challenges, label noise is a common problem in datasets and numerous methods to train deep networks with label noise are proposed in literature. Deep networks are known to be relatively robust to label noise, however their tendency to overfit data makes them vulnerable to memorizing even total random noise. Therefore, it is crucial to consider the existence of label noise and develop counter algorithms to fade away its negative effects for training deep neural networks efficiently. Even though an extensive survey of machine learning techniques under label noise exists, literature lacks a comprehensive survey of methodologies specifically centered around deep learning in the presence of noisy labels. This paper aims to present these algorithms while categorizing them according to their similarity in proposed methodology.
Tasks	Image Classification
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05170v1
PDF	https://arxiv.org/pdf/1912.05170v1.pdf
PWC	https://paperswithcode.com/paper/image-classification-with-deep-learning-in
Repo
Framework

Representing Attitudes Towards Ambiguity in Hilbert Space: Foundations and Applications


Title	Representing Attitudes Towards Ambiguity in Hilbert Space: Foundations and Applications
Authors	Sandro Sozzo
Abstract	We provide here a general mathematical framework to model attitudes towards ambiguity which uses the formalism of quantum theory as a ``purely mathematical formalism, detached from any physical interpretation’'. We show that the quantum-theoretic framework enables modelling of the “Ellsberg paradox”, but it also successfully applies to more concrete human decision-making (DM) tests involving financial, managerial and medical decisions. In particular, we elaborate a mathematical representation of various empirical studies which reveal that attitudes of managers towards uncertainty shift from “ambiguity seeking” to “ambiguity aversion”, and viceversa, thus exhibiting “hope effects” and “fear effects”. The present framework provides a promising direction towards the development of a unified theory of decisions in the presence of uncertainty. \|
Tasks	Decision Making
Published	2019-07-10
URL	https://arxiv.org/abs/1907.06314v2
PDF	https://arxiv.org/pdf/1907.06314v2.pdf
PWC	https://paperswithcode.com/paper/representing-attitudes-towards-ambiguity-in
Repo
Framework

Label-Conditioned Next-Frame Video Generation with Neural Flows


Title	Label-Conditioned Next-Frame Video Generation with Neural Flows
Authors	David Donahue
Abstract	Recent state-of-the-art video generation systems employ Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs) to produce novel videos. However, VAE models typically produce blurry outputs when faced with sub-optimal conditioning of the input, and GANs are known to be unstable for large output sizes. In addition, the output videos of these models are difficult to evaluate, partly because the GAN loss function is not an accurate measure of convergence. In this work, we propose using a state-of-the-art neural flow generator called Glow to generate videos conditioned on a textual label, one frame at a time. Neural flow models are more stable than standard GANs, as they only optimize a single cross entropy loss function, which is monotonic and avoids the circular convergence issues of the GAN minimax objective. In addition, we also show how to condition Glow on external context, while still preserving the invertible nature of each “flow” layer. Finally, we evaluate the proposed Glow model by calculating cross entropy on a held-out validation set of videos, in order to compare multiple versions of the proposed model via an ablation study. We show generated videos and discuss future improvements.
Tasks	Video Generation
Published	2019-10-16
URL	https://arxiv.org/abs/1910.11106v1
PDF	https://arxiv.org/pdf/1910.11106v1.pdf
PWC	https://paperswithcode.com/paper/label-conditioned-next-frame-video-generation
Repo
Framework

An Information Theoretic Interpretation to Deep Neural Networks


Title	An Information Theoretic Interpretation to Deep Neural Networks
Authors	Shao-Lun Huang, Xiangxiang Xu, Lizhong Zheng, Gregory W. Wornell
Abstract	It is commonly believed that the hidden layers of deep neural networks (DNNs) attempt to extract informative features for learning tasks. In this paper, we formalize this intuition by showing that the features extracted by DNN coincide with the result of an optimization problem, which we call the `universal feature selection’ problem, in a local analysis regime. We interpret the weights training in DNN as the projection of feature functions between feature spaces, specified by the network structure. Our formulation has direct operational meaning in terms of the performance for inference tasks, and gives interpretations to the internal computation results of DNNs. Results of numerical experiments are provided to support the analysis. \|
Tasks	Feature Selection
Published	2019-05-16
URL	https://arxiv.org/abs/1905.06600v1
PDF	https://arxiv.org/pdf/1905.06600v1.pdf
PWC	https://paperswithcode.com/paper/an-information-theoretic-interpretation-to
Repo
Framework

Hybrid Density- and Partition-based Clustering Algorithm for Data with Mixed-type Variables


Title	Hybrid Density- and Partition-based Clustering Algorithm for Data with Mixed-type Variables
Authors	Shu Wang, Jonathan G. Yabes, Chung-Chou H. Chang
Abstract	Clustering is an essential technique for discovering patterns in data. The steady increase in amount and complexity of data over the years led to improvements and development of new clustering algorithms. However, algorithms that can cluster data with mixed variable types (continuous and categorical) remain limited, despite the abundance of data with mixed types particularly in the medical field. Among existing methods for mixed data, some posit unverifiable distributional assumptions or that the contributions of different variable types are not well balanced. We propose a two-step hybrid density- and partition-based algorithm (HyDaP) that can detect clusters after variables selection. The first step involves both density-based and partition-based algorithms to identify the data structure formed by continuous variables and recognize the important variables for clustering; the second step involves partition-based algorithm together with a novel dissimilarity measure we designed for mixed data to obtain clustering results. Simulations across various scenarios and data structures were conducted to examine the performance of the HyDaP algorithm compared to commonly used methods. We also applied the HyDaP algorithm on electronic health records to identify sepsis phenotypes.
Tasks
Published	2019-05-06
URL	https://arxiv.org/abs/1905.02257v1
PDF	https://arxiv.org/pdf/1905.02257v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-density-and-partition-based-clustering
Repo
Framework

A Winograd-based Integrated Photonics Accelerator for Convolutional Neural Networks


Title	A Winograd-based Integrated Photonics Accelerator for Convolutional Neural Networks
Authors	Armin Mehrabian, Mario Miscuglio, Yousra Alkabani, Volker J. Sorger, Tarek El-Ghazawi
Abstract	Neural Networks (NNs) have become the mainstream technology in the artificial intelligence (AI) renaissance over the past decade. Among different types of neural networks, convolutional neural networks (CNNs) have been widely adopted as they have achieved leading results in many fields such as computer vision and speech recognition. This success in part is due to the widespread availability of capable underlying hardware platforms. Applications have always been a driving factor for design of such hardware architectures. Hardware specialization can expose us to novel architectural solutions, which can outperform general purpose computers for tasks at hand. Although different applications demand for different performance measures, they all share speed and energy efficiency as high priorities. Meanwhile, photonics processing has seen a resurgence due to its inherited high speed and low power nature. Here, we investigate the potential of using photonics in CNNs by proposing a CNN accelerator design based on Winograd filtering algorithm. Our evaluation results show that while a photonic accelerator can compete with current-state-of-the-art electronic platforms in terms of both speed and power, it has the potential to improve the energy efficiency by up to three orders of magnitude.
Tasks	Speech Recognition
Published	2019-06-25
URL	https://arxiv.org/abs/1906.10487v2
PDF	https://arxiv.org/pdf/1906.10487v2.pdf
PWC	https://paperswithcode.com/paper/a-winograd-based-integrated-photonics
Repo
Framework