January 29, 2020

3166 words 15 mins read

Paper Group ANR 624

End-to-End Conditional GAN-based Architectures for Image Colourisation. Classifying Multilingual User Feedback using Traditional Machine Learning and Deep Learning. Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback. Sample size calculations for the experimental comparison of multiple algorithms on …

End-to-End Conditional GAN-based Architectures for Image Colourisation


Title	End-to-End Conditional GAN-based Architectures for Image Colourisation
Authors	Marc Górriz, Marta Mrak, Alan F. Smeaton, Noel E. O’Connor
Abstract	In this work recent advances in conditional adversarial networks are investigated to develop an end-to-end architecture based on Convolutional Neural Networks (CNNs) to directly map realistic colours to an input greyscale image. Observing that existing colourisation methods sometimes exhibit a lack of colourfulness, this paper proposes a method to improve colourisation results. In particular, the method uses Generative Adversarial Neural Networks (GANs) and focuses on improvement of training stability to enable better generalisation in large multi-class image datasets. Additionally, the integration of instance and batch normalisation layers in both generator and discriminator is introduced to the popular U-Net architecture, boosting the network capabilities to generalise the style changes of the content. The method has been tested using the ILSVRC 2012 dataset, achieving improved automatic colourisation results compared to other methods based on GANs.
Tasks
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09873v2
PDF	https://arxiv.org/pdf/1908.09873v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-conditional-gan-based
Repo
Framework

Classifying Multilingual User Feedback using Traditional Machine Learning and Deep Learning


Title	Classifying Multilingual User Feedback using Traditional Machine Learning and Deep Learning
Authors	Christoph Stanik, Marlo Haering, Walid Maalej
Abstract	With the rise of social media like Twitter and of software distribution platforms like app stores, users got various ways to express their opinion about software products. Popular software vendors get user feedback thousandfold per day. Research has shown that such feedback contains valuable information for software development teams such as problem reports or feature and support inquires. Since the manual analysis of user feedback is cumbersome and hard to manage many researchers and tool vendors suggested to use automated analyses based on traditional supervised machine learning approaches. In this work, we compare the results of traditional machine learning and deep learning in classifying user feedback in English and Italian into problem reports, inquiries, and irrelevant. Our results show that using traditional machine learning, we can still achieve comparable results to deep learning, although we collected thousands of labels.
Tasks
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05504v1
PDF	https://arxiv.org/pdf/1909.05504v1.pdf
PWC	https://paperswithcode.com/paper/classifying-multilingual-user-feedback-using
Repo
Framework

Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback


Title	Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback
Authors	Taku Yamagata, Raúl Santos-Rodríguez, Ryan McConville, Atis Elsts
Abstract	Recent advances in both machine learning and Internet-of-Things have attracted attention to automatic Activity Recognition, where users wear a device with sensors and their outputs are mapped to a predefined set of activities. However, few studies have considered the balance between wearable power consumption and activity recognition accuracy. This is particularly important when part of the computational load happens on the wearable device. In this paper, we present a new methodology to perform feature selection on the device based on Reinforcement Learning (RL) to find the optimum balance between power consumption and accuracy. To accelerate the learning speed, we extend the RL algorithm to address multiple sources of feedback, and use them to tailor the policy in conjunction with estimating the feedback accuracy. We evaluated our system on the SPHERE challenge dataset, a publicly available research dataset. The results show that our proposed method achieves a good trade-off between wearable power consumption and activity recognition accuracy.
Tasks	Activity Recognition, Feature Selection
Published	2019-08-16
URL	https://arxiv.org/abs/1908.06134v1
PDF	https://arxiv.org/pdf/1908.06134v1.pdf
PWC	https://paperswithcode.com/paper/online-feature-selection-for-activity
Repo
Framework

Sample size calculations for the experimental comparison of multiple algorithms on multiple problem instances


Title	Sample size calculations for the experimental comparison of multiple algorithms on multiple problem instances
Authors	Felipe Campelo, Elizabeth F. Wanner
Abstract	This work presents a statistically principled method for estimating the required number of instances in the experimental comparison of multiple algorithms on a given problem class of interest. This approach generalises earlier results by allowing researchers to design experiments based on the desired best, worst, mean or median-case statistical power to detect differences between algorithms larger than a certain threshold. Holm’s step-down procedure is used to maintain the overall significance level controlled at desired levels, without resulting in overly conservative experiments. This paper also presents an approach for sampling each algorithm on each instance, based on optimal sample size ratios that minimise the total required number of runs subject to a desired accuracy in the estimation of paired differences. A case study investigating the effect of 21 variants of a custom-tailored Simulated Annealing for a class of scheduling problems is used to illustrate the application of the proposed methods for sample size calculations in the experimental comparison of algorithms.
Tasks
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01720v1
PDF	https://arxiv.org/pdf/1908.01720v1.pdf
PWC	https://paperswithcode.com/paper/sample-size-calculations-for-the-experimental
Repo
Framework

Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation


Title	Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation
Authors	Renhao Wang, Adam Scibior, Frank Wood
Abstract	Imitation learning is a promising approach to end-to-end training of autonomous vehicle controllers. Typically the driving process with such approaches is entirely automatic and black-box, although in practice it is desirable to control the vehicle through high-level commands, such as telling it which way to go at an intersection. In existing work this has been accomplished by the application of a branched neural architecture, since directly providing the command as an additional input to the controller often results in the command being ignored. In this work we overcome this limitation by learning a disentangled probabilistic latent variable model that generates the steering commands. We achieve faithful command-conditional generation without using a branched architecture and demonstrate improved stability of the controller, applying only a variational objective without any domain-specific adjustments. On top of that, we extend our model with an additional latent variable and augment the dataset to train a controller that is robust to unsafe commands, such as asking it to turn into a wall. The main contribution of this work is a recipe for building controllable imitation driving agents that improves upon multiple aspects of the current state of the art relating to robustness and interpretability.
Tasks	Autonomous Driving, Imitation Learning
Published	2019-09-20
URL	https://arxiv.org/abs/1909.09721v2
PDF	https://arxiv.org/pdf/1909.09721v2.pdf
PWC	https://paperswithcode.com/paper/190909721
Repo
Framework

Diverse Video Captioning Through Latent Variable Expansion with Conditional GAN


Title	Diverse Video Captioning Through Latent Variable Expansion with Conditional GAN
Authors	Huanhou Xiao, Jinglun Shi
Abstract	Automatically describing video content with text description is challenging but important task, which has been attracting a lot of attention in computer vision community. Previous works mainly strive for the accuracy of the generated sentences, while ignoring the sentences diversity, which is inconsistent with human behavior. In this paper, we aim to caption each video with multiple descriptions and propose a novel framework. Concretely, for a given video, the intermediate latent variables of conventional encode-decode process are utilized as input to the conditional generative adversarial network (CGAN) with the purpose of generating diverse sentences. We adopt different CNNs as our generator that produces descriptions conditioned on latent variables and discriminator that assesses the quality of generated sentences. Simultaneously, a novel DCE metric is designed to assess the diverse captions. We evaluate our method on the benchmark datasets, where it demonstrates its ability to generate diverse descriptions and achieves superior results against other state-of-the-art methods.
Tasks	Video Captioning
Published	2019-10-26
URL	https://arxiv.org/abs/1910.12019v4
PDF	https://arxiv.org/pdf/1910.12019v4.pdf
PWC	https://paperswithcode.com/paper/diverse-video-captioning-through-latent
Repo
Framework

HERA: Partial Label Learning by Combining Heterogeneous Loss with Sparse and Low-Rank Regularization


Title	HERA: Partial Label Learning by Combining Heterogeneous Loss with Sparse and Low-Rank Regularization
Authors	Gengyu Lyu, Songhe Feng, Yi Jin, Guojun Dai, Congyan Lang, Yidong Li
Abstract	Partial Label Learning (PLL) aims to learn from the data where each training instance is associated with a set of candidate labels, among which only one is correct. Most existing methods deal with such problem by either treating each candidate label equally or identifying the ground-truth label iteratively. In this paper, we propose a novel PLL approach called HERA, which simultaneously incorporates the HeterogEneous Loss and the SpaRse and Low-rAnk procedure to estimate the labeling confidence for each instance while training the model. Specifically, the heterogeneous loss integrates the strengths of both the pairwise ranking loss and the pointwise reconstruction loss to provide informative label ranking and reconstruction information for label identification, while the embedded sparse and low-rank scheme constrains the sparsity of ground-truth label matrix and the low rank of noise label matrix to explore the global label relevance among the whole training data for improving the learning model. Extensive experiments on both artificial and real-world data sets demonstrate that our method can achieve superior or comparable performance against the state-of-the-art methods.
Tasks
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00551v1
PDF	https://arxiv.org/pdf/1906.00551v1.pdf
PWC	https://paperswithcode.com/paper/190600551
Repo
Framework

Empirical Comparisons of CNN with Other Learning Algorithms for Text Classification in Legal Document Review


Title	Empirical Comparisons of CNN with Other Learning Algorithms for Text Classification in Legal Document Review
Authors	Robert Keeling, Rishi Chhatwal, Nathaniel Huber-Fliflet, Jianping Zhang, Fusheng Wei, Haozhen Zhao, Shi Ye, Han Qin
Abstract	Research has shown that Convolutional Neural Networks (CNN) can be effectively applied to text classification as part of a predictive coding protocol. That said, most research to date has been conducted on data sets with short documents that do not reflect the variety of documents in real world document reviews. Using data from four actual reviews with documents of varying lengths, we compared CNN with other popular machine learning algorithms for text classification, including Logistic Regression, Support Vector Machine, and Random Forest. For each data set, classification models were trained with different training sample sizes using different learning algorithms. These models were then evaluated using a large randomly sampled test set of documents, and the results were compared using precision and recall curves. Our study demonstrates that CNN performed well, but that there was no single algorithm that performed the best across the combination of data sets and training sample sizes. These results will help advance research into the legal profession’s use of machine learning algorithms that maximize performance.
Tasks	Text Classification
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09499v1
PDF	https://arxiv.org/pdf/1912.09499v1.pdf
PWC	https://paperswithcode.com/paper/empirical-comparisons-of-cnn-with-other
Repo
Framework

Sparse Generative Adversarial Network


Title	Sparse Generative Adversarial Network
Authors	Shahin Mahdizadehaghdam, Ashkan Panahi, Hamid Krim
Abstract	We propose a new approach to Generative Adversarial Networks (GANs) to achieve an improved performance with additional robustness to its so-called and well recognized mode collapse. We first proceed by mapping the desired data onto a frame-based space for a sparse representation to lift any limitation of small support features prior to learning the structure. To that end we start by dividing an image into multiple patches and modifying the role of the generative network from producing an entire image, at once, to creating a sparse representation vector for each image patch. We synthesize an entire image by multiplying generated sparse representations to a pre-trained dictionary and assembling the resulting patches. This approach restricts the output of the generator to a particular structure, obtained by imposing a Union of Subspaces (UoS) model to the original training data, leading to more realistic images, while maintaining a desired diversity. To further regularize GANs in generating high-quality images and to avoid the notorious mode-collapse problem, we introduce a third player in GANs, called reconstructor. This player utilizes an auto-encoding scheme to ensure that first, the input-output relation in the generator is injective and second each real image corresponds to some input noise. We present a number of experiments, where the proposed algorithm shows a remarkably higher inception score compared to the equivalent conventional GANs.
Tasks
Published	2019-08-20
URL	https://arxiv.org/abs/1908.08930v1
PDF	https://arxiv.org/pdf/1908.08930v1.pdf
PWC	https://paperswithcode.com/paper/sparse-generative-adversarial-network
Repo
Framework

Towards Constructing a Corpus for Studying the Effects of Treatments and Substances Reported in PubMed Abstracts


Title	Towards Constructing a Corpus for Studying the Effects of Treatments and Substances Reported in PubMed Abstracts
Authors	Evgeni Stefchov, Galia Angelova, Preslav Nakov
Abstract	We present the construction of an annotated corpus of PubMed abstracts reporting about positive, negative or neutral effects of treatments or substances. Our ultimate goal is to annotate one sentence (rationale) for each abstract and to use this resource as a training set for text classification of effects discussed in PubMed abstracts. Currently, the corpus consists of 750 abstracts. We describe the automatic processing that supports the corpus construction, the manual annotation activities and some features of the medical language in the abstracts selected for the annotated corpus. It turns out that recognizing the terminology and the abbreviations is key for determining the rationale sentence. The corpus will be applied to improve our classifier, which currently has accuracy of 78.80% achieved with normalization of the abstract terms based on UMLS concepts from specific semantic groups and an SVM with a linear kernel. Finally, we discuss some other possible applications of this corpus.
Tasks	Text Classification
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01831v1
PDF	https://arxiv.org/pdf/1912.01831v1.pdf
PWC	https://paperswithcode.com/paper/towards-constructing-a-corpus-for-studying
Repo
Framework

Adaptive Neuro-Surrogate-Based Optimisation Method for Wave Energy Converters Placement Optimisation


Title	Adaptive Neuro-Surrogate-Based Optimisation Method for Wave Energy Converters Placement Optimisation
Authors	Mehdi Neshat, Ehsan Abbasnejad, Qinfeng Shi, Bradley Alexander, Markus Wagner
Abstract	The installed amount of renewable energy has expanded massively in recent years. Wave energy, with its high capacity factors has great potential to complement established sources of solar and wind energy. This study explores the problem of optimising the layout of advanced, three-tether wave energy converters in a size-constrained farm in a numerically modelled ocean environment. Simulating and computing the complicated hydrodynamic interactions in wave farms can be computationally costly, which limits optimisation methods to have just a few thousand evaluations. For dealing with this expensive optimisation problem, an adaptive neuro-surrogate optimisation (ANSO) method is proposed that consists of a surrogate Recurrent Neural Network (RNN) model trained with a very limited number of observations. This model is coupled with a fast meta-heuristic optimiser for adjusting the model’s hyper-parameters. The trained model is applied using a greedy local search with a backtracking optimisation strategy. For evaluating the performance of the proposed approach, some of the more popular and successful Evolutionary Algorithms (EAs) are compared in four real wave scenarios (Sydney, Perth, Adelaide and Tasmania). Experimental results show that the adaptive neuro model is competitive with other optimisation methods in terms of total harnessed power output and faster in terms of total computational costs.
Tasks
Published	2019-07-06
URL	https://arxiv.org/abs/1907.03076v2
PDF	https://arxiv.org/pdf/1907.03076v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-neuro-surrogate-based-optimisation
Repo
Framework

Post-Mortem Iris Recognition Resistant to Biological Eye Decay Processes


Title	Post-Mortem Iris Recognition Resistant to Biological Eye Decay Processes
Authors	Mateusz Trokielewicz, Adam Czajka, Piotr Maciejewicz
Abstract	This paper proposes an end-to-end iris recognition method designed specifically for post-mortem samples, and thus serving as a perfect application for iris biometrics in forensics. To our knowledge, it is the first method specific for verification of iris samples acquired after demise. We have fine-tuned a convolutional neural network-based segmentation model with a large set of diversified iris data (including post-mortem and diseased eyes), and combined Gabor kernels with newly designed, iris-specific kernels learnt by Siamese networks. The resulting method significantly outperforms the existing off-the-shelf iris recognition methods (both academic and commercial) on the newly collected database of post-mortem iris images and for all available time horizons since death. We make all models and the method itself available along with this paper.
Tasks	Iris Recognition
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02512v1
PDF	https://arxiv.org/pdf/1912.02512v1.pdf
PWC	https://paperswithcode.com/paper/post-mortem-iris-recognition-resistant-to
Repo
Framework

Less Is Better: Unweighted Data Subsampling via Influence Function


Title	Less Is Better: Unweighted Data Subsampling via Influence Function
Authors	Zifeng Wang, Hong Zhu, Zhenhua Dong, Xiuqiang He, Shao-Lun Huang
Abstract	In the time of Big Data, training complex models on large-scale data sets is challenging, making it appealing to reduce data volume for saving computation resources by subsampling. Most previous works in subsampling are weighted methods designed to help the performance of subset-model approach the full-set-model, hence the weighted methods have no chance to acquire a subset-model that is better than the full-set-model. However, we question that how can we achieve better model with less data? In this work, we propose a novel Unweighted Influence Data Subsampling (UIDS) method, and prove that the subset-model acquired through our method can outperform the full-set-model. Besides, we show that overly confident on a given test set for sampling is common in Influence-based subsampling methods, which can eventually cause our subset-model’s failure in out-of-sample test. To mitigate it, we develop a probabilistic sampling scheme to control the worst-case risk over all distributions close to the empirical distribution. The experiment results demonstrate our methods superiority over existed subsampling methods in diverse tasks, such as text classification, image classification, click-through prediction, etc.
Tasks	Image Classification, Text Classification
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01321v2
PDF	https://arxiv.org/pdf/1912.01321v2.pdf
PWC	https://paperswithcode.com/paper/less-is-better-unweighted-data-subsampling
Repo
Framework

Learned Indexes for Dynamic Workloads


Title	Learned Indexes for Dynamic Workloads
Authors	Chuzhe Tang, Zhiyuan Dong, Minjie Wang, Zhaoguo Wang, Haibo Chen
Abstract	The recent proposal of learned index structures opens up a new perspective on how traditional range indexes can be optimized. However, the current learned indexes assume the data distribution is relatively static and the access pattern is uniform, while real-world scenarios consist of skew query distribution and evolving data. In this paper, we demonstrate that the missing consideration of access patterns and dynamic data distribution notably hinders the applicability of learned indexes. To this end, we propose solutions for learned indexes for dynamic workloads (called Doraemon). To improve the latency for skew queries, Doraemon augments the training data with access frequencies. To address the slow model re-training when data distribution shifts, Doraemon caches the previously-trained models and incrementally fine-tunes them for similar access patterns and data distribution. Our preliminary result shows that, Doraemon improves the query latency by 45.1% and reduces the model re-training time to 1/20.
Tasks
Published	2019-02-02
URL	http://arxiv.org/abs/1902.00655v1
PDF	http://arxiv.org/pdf/1902.00655v1.pdf
PWC	https://paperswithcode.com/paper/learned-indexes-for-dynamic-workloads
Repo
Framework

Grounding Value Alignment with Ethical Principles


Title	Grounding Value Alignment with Ethical Principles
Authors	Tae Wan Kim, Thomas Donaldson, John Hooker
Abstract	An important step in the development of value alignment (VA) systems in AI is understanding how values can interrelate with facts. Designers of future VA systems will need to utilize a hybrid approach in which ethical reasoning and empirical observation interrelate successfully in machine behavior. In this article we identify two problems about this interrelation that have been overlooked by AI discussants and designers. The first problem is that many AI designers commit inadvertently a version of what has been called by moral philosophers the “naturalistic fallacy,” that is, they attempt to derive an “ought” from an “is.” We illustrate when and why this occurs. The second problem is that AI designers adopt training routines that fail fully to simulate human ethical reasoning in the integration of ethical principles and facts. Using concepts of quantified modal logic, we proceed to offer an approach that promises to simulate ethical reasoning in humans by connecting ethical principles on the one hand and propositions about states of affairs on the other.
Tasks
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05447v1
PDF	https://arxiv.org/pdf/1907.05447v1.pdf
PWC	https://paperswithcode.com/paper/grounding-value-alignment-with-ethical
Repo
Framework