October 17, 2019

3151 words 15 mins read

Paper Group ANR 904

Ranking CGANs: Subjective Control over Semantic Image Attributes. A Non-Technical Survey on Deep Convolutional Neural Network Architectures. Attention-Aware Generative Adversarial Networks (ATA-GANs). One Network to Solve All ROIs: Deep Learning CT for Any ROI using Differentiated Backprojection. Efficient sampling for Gaussian linear regression wi …

Ranking CGANs: Subjective Control over Semantic Image Attributes


Title	Ranking CGANs: Subjective Control over Semantic Image Attributes
Authors	Yassir Saquil, Kwang In Kim, Peter Hall
Abstract	In this paper, we investigate the use of generative adversarial networks in the task of image generation according to subjective measures of semantic attributes. Unlike the standard (CGAN) that generates images from discrete categorical labels, our architecture handles both continuous and discrete scales. Given pairwise comparisons of images, our model, called RankCGAN, performs two tasks: it learns to rank images using a subjective measure; and it learns a generative model that can be controlled by that measure. RankCGAN associates each subjective measure of interest to a distinct dimension of some latent space. We perform experiments on UT-Zap50K, PubFig and OSR datasets and demonstrate that the model is expressive and diverse enough to conduct two-attribute exploration and image editing.
Tasks	Image Generation
Published	2018-04-11
URL	http://arxiv.org/abs/1804.04082v3
PDF	http://arxiv.org/pdf/1804.04082v3.pdf
PWC	https://paperswithcode.com/paper/ranking-cgans-subjective-control-over
Repo
Framework

A Non-Technical Survey on Deep Convolutional Neural Network Architectures


Title	A Non-Technical Survey on Deep Convolutional Neural Network Architectures
Authors	Felix Altenberger, Claus Lenz
Abstract	Artificial neural networks have recently shown great results in many disciplines and a variety of applications, including natural language understanding, speech processing, games and image data generation. One particular application in which the strong performance of artificial neural networks was demonstrated is the recognition of objects in images, where deep convolutional neural networks are commonly applied. In this survey, we give a comprehensive introduction to this topic (object recognition with deep convolutional neural networks), with a strong focus on the evolution of network architectures. Therefore, we aim to compress the most important concepts in this field in a simple and non-technical manner to allow for future researchers to have a quick general understanding. This work is structured as follows: 1. We will explain the basic ideas of (convolutional) neural networks and deep learning and examine their usage for three object recognition tasks: image classification, object localization and object detection. 2. We give a review on the evolution of deep convolutional neural networks by providing an extensive overview of the most important network architectures presented in chronological order of their appearances.
Tasks	Image Classification, Object Detection, Object Localization, Object Recognition
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02129v1
PDF	http://arxiv.org/pdf/1803.02129v1.pdf
PWC	https://paperswithcode.com/paper/a-non-technical-survey-on-deep-convolutional
Repo
Framework

Attention-Aware Generative Adversarial Networks (ATA-GANs)


Title	Attention-Aware Generative Adversarial Networks (ATA-GANs)
Authors	Dimitris Kastaniotis, Ioanna Ntinou, Dimitrios Tsourounis, George Economou, Spiros Fotopoulos
Abstract	In this work, we present a novel approach for training Generative Adversarial Networks (GANs). Using the attention maps produced by a Teacher- Network we are able to improve the quality of the generated images as well as perform weakly object localization on the generated images. To this end, we generate images of HEp-2 cells captured with Indirect Imunofluoresence (IIF) and study the ability of our network to perform a weakly localization of the cell. Firstly, we demonstrate that whilst GANs can learn the mapping between the input domain and the target distribution efficiently, the discriminator network is not able to detect the regions of interest. Secondly, we present a novel attention transfer mechanism which allows us to enforce the discriminator to put emphasis on the regions of interest via transfer learning. Thirdly, we show that this leads to more realistic images, as the discriminator learns to put emphasis on the area of interest. Fourthly, the proposed method allows one to generate both images as well as attention maps which can be useful for data annotation e.g in object detection.
Tasks	Object Detection, Object Localization, Transfer Learning
Published	2018-02-25
URL	http://arxiv.org/abs/1802.09070v1
PDF	http://arxiv.org/pdf/1802.09070v1.pdf
PWC	https://paperswithcode.com/paper/attention-aware-generative-adversarial
Repo
Framework

One Network to Solve All ROIs: Deep Learning CT for Any ROI using Differentiated Backprojection


Title	One Network to Solve All ROIs: Deep Learning CT for Any ROI using Differentiated Backprojection
Authors	Yoseob Han, Jong Chul Ye
Abstract	Computed tomography for region-of-interest (ROI) reconstruction has advantages of reducing X-ray radiation dose and using a small detector. However, standard analytic reconstruction methods suffer from severe cupping artifacts, and existing model-based iterative reconstruction methods require extensive computations. Recently, we proposed a deep neural network to learn the cupping artifact, but the network is not well generalized for different ROIs due to the singularities in the corrupted images. Therefore, there is an increasing demand for a neural network that works well for any ROI sizes. In this paper, two types of neural networks are designed. The first type learns ROI size-specific cupping artifacts from the analytic reconstruction images, whereas the second type network is to learn to invert the finite Hilbert transform from the truncated differentiated backprojection (DBP) data. Their generalizability for any ROI sizes is then examined. Experimental results show that the new type of neural network significantly outperforms the existing iterative methods for any ROI size in spite of significantly reduced run-time complexity. Since the proposed method consistently surpasses existing methods for any ROIs, it can be used as a general CT reconstruction engine for many practical applications without compromising possible detector truncation.
Tasks
Published	2018-10-01
URL	https://arxiv.org/abs/1810.00500v2
PDF	https://arxiv.org/pdf/1810.00500v2.pdf
PWC	https://paperswithcode.com/paper/one-network-to-solve-all-rois-deep-learning
Repo
Framework

Efficient sampling for Gaussian linear regression with arbitrary priors


Title	Efficient sampling for Gaussian linear regression with arbitrary priors
Authors	P. Richard Hahn, Jingyu He, Hedibert Lopes
Abstract	This paper develops a slice sampler for Bayesian linear regression models with arbitrary priors. The new sampler has two advantages over current approaches. One, it is faster than many custom implementations that rely on auxiliary latent variables, if the number of regressors is large. Two, it can be used with any prior with a density function that can be evaluated up to a normalizing constant, making it ideal for investigating the properties of new shrinkage priors without having to develop custom sampling algorithms. The new sampler takes advantage of the special structure of the linear regression likelihood, allowing it to produce better effective sample size per second than common alternative approaches.
Tasks
Published	2018-06-14
URL	http://arxiv.org/abs/1806.05738v1
PDF	http://arxiv.org/pdf/1806.05738v1.pdf
PWC	https://paperswithcode.com/paper/efficient-sampling-for-gaussian-linear
Repo
Framework

A convex method for classification of groups of examples


Title	A convex method for classification of groups of examples
Authors	Dori Peleg
Abstract	There are many applications where it important to perform well on a set of examples as opposed to individual examples. For example in image or video classification the question is does an object appear somewhere in the image or video while there are several candidates of the object per image or video. In this context, it is not important what is the performance per candidate. Instead the performance per group is the ultimate objective. For such problems one popular approach assumes weak supervision where labels exist for the entire group and then multiple instance learning is utilized. Another approach is to optimize per candidate, assuming each candidate is labeled, in the belief that this will achieve good performance per group. We will show that better results can be achieved if we offer a new methodology which synthesizes the aforementioned approaches and directly optimizes for the final optimization objective while consisting of a convex optimization problem which solves the global optimization problem. The benefit of grouping examples is demonstrated on an image classification task for detecting polyps in images from capsule endoscopy of the colon. The algorithm was designed to efficiently handle hundreds of millions of examples. Furthermore, modifications to the penalty function of the standard SVM algorithm, have proven to significantly improve performance in our test case.
Tasks	Image Classification, Multiple Instance Learning, Video Classification
Published	2018-06-21
URL	http://arxiv.org/abs/1806.08169v1
PDF	http://arxiv.org/pdf/1806.08169v1.pdf
PWC	https://paperswithcode.com/paper/a-convex-method-for-classification-of-groups
Repo
Framework

Prototypicality effects in global semantic description of objects


Title	Prototypicality effects in global semantic description of objects
Authors	Omar Vidal Pino, Erickson Rangel Nascimento, Mario Fernando Montenegro Campos
Abstract	In this paper, we introduce a novel approach for semantic description of object features based on the prototypicality effects of the Prototype Theory. Our prototype-based description model encodes and stores the semantic meaning of an object, while describing its features using the semantic prototype computed by CNN-classifications models. Our method uses semantic prototypes to create discriminative descriptor signatures that describe an object highlighting its most distinctive features within the category. Our experiments show that: i) our descriptor preserves the semantic information used by the CNN-models in classification tasks; ii) our distance metric can be used as the object’s typicality score; iii) our descriptor signatures are semantically interpretable and enables the simulation of the prototypical organization of objects within a category.
Tasks
Published	2018-01-12
URL	http://arxiv.org/abs/1801.04331v3
PDF	http://arxiv.org/pdf/1801.04331v3.pdf
PWC	https://paperswithcode.com/paper/prototypicality-effects-in-global-semantic
Repo
Framework

Hows and Whys of Artificial Intelligence for Public Sector Decisions: Explanation and Evaluation


Title	Hows and Whys of Artificial Intelligence for Public Sector Decisions: Explanation and Evaluation
Authors	Alun Preece, Rob Ashelford, Harry Armstrong, Dave Braines
Abstract	Evaluation has always been a key challenge in the development of artificial intelligence (AI) based software, due to the technical complexity of the software artifact and, often, its embedding in complex sociotechnical processes. Recent advances in machine learning (ML) enabled by deep neural networks has exacerbated the challenge of evaluating such software due to the opaque nature of these ML-based artifacts. A key related issue is the (in)ability of such systems to generate useful explanations of their outputs, and we argue that the explanation and evaluation problems are closely linked. The paper models the elements of a ML-based AI system in the context of public sector decision (PSD) applications involving both artificial and human intelligence, and maps these elements against issues in both evaluation and explanation, showing how the two are related. We consider a number of common PSD application patterns in the light of our model, and identify a set of key issues connected to explanation and evaluation in each case. Finally, we propose multiple strategies to promote wider adoption of AI/ML technologies in PSD, where each is distinguished by a focus on different elements of our model, allowing PSD policy makers to adopt an approach that best fits their context and concerns.
Tasks
Published	2018-09-28
URL	http://arxiv.org/abs/1810.02689v2
PDF	http://arxiv.org/pdf/1810.02689v2.pdf
PWC	https://paperswithcode.com/paper/hows-and-whys-of-artificial-intelligence-for
Repo
Framework

Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies


Title	Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies
Authors	Yann Ollivier
Abstract	In reinforcement learning, temporal difference (TD) is the most direct algorithm to learn the value function of a policy. For large or infinite state spaces, exact representations of the value function are usually not available, and it must be approximated by a function in some parametric family. However, with \emph{nonlinear} parametric approximations (such as neural networks), TD is not guaranteed to converge to a good approximation of the true value function within the family, and is known to diverge even in relatively simple cases. TD lacks an interpretation as a stochastic gradient descent of an error between the true and approximate value functions, which would provide such guarantees. We prove that approximate TD is a gradient descent provided the current policy is \emph{reversible}. This holds even with nonlinear approximations. A policy with transition probabilities $P(s,s’)$ between states is reversible if there exists a function $\mu$ over states such that $\frac{P(s,s’)}{P(s’,s)}=\frac{\mu(s’)}{\mu(s)}$. In particular, every move can be undone with some probability. This condition is restrictive; it is satisfied, for instance, for a navigation problem in any unoriented graph. In this case, approximate TD is exactly a gradient descent of the \emph{Dirichlet norm}, the norm of the difference of \emph{gradients} between the true and approximate value functions. The Dirichlet norm also controls the bias of approximate policy gradient. These results hold even with no decay factor ($\gamma=1$) and do not rely on contractivity of the Bellman operator, thus proving stability of TD even with $\gamma=1$ for reversible policies.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00869v1
PDF	http://arxiv.org/pdf/1805.00869v1.pdf
PWC	https://paperswithcode.com/paper/approximate-temporal-difference-learning-is-a
Repo
Framework

A comparison of deep networks with ReLU activation function and linear spline-type methods


Title	A comparison of deep networks with ReLU activation function and linear spline-type methods
Authors	Konstantin Eckle, Johannes Schmidt-Hieber
Abstract	Deep neural networks (DNNs) generate much richer function spaces than shallow networks. Since the function spaces induced by shallow networks have several approximation theoretic drawbacks, this explains, however, not necessarily the success of deep networks. In this article we take another route by comparing the expressive power of DNNs with ReLU activation function to piecewise linear spline methods. We show that MARS (multivariate adaptive regression splines) is improper learnable by DNNs in the sense that for any given function that can be expressed as a function in MARS with $M$ parameters there exists a multilayer neural network with $O(M \log (M/\varepsilon))$ parameters that approximates this function up to sup-norm error $\varepsilon.$ We show a similar result for expansions with respect to the Faber-Schauder system. Based on this, we derive risk comparison inequalities that bound the statistical risk of fitting a neural network by the statistical risk of spline-based methods. This shows that deep networks perform better or only slightly worse than the considered spline methods. We provide a constructive proof for the function approximations.
Tasks
Published	2018-04-06
URL	http://arxiv.org/abs/1804.02253v2
PDF	http://arxiv.org/pdf/1804.02253v2.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-deep-networks-with-relu
Repo
Framework

Similarity R-C3D for Few-shot Temporal Activity Detection


Title	Similarity R-C3D for Few-shot Temporal Activity Detection
Authors	Huijuan Xu, Bingyi Kang, Ximeng Sun, Jiashi Feng, Kate Saenko, Trevor Darrell
Abstract	Many activities of interest are rare events, with only a few labeled examples available. Therefore models for temporal activity detection which are able to learn from a few examples are desirable. In this paper, we present a conceptually simple and general yet novel framework for few-shot temporal activity detection which detects the start and end time of the few-shot input activities in an untrimmed video. Our model is end-to-end trainable and can benefit from more few-shot examples. At test time, each proposal is assigned the label of the few-shot activity class corresponding to the maximum similarity score. Our Similarity R-C3D method outperforms previous work on three large-scale benchmarks for temporal activity detection (THUMOS14, ActivityNet1.2, and ActivityNet1.3 datasets) in the few-shot setting. Our code will be made available.
Tasks	Action Detection, Activity Detection
Published	2018-12-25
URL	http://arxiv.org/abs/1812.10000v1
PDF	http://arxiv.org/pdf/1812.10000v1.pdf
PWC	https://paperswithcode.com/paper/similarity-r-c3d-for-few-shot-temporal
Repo
Framework

Autonomously and Simultaneously Refining Deep Neural Network Parameters by Generative Adversarial Networks


Title	Autonomously and Simultaneously Refining Deep Neural Network Parameters by Generative Adversarial Networks
Authors	Burak Kakillioglu, Yantao Lu, Senem Velipasalar
Abstract	The choice of parameters, and the design of the network architecture are important factors affecting the performance of deep neural networks. However, there has not been much work on developing an established and systematic way of building the structure and choosing the parameters of a neural network, and this task heavily depends on trial and error and empirical results. Considering that there are many design and parameter choices, such as the number of neurons in each layer, the type of activation function, the choice of using drop out or not, it is very hard to cover every configuration, and find the optimal structure. In this paper, we propose a novel and systematic method that autonomously and simultaneously optimizes multiple parameters of any given deep neural network by using a generative adversarial network (GAN). In our proposed approach, two different models compete and improve each other progressively with a GAN-based strategy. Our proposed approach can be used to autonomously refine the parameters, and improve the accuracy of different deep neural network architectures. Without loss of generality, the proposed method has been tested with three different neural network architectures, and three very different datasets and applications. The results show that the presented approach can simultaneously and successfully optimize multiple neural network parameters, and achieve increased accuracy in all three scenarios.
Tasks
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09712v1
PDF	http://arxiv.org/pdf/1805.09712v1.pdf
PWC	https://paperswithcode.com/paper/autonomously-and-simultaneously-refining-deep-1
Repo
Framework

When Hypermutations and Ageing Enable Artificial Immune Systems to Outperform Evolutionary Algorithms


Title	When Hypermutations and Ageing Enable Artificial Immune Systems to Outperform Evolutionary Algorithms
Authors	Dogan Corus, Pietro S. Oliveto, Donya Yazdani
Abstract	We present a time complexity analysis of the Opt-IA artificial immune system (AIS). We first highlight the power and limitations of its distinguishing operators (i.e., hypermutations with mutation potential and ageing) by analysing them in isolation. Recent work has shown that ageing combined with local mutations can help escape local optima on a dynamic optimisation benchmark function. We generalise this result by rigorously proving that, compared to evolutionary algorithms (EAs), ageing leads to impressive speed-ups on the standard Cliff benchmark function both when using local and global mutations. Unless the stop at first constructive mutation (FCM) mechanism is applied, we show that hypermutations require exponential expected runtime to optimise any function with a polynomial number of optima. If instead FCM is used, the expected runtime is at most a linear factor larger than the upper bound achieved for any random local search algorithm using the artificial fitness levels method. Nevertheless, we prove that algorithms using hypermutations can be considerably faster than EAs at escaping local optima. An analysis of the complete Opt-IA reveals that it is efficient on the previously considered functions and highlights problems where the use of the full algorithm is crucial. We complete the picture by presenting a class of functions for which Opt-IA fails with overwhelming probability while standard EAs are efficient.
Tasks
Published	2018-04-04
URL	http://arxiv.org/abs/1804.01314v2
PDF	http://arxiv.org/pdf/1804.01314v2.pdf
PWC	https://paperswithcode.com/paper/when-hypermutations-and-ageing-enable
Repo
Framework

Compressive Classification (Machine Learning without learning)


Title	Compressive Classification (Machine Learning without learning)
Authors	Vincent Schellekens, Laurent Jacques
Abstract	Compressive learning is a framework where (so far unsupervised) learning tasks use not the entire dataset but a compressed summary (sketch) of it. We propose a compressive learning classification method, and a novel sketch function for images.
Tasks
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01410v1
PDF	http://arxiv.org/pdf/1812.01410v1.pdf
PWC	https://paperswithcode.com/paper/compressive-classification-machine-learning
Repo
Framework

Feedback-Based Tree Search for Reinforcement Learning


Title	Feedback-Based Tree Search for Reinforcement Learning
Authors	Daniel R. Jiang, Emmanuel Ekwedike, Han Liu
Abstract	Inspired by recent successes of Monte-Carlo tree search (MCTS) in a number of artificial intelligence (AI) application domains, we propose a model-based reinforcement learning (RL) technique that iteratively applies MCTS on batches of small, finite-horizon versions of the original infinite-horizon Markov decision process. The terminal condition of the finite-horizon problems, or the leaf-node evaluator of the decision tree generated by MCTS, is specified using a combination of an estimated value function and an estimated policy function. The recommendations generated by the MCTS procedure are then provided as feedback in order to refine, through classification and regression, the leaf-node evaluator for the next iteration. We provide the first sample complexity bounds for a tree search-based RL algorithm. In addition, we show that a deep neural network implementation of the technique can create a competitive AI agent for the popular multi-player online battle arena (MOBA) game King of Glory.
Tasks
Published	2018-05-15
URL	http://arxiv.org/abs/1805.05935v1
PDF	http://arxiv.org/pdf/1805.05935v1.pdf
PWC	https://paperswithcode.com/paper/feedback-based-tree-search-for-reinforcement
Repo
Framework