Paper Group ANR 95
Exploring Content-based Artwork Recommendation with Metadata and Visual Features. Measuring Inconsistency in Argument Graphs. Unsupervised learning from video to detect foreground objects in single images. Roll-back Hamiltonian Monte Carlo. Balancing Lexicographic Fairness and a Utilitarian Objective with Application to Kidney Exchange. Efficient C …
Exploring Content-based Artwork Recommendation with Metadata and Visual Features
| Title | Exploring Content-based Artwork Recommendation with Metadata and Visual Features |
| Authors | Pablo Messina, Vicente Dominguez, Denis Parra, Christoph Trattner, Alvaro Soto |
| Abstract | Compared to other areas, artwork recommendation has received little attention, despite the continuous growth of the artwork market. Previous research has relied on ratings and metadata to make artwork recommendations, as well as visual features extracted with deep neural networks (DNN). However, these features have no direct interpretation to explicit visual features (e.g. brightness, texture) which might hinder explainability and user-acceptance. In this work, we study the impact of artwork metadata as well as visual features (DNN-based and attractiveness-based) for physical artwork recommendation, using images and transaction data from the UGallery online artwork store. Our results indicate that: (i) visual features perform better than manually curated data, (ii) DNN-based visual features perform better than attractiveness-based ones, and (iii) a hybrid approach improves the performance further. Our research can inform the development of new artwork recommenders relying on diverse content data. |
| Tasks | |
| Published | 2017-06-19 |
| URL | http://arxiv.org/abs/1706.05786v3 |
| http://arxiv.org/pdf/1706.05786v3.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-content-based-artwork |
| Repo | |
| Framework | |
Measuring Inconsistency in Argument Graphs
| Title | Measuring Inconsistency in Argument Graphs |
| Authors | Anthony Hunter |
| Abstract | There have been a number of developments in measuring inconsistency in logic-based representations of knowledge. In contrast, the development of inconsistency measures for computational models of argument has been limited. To address this shortcoming, this paper provides a general framework for measuring inconsistency in abstract argumentation, together with some proposals for specific measures, and a consideration of measuring inconsistency in logic-based instantiations of argument graphs, including a review of some existing proposals and a consideration of how existing logic-based measures of inconsistency can be applied. |
| Tasks | Abstract Argumentation |
| Published | 2017-08-09 |
| URL | http://arxiv.org/abs/1708.02851v1 |
| http://arxiv.org/pdf/1708.02851v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-inconsistency-in-argument-graphs |
| Repo | |
| Framework | |
Unsupervised learning from video to detect foreground objects in single images
| Title | Unsupervised learning from video to detect foreground objects in single images |
| Authors | Ioana Croitoru, Simion-Vlad Bogolin, Marius Leordeanu |
| Abstract | Unsupervised learning from visual data is one of the most difficult challenges in computer vision, being a fundamental task for understanding how visual recognition works. From a practical point of view, learning from unsupervised visual input has an immense practical value, as very large quantities of unlabeled videos can be collected at low cost. In this paper, we address the task of unsupervised learning to detect and segment foreground objects in single images. We achieve our goal by training a student pathway, consisting of a deep neural network. It learns to predict from a single input image (a video frame) the output for that particular frame, of a teacher pathway that performs unsupervised object discovery in video. Our approach is different from the published literature that performs unsupervised discovery in videos or in collections of images at test time. We move the unsupervised discovery phase during the training stage, while at test time we apply the standard feed-forward processing along the student pathway. This has a dual benefit: firstly, it allows in principle unlimited possibilities of learning and generalization during training, while remaining very fast at testing. Secondly, the student not only becomes able to detect in single images significantly better than its unsupervised video discovery teacher, but it also achieves state of the art results on two important current benchmarks, YouTube Objects and Object Discovery datasets. Moreover, at test time, our system is at least two orders of magnitude faster than other previous methods. |
| Tasks | |
| Published | 2017-03-31 |
| URL | http://arxiv.org/abs/1703.10901v1 |
| http://arxiv.org/pdf/1703.10901v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-from-video-to-detect |
| Repo | |
| Framework | |
Roll-back Hamiltonian Monte Carlo
| Title | Roll-back Hamiltonian Monte Carlo |
| Authors | Kexin Yi, Finale Doshi-Velez |
| Abstract | We propose a new framework for Hamiltonian Monte Carlo (HMC) on truncated probability distributions with smooth underlying density functions. Traditional HMC requires computing the gradient of potential function associated with the target distribution, and therefore does not perform its full power on truncated distributions due to lack of continuity and differentiability. In our framework, we introduce a sharp sigmoid factor in the density function to approximate the probability drop at the truncation boundary. The target potential function is approximated by a new potential which smoothly extends to the entire sample space. HMC is then performed on the approximate potential. While our method is easy to implement and applies to a wide range of problems, it also achieves comparable computational efficiency on various sampling tasks compared to other baseline methods. RBHMC also gives rise to a new approach for Bayesian inference on constrained spaces. |
| Tasks | Bayesian Inference |
| Published | 2017-09-08 |
| URL | http://arxiv.org/abs/1709.02855v1 |
| http://arxiv.org/pdf/1709.02855v1.pdf | |
| PWC | https://paperswithcode.com/paper/roll-back-hamiltonian-monte-carlo |
| Repo | |
| Framework | |
Balancing Lexicographic Fairness and a Utilitarian Objective with Application to Kidney Exchange
| Title | Balancing Lexicographic Fairness and a Utilitarian Objective with Application to Kidney Exchange |
| Authors | Duncan C. McElfresh, John P. Dickerson |
| Abstract | Balancing fairness and efficiency in resource allocation is a classical economic and computational problem. The price of fairness measures the worst-case loss of economic efficiency when using an inefficient but fair allocation rule; for indivisible goods in many settings, this price is unacceptably high. One such setting is kidney exchange, where needy patients swap willing but incompatible kidney donors. In this work, we close an open problem regarding the theoretical price of fairness in modern kidney exchanges. We then propose a general hybrid fairness rule that balances a strict lexicographic preference ordering over classes of agents, and a utilitarian objective that maximizes economic efficiency. We develop a utility function for this rule that favors disadvantaged groups lexicographically; but if cost to overall efficiency becomes too high, it switches to a utilitarian objective. This rule has only one parameter which is proportional to a bound on the price of fairness, and can be adjusted by policymakers. We apply this rule to real data from a large kidney exchange and show that our hybrid rule produces more reliable outcomes than other fairness rules. |
| Tasks | |
| Published | 2017-02-27 |
| URL | http://arxiv.org/abs/1702.08286v2 |
| http://arxiv.org/pdf/1702.08286v2.pdf | |
| PWC | https://paperswithcode.com/paper/balancing-lexicographic-fairness-and-a |
| Repo | |
| Framework | |
Efficient Computation in Adaptive Artificial Spiking Neural Networks
| Title | Efficient Computation in Adaptive Artificial Spiking Neural Networks |
| Authors | Davide Zambrano, Roeland Nusselder, H. Steven Scholte, Sander Bohte |
| Abstract | Artificial Neural Networks (ANNs) are bio-inspired models of neural computation that have proven highly effective. Still, ANNs lack a natural notion of time, and neural units in ANNs exchange analog values in a frame-based manner, a computationally and energetically inefficient form of communication. This contrasts sharply with biological neurons that communicate sparingly and efficiently using binary spikes. While artificial Spiking Neural Networks (SNNs) can be constructed by replacing the units of an ANN with spiking neurons, the current performance is far from that of deep ANNs on hard benchmarks and these SNNs use much higher firing rates compared to their biological counterparts, limiting their efficiency. Here we show how spiking neurons that employ an efficient form of neural coding can be used to construct SNNs that match high-performance ANNs and exceed state-of-the-art in SNNs on important benchmarks, while requiring much lower average firing rates. For this, we use spike-time coding based on the firing rate limiting adaptation phenomenon observed in biological spiking neurons. This phenomenon can be captured in adapting spiking neuron models, for which we derive the effective transfer function. Neural units in ANNs trained with this transfer function can be substituted directly with adaptive spiking neurons, and the resulting Adaptive SNNs (AdSNNs) can carry out inference in deep neural networks using up to an order of magnitude fewer spikes compared to previous SNNs. Adaptive spike-time coding additionally allows for the dynamic control of neural coding precision: we show how a simple model of arousal in AdSNNs further halves the average required firing rate and this notion naturally extends to other forms of attention. AdSNNs thus hold promise as a novel and efficient model for neural computation that naturally fits to temporally continuous and asynchronous applications. |
| Tasks | |
| Published | 2017-10-13 |
| URL | http://arxiv.org/abs/1710.04838v1 |
| http://arxiv.org/pdf/1710.04838v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-computation-in-adaptive-artificial |
| Repo | |
| Framework | |
A Hybrid Approach for Secured Optimal Power Flow and Voltage Stability with TCSC Placement
| Title | A Hybrid Approach for Secured Optimal Power Flow and Voltage Stability with TCSC Placement |
| Authors | Sheila Mahapatra, Nitin Malik |
| Abstract | This paper proposes a hybrid technique for secured optimal power flow coupled with enhancing voltage stability with FACTS device installation. The hybrid approach of Improved Gravitational Search algorithm (IGSA) and Firefly algorithm (FA) performance is analyzed by optimally placing TCSC controller. The algorithm is implemented in MATLAB working platform and the power flow security and voltage stability is evaluated with IEEE 30 bus transmission systems. The optimal results generated are compared with those available in literature and the superior performance of algorithm is depicted as minimum generation cost, reduced real power losses along with sustaining voltage stability. |
| Tasks | |
| Published | 2017-01-31 |
| URL | http://arxiv.org/abs/1701.08951v1 |
| http://arxiv.org/pdf/1701.08951v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hybrid-approach-for-secured-optimal-power |
| Repo | |
| Framework | |
Parsimonious Inference on Convolutional Neural Networks: Learning and applying on-line kernel activation rules
| Title | Parsimonious Inference on Convolutional Neural Networks: Learning and applying on-line kernel activation rules |
| Authors | I. Theodorakopoulos, V. Pothos, D. Kastaniotis, N. Fragoulis |
| Abstract | A new, radical CNN design approach is presented in this paper, considering the reduction of the total computational load during inference. This is achieved by a new holistic intervention on both the CNN architecture and the training procedure, which targets to the parsimonious inference by learning to exploit or remove the redundant capacity of a CNN architecture. This is accomplished, by the introduction of a new structural element that can be inserted as an add-on to any contemporary CNN architecture, whilst preserving or even improving its recognition accuracy. Our approach formulates a systematic and data-driven method for developing CNNs that are trained to eventually change size and form in real-time during inference, targeting to the smaller possible computational footprint. Results are provided for the optimal implementation on a few modern, high-end mobile computing platforms indicating a significant speed-up of up to x3 times. |
| Tasks | |
| Published | 2017-01-18 |
| URL | http://arxiv.org/abs/1701.05221v5 |
| http://arxiv.org/pdf/1701.05221v5.pdf | |
| PWC | https://paperswithcode.com/paper/parsimonious-inference-on-convolutional |
| Repo | |
| Framework | |
Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables
| Title | Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables |
| Authors | Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft |
| Abstract | Bayesian neural networks (BNNs) with latent variables are probabilistic models which can automatically identify complex stochastic patterns in the data. We describe and study in these models a decomposition of predictive uncertainty into its epistemic and aleatoric components. First, we show how such a decomposition arises naturally in a Bayesian active learning scenario by following an information theoretic approach. Second, we use a similar decomposition to develop a novel risk sensitive objective for safe reinforcement learning (RL). This objective minimizes the effect of model bias in environments whose stochastic dynamics are described by BNNs with latent variables. Our experiments illustrate the usefulness of the resulting decomposition in active learning and safe RL settings. |
| Tasks | Active Learning |
| Published | 2017-06-26 |
| URL | http://arxiv.org/abs/1706.08495v2 |
| http://arxiv.org/pdf/1706.08495v2.pdf | |
| PWC | https://paperswithcode.com/paper/uncertainty-decomposition-in-bayesian-neural |
| Repo | |
| Framework | |
Cross-validation
| Title | Cross-validation |
| Authors | Sylvain Arlot |
| Abstract | This text is a survey on cross-validation. We define all classical cross-validation procedures, and we study their properties for two different goals: estimating the risk of a given estimator, and selecting the best estimator among a given family. For the risk estimation problem, we compute the bias (which can also be corrected) and the variance of cross-validation methods. For estimator selection, we first provide a first-order analysis (based on expectations). Then, we explain how to take into account second-order terms (from variance computations, and by taking into account the usefulness of overpenalization). This allows, in the end, to provide some guidelines for choosing the best cross-validation method for a given learning problem. |
| Tasks | |
| Published | 2017-03-09 |
| URL | http://arxiv.org/abs/1703.03167v1 |
| http://arxiv.org/pdf/1703.03167v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-validation |
| Repo | |
| Framework | |
DRAW: Deep networks for Recognizing styles of Artists Who illustrate children’s books
| Title | DRAW: Deep networks for Recognizing styles of Artists Who illustrate children’s books |
| Authors | Samet Hicsonmez, Nermin Samet, Fadime Sener, Pinar Duygulu |
| Abstract | This paper is motivated from a young boy’s capability to recognize an illustrator’s style in a totally different context. In the book “We are All Born Free” [1], composed of selected rights from the Universal Declaration of Human Rights interpreted by different illustrators, the boy was surprised to see a picture similar to the ones in the “Winnie the Witch” series drawn by Korky Paul (Figure 1). The style was noticeable in other characters of the same illustrator in different books as well. The capability of a child to easily spot the style was shown to be valid for other illustrators such as Axel Scheffler and Debi Gliori. The boy’s enthusiasm let us to start the journey to explore the capabilities of machines to recognize the style of illustrators. We collected pages from children’s books to construct a new illustrations dataset consisting of about 6500 pages from 24 artists. We exploited deep networks for categorizing illustrators and with around 94% classification performance our method over-performed the traditional methods by more than 10%. Going beyond categorization we explored transferring style. The classification performance on the transferred images has shown the ability of our system to capture the style. Furthermore, we discovered representative illustrations and discriminative stylistic elements. |
| Tasks | |
| Published | 2017-04-10 |
| URL | http://arxiv.org/abs/1704.03057v1 |
| http://arxiv.org/pdf/1704.03057v1.pdf | |
| PWC | https://paperswithcode.com/paper/draw-deep-networks-for-recognizing-styles-of |
| Repo | |
| Framework | |
Adversarial Ranking for Language Generation
| Title | Adversarial Ranking for Language Generation |
| Authors | Kevin Lin, Dianqi Li, Xiaodong He, Zhengyou Zhang, Ming-Ting Sun |
| Abstract | Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize output with rich structures such as natural language descriptions. In this paper, we propose a novel generative adversarial network, RankGAN, for generating high-quality language descriptions. Rather than training the discriminator to learn and assign absolute binary predicate for individual data sample, the proposed RankGAN is able to analyze and rank a collection of human-written and machine-written sentences by giving a reference group. By viewing a set of data samples collectively and evaluating their quality through relative ranking scores, the discriminator is able to make better assessment which in turn helps to learn a better generator. The proposed RankGAN is optimized through the policy gradient technique. Experimental results on multiple public datasets clearly demonstrate the effectiveness of the proposed approach. |
| Tasks | Text Generation |
| Published | 2017-05-31 |
| URL | http://arxiv.org/abs/1705.11001v3 |
| http://arxiv.org/pdf/1705.11001v3.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-ranking-for-language-generation |
| Repo | |
| Framework | |
Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
| Title | Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach |
| Authors | Yunchao Wei, Jiashi Feng, Xiaodan Liang, Ming-Ming Cheng, Yao Zhao, Shuicheng Yan |
| Abstract | We investigate a principle way to progressively mine discriminative object regions using classification networks to address the weakly-supervised semantic segmentation problems. Classification networks are only responsive to small and sparse discriminative regions from the object of interest, which deviates from the requirement of the segmentation task that needs to localize dense, interior and integral regions for pixel-wise inference. To mitigate this gap, we propose a new adversarial erasing approach for localizing and expanding object regions progressively. Starting with a single small object region, our proposed approach drives the classification network to sequentially discover new and complement object regions by erasing the current mined regions in an adversarial manner. These localized regions eventually constitute a dense and complete object region for learning semantic segmentation. To further enhance the quality of the discovered regions by adversarial erasing, an online prohibitive segmentation learning approach is developed to collaborate with adversarial erasing by providing auxiliary segmentation supervision modulated by the more reliable classification scores. Despite its apparent simplicity, the proposed approach achieves 55.0% and 55.7% mean Intersection-over-Union (mIoU) scores on PASCAL VOC 2012 val and test sets, which are the new state-of-the-arts. |
| Tasks | Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
| Published | 2017-03-24 |
| URL | http://arxiv.org/abs/1703.08448v3 |
| http://arxiv.org/pdf/1703.08448v3.pdf | |
| PWC | https://paperswithcode.com/paper/object-region-mining-with-adversarial-erasing |
| Repo | |
| Framework | |
Fast Vehicle Detection in Aerial Imagery
| Title | Fast Vehicle Detection in Aerial Imagery |
| Authors | Jennifer Carlet, Bernard Abayowa |
| Abstract | In recent years, several real-time or near real-time object detectors have been developed. However these object detectors are typically designed for first-person view images where the subject is large in the image and do not directly apply well to detecting vehicles in aerial imagery. Though some detectors have been developed for aerial imagery, these are either slow or do not handle multi-scale imagery very well. Here the popular YOLOv2 detector is modified to vastly improve it’s performance on aerial data. The modified detector is compared to Faster RCNN on several aerial imagery datasets. The proposed detector gives near state of the art performance at more than 4x the speed. |
| Tasks | Fast Vehicle Detection |
| Published | 2017-09-25 |
| URL | http://arxiv.org/abs/1709.08666v1 |
| http://arxiv.org/pdf/1709.08666v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-vehicle-detection-in-aerial-imagery |
| Repo | |
| Framework | |
Related family-based attribute reduction of covering information systems when varying attribute sets
| Title | Related family-based attribute reduction of covering information systems when varying attribute sets |
| Authors | Guangming Lang |
| Abstract | In practical situations, there are many dynamic covering information systems with variations of attributes, but there are few studies on related family-based attribute reduction of dynamic covering information systems. In this paper, we first investigate updated mechanisms of constructing attribute reducts for consistent and inconsistent covering information systems when varying attribute sets by using related families. Then we employ examples to illustrate how to compute attribute reducts of dynamic covering information systems with variations of attribute sets. Finally, the experimental results illustrates that the related family-based methods are effective to perform attribute reduction of dynamic covering information systems when attribute sets are varying with time. |
| Tasks | |
| Published | 2017-11-16 |
| URL | http://arxiv.org/abs/1711.07321v1 |
| http://arxiv.org/pdf/1711.07321v1.pdf | |
| PWC | https://paperswithcode.com/paper/related-family-based-attribute-reduction-of |
| Repo | |
| Framework | |
