Paper Group ANR 47
Positional Cartesian Genetic Programming. Vehicle Detection in Aerial Images. HDM-Net: Monocular Non-Rigid 3D Reconstruction with Learned Deformation Model. Centroid estimation based on symmetric KL divergence for Multinomial text classification problem. Learning through Probing: a decentralized reinforcement learning architecture for social dilemm …
Positional Cartesian Genetic Programming
| Title | Positional Cartesian Genetic Programming |
| Authors | DG Wilson, Julian F. Miller, Sylvain Cussat-Blanc, Hervé Luga |
| Abstract | Cartesian Genetic Programming (CGP) has many modifications across a variety of implementations, such as recursive connections and node weights. Alternative genetic operators have also been proposed for CGP, but have not been fully studied. In this work, we present a new form of genetic programming based on a floating point representation. In this new form of CGP, called Positional CGP, node positions are evolved. This allows for the evaluation of many different genetic operators while allowing for previous CGP improvements like recurrency. Using nine benchmark problems from three different classes, we evaluate the optimal parameters for CGP and PCGP, including novel genetic operators. |
| Tasks | |
| Published | 2018-10-09 |
| URL | http://arxiv.org/abs/1810.04119v1 |
| http://arxiv.org/pdf/1810.04119v1.pdf | |
| PWC | https://paperswithcode.com/paper/positional-cartesian-genetic-programming |
| Repo | |
| Framework | |
Vehicle Detection in Aerial Images
| Title | Vehicle Detection in Aerial Images |
| Authors | Michael Ying Yang, Wentong Liao, Xinbo Li, Bodo Rosenhahn |
| Abstract | The detection of vehicles in aerial images is widely applied in many applications. Comparing with object detection in the ground view images, vehicle detection in aerial images remains a challenging problem because of small vehicle size, monotone appearance and the complex background. In this paper, we propose a novel double focal loss convolutional neural network framework (DFL-CNN). In the proposed framework, the skip connection is used in the CNN structure to enhance the feature learning. Also, the focal loss function is used to substitute for conventional cross entropy loss function in both of the region proposed network and the final classifier. We further introduce the first large-scale vehicle detection dataset ITCVD with ground truth annotations for all the vehicles in the scene. We demonstrate the performance of our model on the existing benchmark DLR 3K dataset as well as the ITCVD dataset. The experimental results show that our DFL-CNN outperforms the baselines on vehicle detection. |
| Tasks | Object Detection |
| Published | 2018-01-22 |
| URL | http://arxiv.org/abs/1801.07339v2 |
| http://arxiv.org/pdf/1801.07339v2.pdf | |
| PWC | https://paperswithcode.com/paper/vehicle-detection-in-aerial-images |
| Repo | |
| Framework | |
HDM-Net: Monocular Non-Rigid 3D Reconstruction with Learned Deformation Model
| Title | HDM-Net: Monocular Non-Rigid 3D Reconstruction with Learned Deformation Model |
| Authors | Vladislav Golyanik, Soshi Shimada, Kiran Varanasi, Didier Stricker |
| Abstract | Monocular dense 3D reconstruction of deformable objects is a hard ill-posed problem in computer vision. Current techniques either require dense correspondences and rely on motion and deformation cues, or assume a highly accurate reconstruction (referred to as a template) of at least a single frame given in advance and operate in the manner of non-rigid tracking. Accurate computation of dense point tracks often requires multiple frames and might be computationally expensive. Availability of a template is a very strong prior which restricts system operation to a pre-defined environment and scenarios. In this work, we propose a new hybrid approach for monocular non-rigid reconstruction which we call Hybrid Deformation Model Network (HDM-Net). In our approach, deformation model is learned by a deep neural network, with a combination of domain-specific loss functions. We train the network with multiple states of a non-rigidly deforming structure with a known shape at rest. HDM-Net learns different reconstruction cues including texture-dependent surface deformations, shading and contours. We show generalisability of HDM-Net to states not presented in the training dataset, with unseen textures and under new illumination conditions. Experiments with noisy data and a comparison with other methods demonstrate robustness and accuracy of the proposed approach and suggest possible application scenarios of the new technique in interventional diagnostics and augmented reality. |
| Tasks | 3D Reconstruction |
| Published | 2018-03-27 |
| URL | https://arxiv.org/abs/1803.10193v2 |
| https://arxiv.org/pdf/1803.10193v2.pdf | |
| PWC | https://paperswithcode.com/paper/hdm-net-monocular-non-rigid-3d-reconstruction |
| Repo | |
| Framework | |
Centroid estimation based on symmetric KL divergence for Multinomial text classification problem
| Title | Centroid estimation based on symmetric KL divergence for Multinomial text classification problem |
| Authors | Jiangning Chen, Heinrich Matzinger, Haoyan Zhai, Mi Zhou |
| Abstract | We define a new method to estimate centroid for text classification based on the symmetric KL-divergence between the distribution of words in training documents and their class centroids. Experiments on several standard data sets indicate that the new method achieves substantial improvements over the traditional classifiers. |
| Tasks | Text Classification |
| Published | 2018-08-29 |
| URL | http://arxiv.org/abs/1808.10261v2 |
| http://arxiv.org/pdf/1808.10261v2.pdf | |
| PWC | https://paperswithcode.com/paper/centroid-estimation-based-on-symmetric-kl |
| Repo | |
| Framework | |
Learning through Probing: a decentralized reinforcement learning architecture for social dilemmas
| Title | Learning through Probing: a decentralized reinforcement learning architecture for social dilemmas |
| Authors | Nicolas Anastassacos, Mirco Musolesi |
| Abstract | Multi-agent reinforcement learning has received significant interest in recent years notably due to the advancements made in deep reinforcement learning which have allowed for the developments of new architectures and learning algorithms. Using social dilemmas as the training ground, we present a novel learning architecture, Learning through Probing (LTP), where agents utilize a probing mechanism to incorporate how their opponent’s behavior changes when an agent takes an action. We use distinct training phases and adjust rewards according to the overall outcome of the experiences accounting for changes to the opponents behavior. We introduce a parameter eta to determine the significance of these future changes to opponent behavior. When applied to the Iterated Prisoner’s Dilemma (IPD), LTP agents demonstrate that they can learn to cooperate with each other, achieving higher average cumulative rewards than other reinforcement learning methods while also maintaining good performance in playing against static agents that are present in Axelrod tournaments. We compare this method with traditional reinforcement learning algorithms and agent-tracking techniques to highlight key differences and potential applications. We also draw attention to the differences between solving games and societal-like interactions and analyze the training of Q-learning agents in makeshift societies. This is to emphasize how cooperation may emerge in societies and demonstrate this using environments where interactions with opponents are determined through a random encounter format of the IPD. |
| Tasks | Multi-agent Reinforcement Learning, Q-Learning |
| Published | 2018-09-26 |
| URL | http://arxiv.org/abs/1809.10007v2 |
| http://arxiv.org/pdf/1809.10007v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-through-probing-a-decentralized |
| Repo | |
| Framework | |
Graph Transformation Policy Network for Chemical Reaction Prediction
| Title | Graph Transformation Policy Network for Chemical Reaction Prediction |
| Authors | Kien Do, Truyen Tran, Svetha Venkatesh |
| Abstract | We address a fundamental problem in chemistry known as chemical reaction product prediction. Our main insight is that the input reactant and reagent molecules can be jointly represented as a graph, and the process of generating product molecules from reactant molecules can be formulated as a sequence of graph transformations. To this end, we propose Graph Transformation Policy Network (GTPN) – a novel generic method that combines the strengths of graph neural networks and reinforcement learning to learn the reactions directly from data with minimal chemical knowledge. Compared to previous methods, GTPN has some appealing properties such as: end-to-end learning, and making no assumption about the length or the order of graph transformations. In order to guide model search through the complex discrete space of sets of bond changes effectively, we extend the standard policy gradient loss by adding useful constraints. Evaluation results show that GTPN improves the top-1 accuracy over the current state-of-the-art method by about 3% on the large USPTO dataset. Our model’s performances and prediction errors are also analyzed carefully in the paper. |
| Tasks | Chemical Reaction Prediction |
| Published | 2018-12-22 |
| URL | http://arxiv.org/abs/1812.09441v1 |
| http://arxiv.org/pdf/1812.09441v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-transformation-policy-network-for |
| Repo | |
| Framework | |
Link Prediction in Dynamic Graphs for Recommendation
| Title | Link Prediction in Dynamic Graphs for Recommendation |
| Authors | Samuel G. Fadel, Ricardo da S. Torres |
| Abstract | Recent advances in employing neural networks on graph domains helped push the state of the art in link prediction tasks, particularly in recommendation services. However, the use of temporal contextual information, often modeled as dynamic graphs that encode the evolution of user-item relationships over time, has been overlooked in link prediction problems. In this paper, we consider the hypothesis that leveraging such information enables models to make better predictions, proposing a new neural network approach for this. Our experiments, performed on the widely used ML-100k and ML-1M datasets, show that our approach produces better predictions in scenarios where the pattern of user-item relationships change over time. In addition, they suggest that existing approaches are significantly impacted by those changes. |
| Tasks | Link Prediction |
| Published | 2018-11-17 |
| URL | http://arxiv.org/abs/1811.07174v1 |
| http://arxiv.org/pdf/1811.07174v1.pdf | |
| PWC | https://paperswithcode.com/paper/link-prediction-in-dynamic-graphs-for |
| Repo | |
| Framework | |
Toward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data
| Title | Toward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data |
| Authors | Thomas Köhler, Michel Bätz, Farzad Naderi, André Kaup, Andreas Maier, Christian Riess |
| Abstract | Capturing ground truth data to benchmark super-resolution (SR) is challenging. Therefore, current quantitative studies are mainly evaluated on simulated data artificially sampled from ground truth images. We argue that such evaluations overestimate the actual performance of SR methods compared to their behavior on real images. Toward bridging this simulated-to-real gap, we introduce the Super-Resolution Erlangen (SupER) database, the first comprehensive laboratory SR database of all-real acquisitions with pixel-wise ground truth. It consists of more than 80k images of 14 scenes combining different facets: CMOS sensor noise, real sampling at four resolution levels, nine scene motion types, two photometric conditions, and lossy video coding at five levels. As such, the database exceeds existing benchmarks by an order of magnitude in quality and quantity. This paper also benchmarks 19 popular single-image and multi-frame algorithms on our data. The benchmark comprises a quantitative study by exploiting ground truth data and qualitative evaluations in a large-scale observer study. We also rigorously investigate agreements between both evaluations from a statistical perspective. One interesting result is that top-performing methods on simulated data may be surpassed by others on real data. Our insights can spur further algorithm development, and the publicy available dataset can foster future evaluations. |
| Tasks | Super-Resolution |
| Published | 2018-09-17 |
| URL | https://arxiv.org/abs/1809.06420v2 |
| https://arxiv.org/pdf/1809.06420v2.pdf | |
| PWC | https://paperswithcode.com/paper/bridging-the-simulated-to-real-gap |
| Repo | |
| Framework | |
Dilated Convolutions in Neural Networks for Left Atrial Segmentation in 3D Gadolinium Enhanced-MRI
| Title | Dilated Convolutions in Neural Networks for Left Atrial Segmentation in 3D Gadolinium Enhanced-MRI |
| Authors | Sulaiman Vesal, Nishant Ravikumar, Andreas Maier |
| Abstract | Segmentation of the left atrial chamber and assessing its morphology, are essential for improving our understanding of atrial fibrillation, the most common type of cardiac arrhythmia. Automation of this process in 3D gadolinium enhanced-MRI (GE-MRI) data is desirable, as manual delineation is time-consuming, challenging and observer-dependent. Recently, deep convolutional neural networks (CNNs) have gained tremendous traction and achieved state-of-the-art results in medical image segmentation. However, it is difficult to incorporate local and global information without using contracting (pooling) layers, which in turn reduces segmentation accuracy for smaller structures. In this paper, we propose a 3D CNN for volumetric segmentation of the left atrial chamber in LGE-MRI. Our network is based on the well known U-Net architecture. We employ a 3D fully convolutional network, with dilated convolutions in the lowest level of the network, and residual connections between encoder blocks to incorporate local and global knowledge. The results show that including global context through the use of dilated convolutions, helps in domain adaptation, and the overall segmentation accuracy is improved in comparison to a 3D U-Net. |
| Tasks | Domain Adaptation, Medical Image Segmentation, Semantic Segmentation |
| Published | 2018-08-05 |
| URL | http://arxiv.org/abs/1808.01673v1 |
| http://arxiv.org/pdf/1808.01673v1.pdf | |
| PWC | https://paperswithcode.com/paper/dilated-convolutions-in-neural-networks-for |
| Repo | |
| Framework | |
Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
| Title | Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks |
| Authors | Guotai Wang, Wenqi Li, Michael Aertsen, Jan Deprest, Sebastien Ourselin, Tom Vercauteren |
| Abstract | Despite the state-of-the-art performance for medical image segmentation, deep convolutional neural networks (CNNs) have rarely provided uncertainty estimations regarding their segmentation outputs, e.g., model (epistemic) and image-based (aleatoric) uncertainties. In this work, we analyze these different types of uncertainties for CNN-based 2D and 3D medical image segmentation tasks. We additionally propose a test-time augmentation-based aleatoric uncertainty to analyze the effect of different transformations of the input image on the segmentation output. Test-time augmentation has been previously used to improve segmentation accuracy, yet not been formulated in a consistent mathematical framework. Hence, we also propose a theoretical formulation of test-time augmentation, where a distribution of the prediction is estimated by Monte Carlo simulation with prior distributions of parameters in an image acquisition model that involves image transformations and noise. We compare and combine our proposed aleatoric uncertainty with model uncertainty. Experiments with segmentation of fetal brains and brain tumors from 2D and 3D Magnetic Resonance Images (MRI) showed that 1) the test-time augmentation-based aleatoric uncertainty provides a better uncertainty estimation than calculating the test-time dropout-based model uncertainty alone and helps to reduce overconfident incorrect predictions, and 2) our test-time augmentation outperforms a single-prediction baseline and dropout-based multiple predictions. |
| Tasks | Medical Image Segmentation, Semantic Segmentation |
| Published | 2018-07-19 |
| URL | http://arxiv.org/abs/1807.07356v3 |
| http://arxiv.org/pdf/1807.07356v3.pdf | |
| PWC | https://paperswithcode.com/paper/aleatoric-uncertainty-estimation-with-test |
| Repo | |
| Framework | |
Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning
| Title | Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning |
| Authors | Jun Feng, Heng Li, Minlie Huang, Shichen Liu, Wenwu Ou, Zhirong Wang, Xiaoyan Zhu |
| Abstract | Ranking is a fundamental and widely studied problem in scenarios such as search, advertising, and recommendation. However, joint optimization for multi-scenario ranking, which aims to improve the overall performance of several ranking strategies in different scenarios, is rather untouched. Separately optimizing each individual strategy has two limitations. The first one is lack of collaboration between scenarios meaning that each strategy maximizes its own objective but ignores the goals of other strategies, leading to a sub-optimal overall performance. The second limitation is the inability of modeling the correlation between scenarios meaning that independent optimization in one scenario only uses its own user data but ignores the context in other scenarios. In this paper, we formulate multi-scenario ranking as a fully cooperative, partially observable, multi-agent sequential decision problem. We propose a novel model named Multi-Agent Recurrent Deterministic Policy Gradient (MA-RDPG) which has a communication component for passing messages, several private actors (agents) for making actions for ranking, and a centralized critic for evaluating the overall performance of the co-working actors. Each scenario is treated as an agent (actor). Agents collaborate with each other by sharing a global action-value function (the critic) and passing messages that encodes historical information across scenarios. The model is evaluated with online settings on a large E-commerce platform. Results show that the proposed model exhibits significant improvements against baselines in terms of the overall performance. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2018-09-17 |
| URL | http://arxiv.org/abs/1809.06260v1 |
| http://arxiv.org/pdf/1809.06260v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-collaborate-multi-scenario |
| Repo | |
| Framework | |
Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
| Title | Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization |
| Authors | Guoliang Kang, Liang Zheng, Yan Yan, Yi Yang |
| Abstract | In this paper, we make two contributions to unsupervised domain adaptation (UDA) using the convolutional neural network (CNN). First, our approach transfers knowledge in all the convolutional layers through attention alignment. Most previous methods align high-level representations, e.g., activations of the fully connected (FC) layers. In these methods, however, the convolutional layers which underpin critical low-level domain knowledge cannot be updated directly towards reducing domain discrepancy. Specifically, we assume that the discriminative regions in an image are relatively invariant to image style changes. Based on this assumption, we propose an attention alignment scheme on all the target convolutional layers to uncover the knowledge shared by the source domain. Second, we estimate the posterior label distribution of the unlabeled data for target network training. Previous methods, which iteratively update the pseudo labels by the target network and refine the target network by the updated pseudo labels, are vulnerable to label estimation errors. Instead, our approach uses category distribution to calculate the cross-entropy loss for training, thereby ameliorating the error accumulation of the estimated labels. The two contributions allow our approach to outperform the state-of-the-art methods by +2.6% on the Office-31 dataset. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2018-01-30 |
| URL | http://arxiv.org/abs/1801.10068v4 |
| http://arxiv.org/pdf/1801.10068v4.pdf | |
| PWC | https://paperswithcode.com/paper/deep-adversarial-attention-alignment-for |
| Repo | |
| Framework | |
Unsupervised detection of diachronic word sense evolution
| Title | Unsupervised detection of diachronic word sense evolution |
| Authors | Jean-François Delpech |
| Abstract | Most words have several senses and connotations which evolve in time due to semantic shift, so that closely related words may gain different or even opposite meanings over the years. This evolution is very relevant to the study of language and of cultural changes, but the tools currently available for diachronic semantic analysis have significant, inherent limitations and are not suitable for real-time analysis. In this article, we demonstrate how the linearity of random vectors techniques enables building time series of congruent word embeddings (or semantic spaces) which can then be compared and combined linearly without loss of precision over any time period to detect diachronic semantic shifts. We show how this approach yields time trajectories of polysemous words such as amazon or apple, enables following semantic drifts and gender bias across time, reveals the shifting instantiations of stable concepts such as hurricane or president. This very fast, linear approach can easily be distributed over many processors to follow in real time streams of social media such as Twitter or Facebook; the resulting, time-dependent semantic spaces can then be combined at will by simple additions or subtractions. |
| Tasks | Time Series, Word Embeddings |
| Published | 2018-05-29 |
| URL | http://arxiv.org/abs/1805.11295v2 |
| http://arxiv.org/pdf/1805.11295v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-detection-of-diachronic-word |
| Repo | |
| Framework | |
A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising
| Title | A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising |
| Authors | Di Wu, Cheng Chen, Xun Yang, Xiujun Chen, Qing Tan, Jian Xu, Kun Gai |
| Abstract | In online display advertising, guaranteed contracts and real-time bidding (RTB) are two major ways to sell impressions for a publisher. Despite the increasing popularity of RTB, there is still half of online display advertising revenue generated from guaranteed contracts. Therefore, simultaneously selling impressions through both guaranteed contracts and RTB is a straightforward choice for a publisher to maximize its yield. However, deriving the optimal strategy to allocate impressions is not a trivial task, especially when the environment is unstable in real-world applications. In this paper, we formulate the impression allocation problem as an auction problem where each contract can submit virtual bids for individual impressions. With this formulation, we derive the optimal impression allocation strategy by solving the optimal bidding functions for contracts. Since the bids from contracts are decided by the publisher, we propose a multi-agent reinforcement learning (MARL) approach to derive cooperative policies for the publisher to maximize its yield in an unstable environment. The proposed approach also resolves the common challenges in MARL such as input dimension explosion, reward credit assignment, and non-stationary environment. Experimental evaluations on large-scale real datasets demonstrate the effectiveness of our approach. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2018-09-10 |
| URL | http://arxiv.org/abs/1809.03152v1 |
| http://arxiv.org/pdf/1809.03152v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-agent-reinforcement-learning-method |
| Repo | |
| Framework | |
Hierarchical Novelty Detection for Visual Object Recognition
| Title | Hierarchical Novelty Detection for Visual Object Recognition |
| Authors | Kibok Lee, Kimin Lee, Kyle Min, Yuting Zhang, Jinwoo Shin, Honglak Lee |
| Abstract | Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes. However, recognizing objects of novel classes unseen during training still remains challenging. The problem of detecting such novel classes has been addressed in the literature, but most prior works have focused on providing simple binary or regressive decisions, e.g., the output would be “known,” “novel,” or corresponding confidence intervals. In this paper, we study more informative novelty detection schemes based on a hierarchical classification framework. For an object of a novel class, we aim for finding its closest super class in the hierarchical taxonomy of known classes. To this end, we propose two different approaches termed top-down and flatten methods, and their combination as well. The essential ingredients of our methods are confidence-calibrated classifiers, data relabeling, and the leave-one-out strategy for modeling novel classes under the hierarchical taxonomy. Furthermore, our method can generate a hierarchical embedding that leads to improved generalized zero-shot learning performance in combination with other commonly-used semantic embeddings. |
| Tasks | Object Recognition, Zero-Shot Learning |
| Published | 2018-04-02 |
| URL | http://arxiv.org/abs/1804.00722v2 |
| http://arxiv.org/pdf/1804.00722v2.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-novelty-detection-for-visual |
| Repo | |
| Framework | |
