Paper Group ANR 69
3D human pose estimation from depth maps using a deep combination of poses. On consistent estimation of the missing mass. Using Deep Reinforcement Learning for the Continuous Control of Robotic Arms. Combining a Context Aware Neural Network with a Denoising Autoencoder for Measuring String Similarities. Less is More: Culling the Training Set to Imp …
3D human pose estimation from depth maps using a deep combination of poses
| Title | 3D human pose estimation from depth maps using a deep combination of poses |
| Authors | Manuel J. Marin-Jimenez, Francisco J. Romero-Ramirez, Rafael Muñoz-Salinas, Rafael Medina-Carnicer |
| Abstract | Many real-world applications require the estimation of human body joints for higher-level tasks as, for example, human behaviour understanding. In recent years, depth sensors have become a popular approach to obtain three-dimensional information. The depth maps generated by these sensors provide information that can be employed to disambiguate the poses observed in two-dimensional images. This work addresses the problem of 3D human pose estimation from depth maps employing a Deep Learning approach. We propose a model, named Deep Depth Pose (DDP), which receives a depth map containing a person and a set of predefined 3D prototype poses and returns the 3D position of the body joints of the person. In particular, DDP is defined as a ConvNet that computes the specific weights needed to linearly combine the prototypes for the given input. We have thoroughly evaluated DDP on the challenging ‘ITOP’ and ‘UBC3V’ datasets, which respectively depict realistic and synthetic samples, defining a new state-of-the-art on them. |
| Tasks | 3D Human Pose Estimation, Pose Estimation |
| Published | 2018-07-14 |
| URL | http://arxiv.org/abs/1807.05389v1 |
| http://arxiv.org/pdf/1807.05389v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-human-pose-estimation-from-depth-maps |
| Repo | |
| Framework | |
On consistent estimation of the missing mass
| Title | On consistent estimation of the missing mass |
| Authors | Fadhel Ayed, Marco Battiston, Federico Camerlenghi, Stefano Favaro |
| Abstract | Given $n$ samples from a population of individuals belonging to different types with unknown proportions, how do we estimate the probability of discovering a new type at the $(n+1)$-th draw? This is a classical problem in statistics, commonly referred to as the missing mass estimation problem. Recent results by Ohannessian and Dahleh \citet{Oha12} and Mossel and Ohannessian \citet{Mos15} showed: i) the impossibility of estimating (learning) the missing mass without imposing further structural assumptions on the type proportions; ii) the consistency of the Good-Turing estimator for the missing mass under the assumption that the tail of the type proportions decays to zero as a regularly varying function with parameter $\alpha\in(0,1)$. In this paper we rely on tools from Bayesian nonparametrics to provide an alternative, and simpler, proof of the impossibility of a distribution-free estimation of the missing mass. Up to our knowledge, the use of Bayesian ideas to study large sample asymptotics for the missing mass is new, and it could be of independent interest. Still relying on Bayesian nonparametric tools, we then show that under regularly varying type proportions the convergence rate of the Good-Turing estimator is the best rate that any estimator can achieve, up to a slowly varying function, and that minimax rate must be at least $n^{-\alpha/2}$. We conclude with a discussion of our results, and by conjecturing that the Good-Turing estimator is an rate optimal minimax estimator under regularly varying type proportions. |
| Tasks | |
| Published | 2018-06-25 |
| URL | http://arxiv.org/abs/1806.09712v1 |
| http://arxiv.org/pdf/1806.09712v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-consistent-estimation-of-the-missing-mass |
| Repo | |
| Framework | |
Using Deep Reinforcement Learning for the Continuous Control of Robotic Arms
| Title | Using Deep Reinforcement Learning for the Continuous Control of Robotic Arms |
| Authors | Winfried Lötzsch |
| Abstract | Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area of research and many concurrent inventions, we decided to focus on a relatively simple robotic task to evaluate a set of ideas that might help to solve recent reinforcement learning problems. We test a newly created combination of two commonly used reinforcement learning methods, whether it is able to learn more effectively than a baseline. We also compare different ideas to preprocess information before it is fed to the reinforcement learning algorithm. The goal of this strategy is to reduce training time and eventually help the algorithm to converge. The concluding evaluation proves the general applicability of the described concepts by testing them using a simulated environment. These concepts might be reused for future experiments. |
| Tasks | Continuous Control |
| Published | 2018-10-15 |
| URL | http://arxiv.org/abs/1810.06746v1 |
| http://arxiv.org/pdf/1810.06746v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-deep-reinforcement-learning-for-the |
| Repo | |
| Framework | |
Combining a Context Aware Neural Network with a Denoising Autoencoder for Measuring String Similarities
| Title | Combining a Context Aware Neural Network with a Denoising Autoencoder for Measuring String Similarities |
| Authors | Mehdi Ben Lazreg, Morten Goodwin |
| Abstract | Measuring similarities between strings is central for many established and fast growing research areas including information retrieval, biology, and natural language processing. The traditional approach for string similarity measurements is to define a metric over a word space that quantifies and sums up the differences between characters in two strings. The state-of-the-art in the area has, surprisingly, not evolved much during the last few decades. The majority of the metrics are based on a simple comparison between character and character distributions without consideration for the context of the words. This paper proposes a string metric that encompasses similarities between strings based on (1) the character similarities between the words including. Non-Standard and standard spellings of the same words, and (2) the context of the words. Our proposal is a neural network composed of a denoising autoencoder and what we call a context encoder specifically designed to find similarities between the words based on their context. The experimental results show that the resulting metrics succeeds in 85.4% of the cases in finding the correct version of a non-standard spelling among the closest words, compared to 63.2% with the established Normalised-Levenshtein distance. Besides, we show that words used in similar context are with our approach calculated to be similar than words with different contexts, which is a desirable property missing in established string metrics. |
| Tasks | Denoising, Information Retrieval |
| Published | 2018-07-16 |
| URL | http://arxiv.org/abs/1807.06414v1 |
| http://arxiv.org/pdf/1807.06414v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-a-context-aware-neural-network-with |
| Repo | |
| Framework | |
Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks
| Title | Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks |
| Authors | Yongshuai Liu, Jiyu Chen, Hao Chen |
| Abstract | Deep neural networks are vulnerable to adversarial examples. Prior defenses attempted to make deep networks more robust by either changing the network architecture or augmenting the training set with adversarial examples, but both have inherent limitations. Motivated by recent research that shows outliers in the training set have a high negative influence on the trained model, we studied the relationship between model robustness and the quality of the training set. We first show that outliers give the model better generalization ability but weaker robustness. Next, we propose an adversarial example detection framework, in which we design two methods for removing outliers from training set to obtain the sanitized model and then detect adversarial example by calculating the difference of outputs between the original and the sanitized model. We evaluated the framework on both MNIST and SVHN. Based on the difference measured by Kullback-Leibler divergence, we could detect adversarial examples with accuracy between 94.67% to 99.89%. |
| Tasks | |
| Published | 2018-01-09 |
| URL | http://arxiv.org/abs/1801.02850v2 |
| http://arxiv.org/pdf/1801.02850v2.pdf | |
| PWC | https://paperswithcode.com/paper/less-is-more-culling-the-training-set-to |
| Repo | |
| Framework | |
Improved Training with Curriculum GANs
| Title | Improved Training with Curriculum GANs |
| Authors | Rishi Sharma, Shane Barratt, Stefano Ermon, Vijay Pande |
| Abstract | In this paper we introduce Curriculum GANs, a curriculum learning strategy for training Generative Adversarial Networks that increases the strength of the discriminator over the course of training, thereby making the learning task progressively more difficult for the generator. We demonstrate that this strategy is key to obtaining state-of-the-art results in image generation. We also show evidence that this strategy may be broadly applicable to improving GAN training in other data modalities. |
| Tasks | Image Generation |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.09295v1 |
| http://arxiv.org/pdf/1807.09295v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-training-with-curriculum-gans |
| Repo | |
| Framework | |
Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition
| Title | Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition |
| Authors | Justin Fu, Avi Singh, Dibya Ghosh, Larry Yang, Sergey Levine |
| Abstract | The design of a reward function often poses a major practical challenge to real-world applications of reinforcement learning. Approaches such as inverse reinforcement learning attempt to overcome this challenge, but require expert demonstrations, which can be difficult or expensive to obtain in practice. We propose variational inverse control with events (VICE), which generalizes inverse reinforcement learning methods to cases where full demonstrations are not needed, such as when only samples of desired goal states are available. Our method is grounded in an alternative perspective on control and reinforcement learning, where an agent’s goal is to maximize the probability that one or more events will happen at some point in the future, rather than maximizing cumulative rewards. We demonstrate the effectiveness of our methods on continuous control tasks, with a focus on high-dimensional observations like images where rewards are hard or even impossible to specify. |
| Tasks | Continuous Control |
| Published | 2018-05-29 |
| URL | http://arxiv.org/abs/1805.11686v3 |
| http://arxiv.org/pdf/1805.11686v3.pdf | |
| PWC | https://paperswithcode.com/paper/variational-inverse-control-with-events-a |
| Repo | |
| Framework | |
Exploring Feature Reuse in DenseNet Architectures
| Title | Exploring Feature Reuse in DenseNet Architectures |
| Authors | Andy Hess |
| Abstract | Densely Connected Convolutional Networks (DenseNets) have been shown to achieve state-of-the-art results on image classification tasks while using fewer parameters and computation than competing methods. Since each layer in this architecture has full access to the feature maps of all previous layers, the network is freed from the burden of having to relearn previously useful features, thus alleviating issues with vanishing gradients. In this work we explore the question: To what extent is it necessary to connect to all previous layers in order to reap the benefits of feature reuse? To this end, we introduce the notion of local dense connectivity and present evidence that less connectivity, allowing for increased growth rate at a fixed network capacity, can achieve a more efficient reuse of features and lead to higher accuracy in dense architectures. |
| Tasks | Image Classification |
| Published | 2018-06-05 |
| URL | http://arxiv.org/abs/1806.01935v1 |
| http://arxiv.org/pdf/1806.01935v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-feature-reuse-in-densenet |
| Repo | |
| Framework | |
Sequential Attacks on Agents for Long-Term Adversarial Goals
| Title | Sequential Attacks on Agents for Long-Term Adversarial Goals |
| Authors | Edgar Tretschk, Seong Joon Oh, Mario Fritz |
| Abstract | Reinforcement learning (RL) has advanced greatly in the past few years with the employment of effective deep neural networks (DNNs) on the policy networks. With the great effectiveness came serious vulnerability issues with DNNs that small adversarial perturbations on the input can change the output of the network. Several works have pointed out that learned agents with a DNN policy network can be manipulated against achieving the original task through a sequence of small perturbations on the input states. In this paper, we demonstrate furthermore that it is also possible to impose an arbitrary adversarial reward on the victim policy network through a sequence of attacks. Our method involves the latest adversarial attack technique, Adversarial Transformer Network (ATN), that learns to generate the attack and is easy to integrate into the policy network. As a result of our attack, the victim agent is misguided to optimise for the adversarial reward over time. Our results expose serious security threats for RL applications in safety-critical systems including drones, medical analysis, and self-driving cars. |
| Tasks | Adversarial Attack, Self-Driving Cars |
| Published | 2018-05-31 |
| URL | http://arxiv.org/abs/1805.12487v2 |
| http://arxiv.org/pdf/1805.12487v2.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-attacks-on-agents-for-long-term |
| Repo | |
| Framework | |
Punctuation Prediction Model for Conversational Speech
| Title | Punctuation Prediction Model for Conversational Speech |
| Authors | Piotr Żelasko, Piotr Szymański, Jan Mizgajski, Adrian Szymczak, Yishay Carmiel, Najim Dehak |
| Abstract | An ASR system usually does not predict any punctuation or capitalization. Lack of punctuation causes problems in result presentation and confuses both the human reader andoff-the-shelf natural language processing algorithms. To overcome these limitations, we train two variants of Deep Neural Network (DNN) sequence labelling models - a Bidirectional Long Short-Term Memory (BLSTM) and a Convolutional Neural Network (CNN), to predict the punctuation. The models are trained on the Fisher corpus which includes punctuation annotation. In our experiments, we combine time-aligned and punctuated Fisher corpus transcripts using a sequence alignment algorithm. The neural networks are trained on Common Web Crawl GloVe embedding of the words in Fisher transcripts aligned with conversation side indicators and word time infomation. The CNNs yield a better precision and BLSTMs tend to have better recall. While BLSTMs make fewer mistakes overall, the punctuation predicted by the CNN is more accurate - especially in the case of question marks. Our results constitute significant evidence that the distribution of words in time, as well as pre-trained embeddings, can be useful in the punctuation prediction task. |
| Tasks | |
| Published | 2018-07-02 |
| URL | http://arxiv.org/abs/1807.00543v1 |
| http://arxiv.org/pdf/1807.00543v1.pdf | |
| PWC | https://paperswithcode.com/paper/punctuation-prediction-model-for |
| Repo | |
| Framework | |
Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks
| Title | Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks |
| Authors | Fusheng Hao, Jun Cheng, Lei Wang, Xinchao Wang, Jianzhong Cao, Xiping Hu, Dapeng Tao |
| Abstract | Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly enforced. In this paper, we propose a novel approach to train deep CNNs by imposing the intra-class compactness and the inter-class separability, so as to enhance the learned features’ discriminant power. To this end, we introduce anchors, which are predefined vectors regarded as the centers for each class and fixed during training. Discriminative features are obtained by constraining the deep CNNs to map training samples to the corresponding anchors as close as possible. We propose two principles to select the anchors, and measure the proximity of two points using the Euclidean and cosine distance metric functions, which results in two novel loss functions. These loss functions require no sample pairs or triplets and can be efficiently optimized by batch stochastic gradient descent. We test the proposed method on three benchmark image classification datasets and demonstrate its promising results. |
| Tasks | Image Classification |
| Published | 2018-04-22 |
| URL | http://arxiv.org/abs/1804.08087v1 |
| http://arxiv.org/pdf/1804.08087v1.pdf | |
| PWC | https://paperswithcode.com/paper/anchor-based-nearest-class-mean-loss-for |
| Repo | |
| Framework | |
Prosocial or Selfish? Agents with different behaviors for Contract Negotiation using Reinforcement Learning
| Title | Prosocial or Selfish? Agents with different behaviors for Contract Negotiation using Reinforcement Learning |
| Authors | Vishal Sunder, Lovekesh Vig, Arnab Chatterjee, Gautam Shroff |
| Abstract | We present an effective technique for training deep learning agents capable of negotiating on a set of clauses in a contract agreement using a simple communication protocol. We use Multi Agent Reinforcement Learning to train both agents simultaneously as they negotiate with each other in the training environment. We also model selfish and prosocial behavior to varying degrees in these agents. Empirical evidence is provided showing consistency in agent behaviors. We further train a meta agent with a mixture of behaviors by learning an ensemble of different models using reinforcement learning. Finally, to ascertain the deployability of the negotiating agents, we conducted experiments pitting the trained agents against human players. Results demonstrate that the agents are able to hold their own against human players, often emerging as winners in the negotiation. Our experiments demonstrate that the meta agent is able to reasonably emulate human behavior. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2018-09-19 |
| URL | http://arxiv.org/abs/1809.07066v1 |
| http://arxiv.org/pdf/1809.07066v1.pdf | |
| PWC | https://paperswithcode.com/paper/prosocial-or-selfish-agents-with-different |
| Repo | |
| Framework | |
Dempsterian-Shaferian Belief Network From Data
| Title | Dempsterian-Shaferian Belief Network From Data |
| Authors | Mieczysław A. Kłopotek |
| Abstract | Shenoy and Shafer {Shenoy:90} demonstrated that both for Dempster-Shafer Theory and probability theory there exists a possibility to calculate efficiently marginals of joint belief distributions (by so-called local computations) provided that the joint distribution can be decomposed (factorized) into a belief network. A number of algorithms exists for decomposition of probabilistic joint belief distribution into a bayesian (belief) network from data. For example Spirtes, Glymour and Schein{Spirtes:90b} formulated a Conjecture that a direct dependence test and a head-to-head meeting test would suffice to construe bayesian network from data in such a way that Pearl’s concept of d-separation {Geiger:90} applies. This paper is intended to transfer Spirtes, Glymour and Scheines {Spirtes:90b} approach onto the ground of the Dempster-Shafer Theory (DST). For this purpose, a frequentionistic interpretation of the DST developed in {Klopotek:93b} is exploited. A special notion of conditionality for DST is introduced and demonstrated to behave with respect to Pearl’s d-separation {Geiger:90} much the same way as conditional probability (though some differences like non-uniqueness are evident). Based on this, an algorithm analogous to that from {Spirtes:90b} is developed. The notion of a partially oriented graph (pog) is introduced and within this graph the notion of p-d-separation is defined. If direct dependence test and head-to-head meeting test are used to orient the pog then its p-d-separation is shown to be equivalent to the Pearl’s d-separation for any compatible dag. |
| Tasks | |
| Published | 2018-06-06 |
| URL | http://arxiv.org/abs/1806.02373v1 |
| http://arxiv.org/pdf/1806.02373v1.pdf | |
| PWC | https://paperswithcode.com/paper/dempsterian-shaferian-belief-network-from |
| Repo | |
| Framework | |
Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarios
| Title | Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarios |
| Authors | Shabab Bazrafkan, Peter Corcoran |
| Abstract | Conditional generators learn the data distribution for each class in a multi-class scenario and generate samples for a specific class given the right input from the latent space. In this work, a method known as “Versatile Auxiliary Classifier with Generative Adversarial Network” for multi-class scenarios is presented. In this technique, the Generative Adversarial Networks (GAN)‘s generator is turned into a conditional generator by placing a multi-class classifier in parallel with the discriminator network and backpropagate the classification error through the generator. This technique is versatile enough to be applied to any GAN implementation. The results on two databases and comparisons with other method are provided as well. |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07751v1 |
| http://arxiv.org/pdf/1806.07751v1.pdf | |
| PWC | https://paperswithcode.com/paper/versatile-auxiliary-classifier-with |
| Repo | |
| Framework | |
A Vehicle Detection Approach using Deep Learning Methodologies
| Title | A Vehicle Detection Approach using Deep Learning Methodologies |
| Authors | Abdullah Asim Yilmaz, Mehmet Serdar Guzel, Iman Askerbeyli, Erkan Bostanci |
| Abstract | The purpose of this study is to successfully train our vehicle detector using R-CNN, Faster R-CNN deep learning methods on a sample vehicle data sets and to optimize the success rate of the trained detector by providing efficient results for vehicle detection by testing the trained vehicle detector on the test data. The working method consists of six main stages. These are respectively; loading the data set, the design of the convolutional neural network, configuration of training options, training of the Faster R-CNN object detector and evaluation of trained detector. In addition, in the scope of the study, Faster R-CNN, R-CNN deep learning methods were mentioned and experimental analysis comparisons were made with the results obtained from vehicle detection. |
| Tasks | |
| Published | 2018-04-02 |
| URL | http://arxiv.org/abs/1804.00429v1 |
| http://arxiv.org/pdf/1804.00429v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-vehicle-detection-approach-using-deep |
| Repo | |
| Framework | |
