Paper Group ANR 735
Precise Runtime Analysis for Plateaus. Fully Convolutional Network for Melanoma Diagnostics. Email Classification into Relevant Category Using Neural Networks. Queuing Theory Guided Intelligent Traffic Scheduling through Video Analysis using Dirichlet Process Mixture Model. Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning. C …
Precise Runtime Analysis for Plateaus
| Title | Precise Runtime Analysis for Plateaus |
| Authors | Denis Antipov, Benjamin Doerr |
| Abstract | To gain a better theoretical understanding of how evolutionary algorithms cope with plateaus of constant fitness, we analyze how the $(1 + 1)$ EA optimizes the $n$-dimensional $Plateau_k$ function. This function has a plateau of second-best fitness in a radius of $k$ around the optimum. As optimization algorithm, we regard the $(1 + 1)$ EA using an arbitrary unbiased mutation operator. Denoting by $\alpha$ the random number of bits flipped in an application of this operator and assuming $\Pr[\alpha = 1] = \Omega(1)$, we show the surprising result that for $k \ge 2$ the expected optimization time of this algorithm is [\frac{n^k}{k!\Pr[1 \le \alpha \le k]}(1 + o(1)),] that is, the size of the plateau times the expected waiting time for an iteration flipping between $1$ and $k$ bits. Our result implies that the optimal mutation rate for this function is approximately $k/en$. Our main analysis tool is a combined analysis of the Markov chains on the search point space and on the Hamming level space, an approach that promises to be useful also for other plateau problems. |
| Tasks | |
| Published | 2018-06-04 |
| URL | https://arxiv.org/abs/1806.01331v3 |
| https://arxiv.org/pdf/1806.01331v3.pdf | |
| PWC | https://paperswithcode.com/paper/precise-runtime-analysis-for-plateaus |
| Repo | |
| Framework | |
Fully Convolutional Network for Melanoma Diagnostics
| Title | Fully Convolutional Network for Melanoma Diagnostics |
| Authors | Adon Phillips, Iris Teo, Jochen Lang |
| Abstract | This work seeks to determine how modern machine learning techniques may be applied to the previously unexplored topic of melanoma diagnostics using digital pathology. We curated a new dataset of 50 patient cases of cutaneous melanoma using digital pathology. We provide gold standard annotations for three tissue types (tumour, epidermis, and dermis) which are important for the prognostic measurements known as Breslow thickness and Clark level. Then, we devised a novel multi-stride fully convolutional network (FCN) architecture that outperformed other networks trained and evaluated using the same data according to standard metrics. Finally, we trained a model to detect and localize the target tissue types. When processing previously unseen cases, our model’s output is qualitatively very similar to the gold standard. In addition to the standard metrics computed as a baseline for our approach, we asked three additional pathologists to measure the Breslow thickness on the network’s output. Their responses were diagnostically equivalent to the ground truth measurements, and when removing cases where a measurement was not appropriate, inter-rater reliability (IRR) between the four pathologists was 75.0%. Given the qualitative and quantitative results, it is possible to overcome the discriminative challenges of the skin and tumour anatomy for segmentation using modern machine learning techniques, though more work is required to improve the network’s performance on dermis segmentation. Further, we show that it is possible to achieve a level of accuracy required to manually perform the Breslow thickness measurement. |
| Tasks | |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.04765v1 |
| http://arxiv.org/pdf/1806.04765v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-convolutional-network-for-melanoma |
| Repo | |
| Framework | |
Email Classification into Relevant Category Using Neural Networks
| Title | Email Classification into Relevant Category Using Neural Networks |
| Authors | Deepak Kumar Gupta, Shruti Goyal |
| Abstract | In the real world, many online shopping websites or service provider have single email-id where customers can send their query, concern etc. At the back-end service provider receive million of emails every week, how they can identify which email is belonged of a particular department? This paper presents an artificial neural network (ANN) model that is used to solve this problem and experiments are carried out on user personal Gmail emails datasets. This problem can be generalised as typical Text Classification or Categorization. |
| Tasks | Text Classification |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.03971v1 |
| http://arxiv.org/pdf/1802.03971v1.pdf | |
| PWC | https://paperswithcode.com/paper/email-classification-into-relevant-category |
| Repo | |
| Framework | |
Queuing Theory Guided Intelligent Traffic Scheduling through Video Analysis using Dirichlet Process Mixture Model
| Title | Queuing Theory Guided Intelligent Traffic Scheduling through Video Analysis using Dirichlet Process Mixture Model |
| Authors | Santhosh Kelathodi Kumaran, Debi Prosad Dogra, Partha Pratim Roy |
| Abstract | Accurate prediction of traffic signal duration for roadway junction is a challenging problem due to the dynamic nature of traffic flows. Though supervised learning can be used, parameters may vary across roadway junctions. In this paper, we present a computer vision guided expert system that can learn the departure rate of a given traffic junction modeled using traditional queuing theory. First, we temporally group the optical flow of the moving vehicles using Dirichlet Process Mixture Model (DPMM). These groups are referred to as tracklets or temporal clusters. Tracklet features are then used to learn the dynamic behavior of a traffic junction, especially during on/off cycles of a signal. The proposed queuing theory based approach can predict the signal open duration for the next cycle with higher accuracy when compared with other popular features used for tracking. The hypothesis has been verified on two publicly available video datasets. The results reveal that the DPMM based features are better than existing tracking frameworks to estimate $\mu$. Thus, signal duration prediction is more accurate when tested on these datasets.The method can be used for designing intelligent operator-independent traffic control systems for roadway junctions at cities and highways. |
| Tasks | Optical Flow Estimation |
| Published | 2018-03-17 |
| URL | http://arxiv.org/abs/1803.06480v1 |
| http://arxiv.org/pdf/1803.06480v1.pdf | |
| PWC | https://paperswithcode.com/paper/queuing-theory-guided-intelligent-traffic |
| Repo | |
| Framework | |
Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning
| Title | Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning |
| Authors | Shang-Yu Su, Xiujun Li, Jianfeng Gao, Jingjing Liu, Yun-Nung Chen |
| Abstract | This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion dialogue policy learning. To obviate DDQ’s high dependency on the quality of simulated experiences, we incorporate an RNN-based discriminator in D3Q to differentiate simulated experience from real user experience in order to control the quality of training data. Experiments show that D3Q significantly outperforms DDQ by controlling the quality of simulated experience used for planning. The effectiveness and robustness of D3Q is further demonstrated in a domain extension setting, where the agent’s capability of adapting to a changing environment is tested. |
| Tasks | Task-Completion Dialogue Policy Learning |
| Published | 2018-08-28 |
| URL | http://arxiv.org/abs/1808.09442v2 |
| http://arxiv.org/pdf/1808.09442v2.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-deep-dyna-q-robust-planning |
| Repo | |
| Framework | |
Computer Vision-aided Atom Tracking in STEM Imaging
| Title | Computer Vision-aided Atom Tracking in STEM Imaging |
| Authors | Yawei Hui, Yaohua Liu |
| Abstract | To address the SMC’17 data challenge – “Data mining atomically resolved images for material properties”, we first used the classic “blob detection” algorithms developed in computer vision to identify all atom centers in each STEM image frame. With the help of nearest neighbor analysis, we then found and labeled every atom center common to all the STEM frames and tracked their movements through the given time interval for both Molybdenum or Selenium atoms. |
| Tasks | |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.05076v1 |
| http://arxiv.org/pdf/1809.05076v1.pdf | |
| PWC | https://paperswithcode.com/paper/computer-vision-aided-atom-tracking-in-stem |
| Repo | |
| Framework | |
Median activation functions for graph neural networks
| Title | Median activation functions for graph neural networks |
| Authors | Luana Ruiz, Fernando Gama, Antonio G. Marques, Alejandro Ribeiro |
| Abstract | Graph neural networks (GNNs) have been shown to replicate convolutional neural networks’ (CNNs) superior performance in many problems involving graphs. By replacing regular convolutions with linear shift-invariant graph filters (LSI-GFs), GNNs take into account the (irregular) structure of the graph and provide meaningful representations of network data. However, LSI-GFs fail to encode local nonlinear graph signal behavior, and so do regular activation functions, which are nonlinear but pointwise. To address this issue, we propose median activation functions with support on graph neighborhoods instead of individual nodes. A GNN architecture with a trainable multirresolution version of this activation function is then tested on synthetic and real-word datasets, where we show that median activation functions can improve GNN capacity with marginal increase in complexity. |
| Tasks | |
| Published | 2018-10-29 |
| URL | http://arxiv.org/abs/1810.12165v2 |
| http://arxiv.org/pdf/1810.12165v2.pdf | |
| PWC | https://paperswithcode.com/paper/median-activation-functions-for-graph-neural |
| Repo | |
| Framework | |
Terabyte-scale Deep Multiple Instance Learning for Classification and Localization in Pathology
| Title | Terabyte-scale Deep Multiple Instance Learning for Classification and Localization in Pathology |
| Authors | Gabriele Campanella, Vitor Werneck Krauss Silva, Thomas J. Fuchs |
| Abstract | In the field of computational pathology, the use of decision support systems powered by state-of-the-art deep learning solutions has been hampered by the lack of large labeled datasets. Until recently, studies relied on datasets in the order of few hundreds of slides which are not enough to train a model that can work at scale in the clinic. Here, we have gathered a dataset consisting of 12,160 slides, two orders of magnitude larger than previous datasets in pathology and equivalent to 25 times the pixel count of the entire ImageNet dataset. Given the size of our dataset it is possible for us to train a deep learning model under the Multiple Instance Learning (MIL) assumption where only the overall slide diagnosis is necessary for training, avoiding all the expensive pixel-wise annotations that are usually part of supervised learning approaches. We test our framework on a complex task, that of prostate cancer diagnosis on needle biopsies. We performed a thorough evaluation of the performance of our MIL pipeline under several conditions achieving an AUC of 0.98 on a held-out test set of 1,824 slides. These results open the way for training accurate diagnosis prediction models at scale, laying the foundation for decision support system deployment in the clinic. |
| Tasks | Multiple Instance Learning |
| Published | 2018-05-17 |
| URL | http://arxiv.org/abs/1805.06983v2 |
| http://arxiv.org/pdf/1805.06983v2.pdf | |
| PWC | https://paperswithcode.com/paper/terabyte-scale-deep-multiple-instance |
| Repo | |
| Framework | |
Reinforcement Learning with Perturbed Rewards
| Title | Reinforcement Learning with Perturbed Rewards |
| Authors | Jingkang Wang, Yang Liu, Bo Li |
| Abstract | Recent studies have shown that reinforcement learning (RL) models are vulnerable in various noisy scenarios. For instance, the observed reward channel is often subject to noise in practice (e.g., when rewards are collected through sensors), and is therefore not credible. In addition, for applications such as robotics, a deep reinforcement learning (DRL) algorithm can be manipulated to produce arbitrary errors by receiving corrupted rewards. In this paper, we consider noisy RL problems with perturbed rewards, which can be approximated with a confusion matrix. We develop a robust RL framework that enables agents to learn in noisy environments where only perturbed rewards are observed. Our solution framework builds on existing RL/DRL algorithms and firstly addresses the biased noisy reward setting without any assumptions on the true distribution (e.g., zero-mean Gaussian noise as made in previous works). The core ideas of our solution include estimating a reward confusion matrix and defining a set of unbiased surrogate rewards. We prove the convergence and sample complexity of our approach. Extensive experiments on different DRL platforms show that trained policies based on our estimated surrogate reward can achieve higher expected rewards, and converge faster than existing baselines. For instance, the state-of-the-art PPO algorithm is able to obtain 84.6% and 80.8% improvements on average score for five Atari games, with error rates as 10% and 30% respectively. |
| Tasks | Atari Games |
| Published | 2018-10-02 |
| URL | https://arxiv.org/abs/1810.01032v4 |
| https://arxiv.org/pdf/1810.01032v4.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-with-perturbed-rewards |
| Repo | |
| Framework | |
Robustness via curvature regularization, and vice versa
| Title | Robustness via curvature regularization, and vice versa |
| Authors | Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Jonathan Uesato, Pascal Frossard |
| Abstract | State-of-the-art classifiers have been shown to be largely vulnerable to adversarial perturbations. One of the most effective strategies to improve robustness is adversarial training. In this paper, we investigate the effect of adversarial training on the geometry of the classification landscape and decision boundaries. We show in particular that adversarial training leads to a significant decrease in the curvature of the loss surface with respect to inputs, leading to a drastically more “linear” behaviour of the network. Using a locally quadratic approximation, we provide theoretical evidence on the existence of a strong relation between large robustness and small curvature. To further show the importance of reduced curvature for improving the robustness, we propose a new regularizer that directly minimizes curvature of the loss surface, and leads to adversarial robustness that is on par with adversarial training. Besides being a more efficient and principled alternative to adversarial training, the proposed regularizer confirms our claims on the importance of exhibiting quasi-linear behavior in the vicinity of data points in order to achieve robustness. |
| Tasks | |
| Published | 2018-11-23 |
| URL | http://arxiv.org/abs/1811.09716v1 |
| http://arxiv.org/pdf/1811.09716v1.pdf | |
| PWC | https://paperswithcode.com/paper/robustness-via-curvature-regularization-and |
| Repo | |
| Framework | |
Information Scaling Law of Deep Neural Networks
| Title | Information Scaling Law of Deep Neural Networks |
| Authors | Xiao-Yang Liu |
| Abstract | With the rapid development of Deep Neural Networks (DNNs), various network models that show strong computing power and impressive expressive power are proposed. However, there is no comprehensive informational interpretation of DNNs from the perspective of information theory. Due to the nonlinear function and the uncertain number of layers and neural units used in the DNNs, the network structure shows nonlinearity and complexity. With the typical DNNs named Convolutional Arithmetic Circuits (ConvACs), the complex DNNs can be converted into mathematical formula. Thus, we can use rigorous mathematical theory especially the information theory to analyse the complicated DNNs. In this paper, we propose a novel information scaling law scheme that can interpret the network’s inner organization by information theory. First, we show the informational interpretation of the activation function. Secondly, we prove that the information entropy increases when the information is transmitted through the ConvACs. Finally, we propose the information scaling law of ConvACs through making a reasonable assumption. |
| Tasks | |
| Published | 2018-02-13 |
| URL | http://arxiv.org/abs/1802.04473v1 |
| http://arxiv.org/pdf/1802.04473v1.pdf | |
| PWC | https://paperswithcode.com/paper/information-scaling-law-of-deep-neural |
| Repo | |
| Framework | |
Learning Conditional Random Fields with Augmented Observations for Partially Observed Action Recognition
| Title | Learning Conditional Random Fields with Augmented Observations for Partially Observed Action Recognition |
| Authors | Shih-Yao Lin, Yen-Yu Lin, Chu-Song Chen, Yi-Ping Hung |
| Abstract | This paper aims at recognizing partially observed human actions in videos. Action videos acquired in uncontrolled environments often contain corrupt frames, which make actions partially observed. Furthermore, these frames can last for arbitrary lengths of time and appear irregularly. They are inconsistent with training data and degrade the performance of pre-trained action recognition systems. We present an approach to address this issue. For each training and testing actions, we divide it into segments and explore the mutual dependency between temporal segments. This property states that the similarity of two actions at one segment often implies their similarity at another. We augment each segment with extra alternatives retrieved from training data. The augmentation algorithm is designed in a way where a few alternatives are good enough to replace the original segment where corrupt frames occur. Our approach is developed upon hidden conditional random fields and leverages the flexibility of hidden variables for uncertainty handling. It turns out that our approach integrates corrupt segment detection and alternative selection into the process of prediction, and can recognize partially observed actions more accurately. It is evaluated on both fully observed actions and partially observed ones with either synthetic or real corrupt frames. The experimental results manifest its general applicability and superior performance, especially when corrupt frames are present in the action videos. |
| Tasks | Temporal Action Localization |
| Published | 2018-11-25 |
| URL | http://arxiv.org/abs/1811.09986v3 |
| http://arxiv.org/pdf/1811.09986v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-conditional-random-fields-with |
| Repo | |
| Framework | |
Fair comparison of skin detection approaches on publicly available datasets
| Title | Fair comparison of skin detection approaches on publicly available datasets |
| Authors | Alessandra Lumini, Loris Nanni |
| Abstract | Skin detection is the process of discriminating skin and non-skin regions in a digital image and it is widely used in several applications ranging from hand gesture analysis to track body parts and face detection. Skin detection is a challenging problem which has drawn extensive attention from the research community, nevertheless a fair comparison among approaches is very difficult due to the lack of a common benchmark and a unified testing protocol. In this work, we investigate the most recent researches in this field and we propose a fair comparison among approaches using several different datasets. The major contributions of this work are an exhaustive literature review of skin color detection approaches, a framework to evaluate and combine different skin detector approaches, whose source code is made freely available for future research, and an extensive experimental comparison among several recent methods which have also been used to define an ensemble that works well in many different problems. Experiments are carried out in 10 different datasets including more than 10000 labelled images: experimental results confirm that the best method here proposed obtains a very good performance with respect to other stand-alone approaches, without requiring ad hoc parameter tuning. A MATLAB version of the framework for testing and of the methods proposed in this paper will be freely available from https://github.com/LorisNanni |
| Tasks | Face Detection |
| Published | 2018-02-07 |
| URL | https://arxiv.org/abs/1802.02531v4 |
| https://arxiv.org/pdf/1802.02531v4.pdf | |
| PWC | https://paperswithcode.com/paper/fair-comparison-of-skin-detection-approaches |
| Repo | |
| Framework | |
Importance Weighted Generative Networks
| Title | Importance Weighted Generative Networks |
| Authors | Maurice Diesendruck, Ethan R. Elenberg, Rajat Sen, Guy W. Cole, Sanjay Shakkottai, Sinead A. Williamson |
| Abstract | Deep generative networks can simulate from a complex target distribution, by minimizing a loss with respect to samples from that distribution. However, often we do not have direct access to our target distribution - our data may be subject to sample selection bias, or may be from a different but related distribution. We present methods based on importance weighting that can estimate the loss with respect to a target distribution, even if we cannot access that distribution directly, in a variety of settings. These estimators, which differentially weight the contribution of data to the loss function, offer both theoretical guarantees and impressive empirical performance. |
| Tasks | |
| Published | 2018-06-07 |
| URL | https://arxiv.org/abs/1806.02512v2 |
| https://arxiv.org/pdf/1806.02512v2.pdf | |
| PWC | https://paperswithcode.com/paper/importance-weighted-generative-networks |
| Repo | |
| Framework | |
Overview: A Hierarchical Framework for Plan Generation and Execution in Multi-Robot Systems
| Title | Overview: A Hierarchical Framework for Plan Generation and Execution in Multi-Robot Systems |
| Authors | Hang Ma, Wolfgang Hönig, Liron Cohen, Tansel Uras, Hong Xu, T. K. Satish Kumar, Nora Ayanian, Sven Koenig |
| Abstract | The authors present an overview of a hierarchical framework for coordinating task- and motion-level operations in multirobot systems. Their framework is based on the idea of using simple temporal networks to simultaneously reason about precedence/causal constraints required for task-level coordination and simple temporal constraints required to take some kinematic constraints of robots into account. In the plan-generation phase, the framework provides a computationally scalable method for generating plans that achieve high-level tasks for groups of robots and take some of their kinematic constraints into account. In the plan-execution phase, the framework provides a method for absorbing an imperfect plan execution to avoid time-consuming re-planning in many cases. The authors use the multirobot path-planning problem as a case study to present the key ideas behind their framework for the long-term autonomy of multirobot systems. |
| Tasks | |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1804.00038v1 |
| http://arxiv.org/pdf/1804.00038v1.pdf | |
| PWC | https://paperswithcode.com/paper/overview-a-hierarchical-framework-for-plan |
| Repo | |
| Framework | |
