Paper Group ANR 389
Convolutional Neural Network Committees for Melanoma Classification with Classical And Expert Knowledge Based Image Transforms Data Augmentation. SLDR-DL: A Framework for SLD-Resolution with Deep Learning. WordFence: Text Detection in Natural Images with Border Awareness. Optimization assisted MCMC. Tracking of enriched dialog states for flexible c …
Convolutional Neural Network Committees for Melanoma Classification with Classical And Expert Knowledge Based Image Transforms Data Augmentation
| Title | Convolutional Neural Network Committees for Melanoma Classification with Classical And Expert Knowledge Based Image Transforms Data Augmentation |
| Authors | Cristina Nader Vasconcelos, Bárbara Nader Vasconcelos |
| Abstract | Skin cancer is a major public health problem, as is the most common type of cancer and represents more than half of cancer diagnoses worldwide. Early detection influences the outcome of the disease and motivates our work. We investigate the composition of CNN committees and data augmentation for the the ISBI 2017 Melanoma Classification Challenge (named Skin Lesion Analysis towards Melanoma Detection) facing the peculiarities of dealing with such a small, unbalanced, biological database. For that, we explore committees of Convolutional Neural Networks trained over the ISBI challenge training dataset artificially augmented by both classical image processing transforms and image warping guided by specialist knowledge about the lesion axis and improve the final classifier invariance to common melanoma variations. |
| Tasks | Data Augmentation |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1702.07025v2 |
| http://arxiv.org/pdf/1702.07025v2.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-network-committees-for |
| Repo | |
| Framework | |
SLDR-DL: A Framework for SLD-Resolution with Deep Learning
| Title | SLDR-DL: A Framework for SLD-Resolution with Deep Learning |
| Authors | Cheng-Hao Cai |
| Abstract | This paper introduces an SLD-resolution technique based on deep learning. This technique enables neural networks to learn from old and successful resolution processes and to use learnt experiences to guide new resolution processes. An implementation of this technique is named SLDR-DL. It includes a Prolog library of deep feedforward neural networks and some essential functions of resolution. In the SLDR-DL framework, users can define logical rules in the form of definite clauses and teach neural networks to use the rules in reasoning processes. |
| Tasks | |
| Published | 2017-05-05 |
| URL | http://arxiv.org/abs/1705.02210v1 |
| http://arxiv.org/pdf/1705.02210v1.pdf | |
| PWC | https://paperswithcode.com/paper/sldr-dl-a-framework-for-sld-resolution-with |
| Repo | |
| Framework | |
WordFence: Text Detection in Natural Images with Border Awareness
| Title | WordFence: Text Detection in Natural Images with Border Awareness |
| Authors | Andrei Polzounov, Artsiom Ablavatski, Sergio Escalera, Shijian Lu, Jianfei Cai |
| Abstract | In recent years, text recognition has achieved remarkable success in recognizing scanned document text. However, word recognition in natural images is still an open problem, which generally requires time consuming post-processing steps. We present a novel architecture for individual word detection in scene images based on semantic segmentation. Our contributions are twofold: the concept of WordFence, which detects border areas surrounding each individual word and a novel pixelwise weighted softmax loss function which penalizes background and emphasizes small text regions. WordFence ensures that each word is detected individually, and the new loss function provides a strong training signal to both text and word border localization. The proposed technique avoids intensive post-processing, producing an end-to-end word detection system. We achieve superior localization recall on common benchmark datasets - 92% recall on ICDAR11 and ICDAR13 and 63% recall on SVT. Furthermore, our end-to-end word recognition system achieves state-of-the-art 86% F-Score on ICDAR13. |
| Tasks | Semantic Segmentation |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05483v1 |
| http://arxiv.org/pdf/1705.05483v1.pdf | |
| PWC | https://paperswithcode.com/paper/wordfence-text-detection-in-natural-images |
| Repo | |
| Framework | |
Optimization assisted MCMC
| Title | Optimization assisted MCMC |
| Authors | Ricky Fok, Aijun An, Xiaogang Wang |
| Abstract | Markov Chain Monte Carlo (MCMC) sampling methods are widely used but often encounter either slow convergence or biased sampling when applied to multimodal high dimensional distributions. In this paper, we present a general framework of improving classical MCMC samplers by employing a global optimization method. The global optimization method first reduces a high dimensional search to an one dimensional geodesic to find a starting point close to a local mode. The search is accelerated and completed by using a local search method such as BFGS. We modify the target distribution by extracting a local Gaussian distribution aound the found mode. The process is repeated to find all the modes during sampling on the fly. We integrate the optimization algorithm into the Wormhole Hamiltonian Monte Carlo (WHMC) method. Experimental results show that, when applied to high dimensional, multimodal Gaussian mixture models and the network sensor localization problem, the proposed method achieves much faster convergence, with relative error from the mean improved by about an order of magnitude than WHMC in some cases. |
| Tasks | |
| Published | 2017-09-09 |
| URL | http://arxiv.org/abs/1709.02888v1 |
| http://arxiv.org/pdf/1709.02888v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimization-assisted-mcmc |
| Repo | |
| Framework | |
Tracking of enriched dialog states for flexible conversational information access
| Title | Tracking of enriched dialog states for flexible conversational information access |
| Authors | Yinpei Dai, Zhijian Ou, Dawei Ren, Pengfei Yu |
| Abstract | Dialog state tracking (DST) is a crucial component in a task-oriented dialog system for conversational information access. A common practice in current dialog systems is to define the dialog state by a set of slot-value pairs. Such representation of dialog states and the slot-filling based DST have been widely employed, but suffer from three drawbacks. (1) The dialog state can contain only a single value for a slot, and (2) can contain only users’ affirmative preference over the values for a slot. (3) Current task-based dialog systems mainly focus on the searching task, while the enquiring task is also very common in practice. The above observations motivate us to enrich current representation of dialog states and collect a brand new dialog dataset about movies, based upon which we build a new DST, called enriched DST (EDST), for flexible accessing movie information. The EDST supports the searching task, the enquiring task and their mixed task. We show that the new EDST method not only achieves good results on Iqiyi dataset, but also outperforms other state-of-the-art DST methods on the traditional dialog datasets, WOZ2.0 and DSTC2. |
| Tasks | Slot Filling |
| Published | 2017-11-09 |
| URL | http://arxiv.org/abs/1711.03381v2 |
| http://arxiv.org/pdf/1711.03381v2.pdf | |
| PWC | https://paperswithcode.com/paper/tracking-of-enriched-dialog-states-for |
| Repo | |
| Framework | |
Variational Memory Addressing in Generative Models
| Title | Variational Memory Addressing in Generative Models |
| Authors | Jörg Bornschein, Andriy Mnih, Daniel Zoran, Danilo J. Rezende |
| Abstract | Aiming to augment generative models with external memory, we interpret the output of a memory module with stochastic addressing as a conditional mixture distribution, where a read operation corresponds to sampling a discrete memory address and retrieving the corresponding content from memory. This perspective allows us to apply variational inference to memory addressing, which enables effective training of the memory module by using the target information to guide memory lookups. Stochastic addressing is particularly well-suited for generative models as it naturally encourages multimodality which is a prominent aspect of most high-dimensional datasets. Treating the chosen address as a latent variable also allows us to quantify the amount of information gained with a memory lookup and measure the contribution of the memory module to the generative process. To illustrate the advantages of this approach we incorporate it into a variational autoencoder and apply the resulting model to the task of generative few-shot learning. The intuition behind this architecture is that the memory module can pick a relevant template from memory and the continuous part of the model can concentrate on modeling remaining variations. We demonstrate empirically that our model is able to identify and access the relevant memory contents even with hundreds of unseen Omniglot characters in memory |
| Tasks | Few-Shot Learning, Omniglot |
| Published | 2017-09-21 |
| URL | http://arxiv.org/abs/1709.07116v1 |
| http://arxiv.org/pdf/1709.07116v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-memory-addressing-in-generative |
| Repo | |
| Framework | |
Bayesian bandits: balancing the exploration-exploitation tradeoff via double sampling
| Title | Bayesian bandits: balancing the exploration-exploitation tradeoff via double sampling |
| Authors | Iñigo Urteaga, Chris H. Wiggins |
| Abstract | Reinforcement learning studies how to balance exploration and exploitation in real-world systems, optimizing interactions with the world while simultaneously learning how the world operates. One general class of algorithms for such learning is the multi-armed bandit setting. Randomized probability matching, based upon the Thompson sampling approach introduced in the 1930s, has recently been shown to perform well and to enjoy provable optimality properties. It permits generative, interpretable modeling in a Bayesian setting, where prior knowledge is incorporated, and the computed posteriors naturally capture the full state of knowledge. In this work, we harness the information contained in the Bayesian posterior and estimate its sufficient statistics via sampling. In several application domains, for example in health and medicine, each interaction with the world can be expensive and invasive, whereas drawing samples from the model is relatively inexpensive. Exploiting this viewpoint, we develop a double sampling technique driven by the uncertainty in the learning process: it favors exploitation when certain about the properties of each arm, exploring otherwise. The proposed algorithm does not make any distributional assumption and it is applicable to complex reward distributions, as long as Bayesian posterior updates are computable. Utilizing the estimated posterior sufficient statistics, double sampling autonomously balances the exploration-exploitation tradeoff to make better informed decisions. We empirically show its reduced cumulative regret when compared to state-of-the-art alternatives in representative bandit settings. |
| Tasks | |
| Published | 2017-09-10 |
| URL | http://arxiv.org/abs/1709.03162v2 |
| http://arxiv.org/pdf/1709.03162v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-bandits-balancing-the-exploration |
| Repo | |
| Framework | |
MILD: Multi-Index hashing for Loop closure Detection
| Title | MILD: Multi-Index hashing for Loop closure Detection |
| Authors | Lei Han, Lu Fang |
| Abstract | Loop Closure Detection (LCD) has been proved to be extremely useful in global consistent visual Simultaneously Localization and Mapping (SLAM) and appearance-based robot relocalization. Methods exploiting binary features in bag of words representation have recently gained a lot of popularity for their efficiency, but suffer from low recall due to the inherent drawback that high dimensional binary feature descriptors lack well-defined centroids. In this paper, we propose a realtime LCD approach called MILD (Multi-Index Hashing for Loop closure Detection), in which image similarity is measured by feature matching directly to achieve high recall without introducing extra computational complexity with the aid of Multi-Index Hashing (MIH). A theoretical analysis of the approximate image similarity measurement using MIH is presented, which reveals the trade-off between efficiency and accuracy from a probabilistic perspective. Extensive comparisons with state-of-the-art LCD methods demonstrate the superiority of MILD in both efficiency and accuracy. |
| Tasks | Loop Closure Detection |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1702.08780v1 |
| http://arxiv.org/pdf/1702.08780v1.pdf | |
| PWC | https://paperswithcode.com/paper/mild-multi-index-hashing-for-loop-closure |
| Repo | |
| Framework | |
Lexicographic choice functions
| Title | Lexicographic choice functions |
| Authors | Arthur Van Camp, Gert de Cooman, Enrique Miranda |
| Abstract | We investigate a generalisation of the coherent choice functions considered by Seidenfeld et al. (2010), by sticking to the convexity axiom but imposing no Archimedeanity condition. We define our choice functions on vector spaces of options, which allows us to incorporate as special cases both Seidenfeld et al.‘s (2010) choice functions on horse lotteries and sets of desirable gambles (Quaeghebeur, 2014), and to investigate their connections. We show that choice functions based on sets of desirable options (gambles) satisfy Seidenfeld’s convexity axiom only for very particular types of sets of desirable options, which are in a one-to-one relationship with the lexicographic probabilities. We call them lexicographic choice functions. Finally, we prove that these choice functions can be used to determine the most conservative convex choice function associated with a given binary relation. |
| Tasks | |
| Published | 2017-07-10 |
| URL | http://arxiv.org/abs/1707.03069v1 |
| http://arxiv.org/pdf/1707.03069v1.pdf | |
| PWC | https://paperswithcode.com/paper/lexicographic-choice-functions |
| Repo | |
| Framework | |
In Defense of the Indefensible: A Very Naive Approach to High-Dimensional Inference
| Title | In Defense of the Indefensible: A Very Naive Approach to High-Dimensional Inference |
| Authors | Sen Zhao, Ali Shojaie, Daniela Witten |
| Abstract | In recent years, a great deal of interest has focused on conducting inference on the parameters in a linear model in the high-dimensional setting. In this paper, we consider a simple and very na"{i}ve two-step procedure for this task, in which we (i) fit a lasso model in order to obtain a subset of the variables; and (ii) fit a least squares model on the lasso-selected set. Conventional statistical wisdom tells us that we cannot make use of the standard statistical inference tools for the resulting least squares model (such as confidence intervals and $p$-values), since we peeked at the data twice: once in running the lasso, and again in fitting the least squares model. However, in this paper, we show that under a certain set of assumptions, with high probability, the set of variables selected by the lasso is deterministic. Consequently, the na"{i}ve two-step approach can yield confidence intervals that have asymptotically correct coverage, as well as p-values with proper Type-I error control. Furthermore, this two-step approach unifies two existing camps of work on high-dimensional inference: one camp has focused on inference based on a sub-model selected by the lasso, and the other has focused on inference using a debiased version of the lasso estimator. |
| Tasks | |
| Published | 2017-05-16 |
| URL | http://arxiv.org/abs/1705.05543v2 |
| http://arxiv.org/pdf/1705.05543v2.pdf | |
| PWC | https://paperswithcode.com/paper/in-defense-of-the-indefensible-a-very-naive |
| Repo | |
| Framework | |
Selective Inference for Change Point Detection in Multi-dimensional Sequences
| Title | Selective Inference for Change Point Detection in Multi-dimensional Sequences |
| Authors | Yuta Umezu, Ichiro Takeuchi |
| Abstract | We study the problem of detecting change points (CPs) that are characterized by a subset of dimensions in a multi-dimensional sequence. A method for detecting those CPs can be formulated as a two-stage method: one for selecting relevant dimensions, and another for selecting CPs. It has been difficult to properly control the false detection probability of these CP detection methods because selection bias in each stage must be properly corrected. Our main contribution in this paper is to formulate a CP detection problem as a selective inference problem, and show that exact (non-asymptotic) inference is possible for a class of CP detection methods. We demonstrate the performances of the proposed selective inference framework through numerical simulations and its application to our motivating medical data analysis problem. |
| Tasks | Change Point Detection |
| Published | 2017-06-01 |
| URL | http://arxiv.org/abs/1706.00514v3 |
| http://arxiv.org/pdf/1706.00514v3.pdf | |
| PWC | https://paperswithcode.com/paper/selective-inference-for-change-point |
| Repo | |
| Framework | |
Extrinsic Parameter Calibration for Line Scanning Cameras on Ground Vehicles with Navigation Systems Using a Calibration Pattern
| Title | Extrinsic Parameter Calibration for Line Scanning Cameras on Ground Vehicles with Navigation Systems Using a Calibration Pattern |
| Authors | Alexander Wendel, James Underwood |
| Abstract | Line scanning cameras, which capture only a single line of pixels, have been increasingly used in ground based mobile or robotic platforms. In applications where it is advantageous to directly georeference the camera data to world coordinates, an accurate estimate of the camera’s 6D pose is required. This paper focuses on the common case where a mobile platform is equipped with a rigidly mounted line scanning camera, whose pose is unknown, and a navigation system providing vehicle body pose estimates. We propose a novel method that estimates the camera’s pose relative to the navigation system. The approach involves imaging and manually labelling a calibration pattern with distinctly identifiable points, triangulating these points from camera and navigation system data and reprojecting them in order to compute a likelihood, which is maximised to estimate the 6D camera pose. Additionally, a Markov Chain Monte Carlo (MCMC) algorithm is used to estimate the uncertainty of the offset. Tested on two different platforms, the method was able to estimate the pose to within 0.06 m / 1.05$^{\circ}$ and 0.18 m / 2.39$^{\circ}$. We also propose several approaches to displaying and interpreting the 6D results in a human readable way. |
| Tasks | Calibration |
| Published | 2017-09-04 |
| URL | http://arxiv.org/abs/1709.00846v3 |
| http://arxiv.org/pdf/1709.00846v3.pdf | |
| PWC | https://paperswithcode.com/paper/extrinsic-parameter-calibration-for-line |
| Repo | |
| Framework | |
Towards Semantic Fast-Forward and Stabilized Egocentric Videos
| Title | Towards Semantic Fast-Forward and Stabilized Egocentric Videos |
| Authors | Michel Melo Silva, Washington Luis Souza Ramos, Joao Pedro Klock Ferreira, Mario Fernando Montenegro Campos, Erickson Rangel Nascimento |
| Abstract | The emergence of low-cost personal mobiles devices and wearable cameras and the increasing storage capacity of video-sharing websites have pushed forward a growing interest towards first-person videos. Since most of the recorded videos compose long-running streams with unedited content, they are tedious and unpleasant to watch. The fast-forward state-of-the-art methods are facing challenges of balancing the smoothness of the video and the emphasis in the relevant frames given a speed-up rate. In this work, we present a methodology capable of summarizing and stabilizing egocentric videos by extracting the semantic information from the frames. This paper also describes a dataset collection with several semantically labeled videos and introduces a new smoothness evaluation metric for egocentric videos that is used to test our method. |
| Tasks | |
| Published | 2017-08-14 |
| URL | http://arxiv.org/abs/1708.04146v2 |
| http://arxiv.org/pdf/1708.04146v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-semantic-fast-forward-and-stabilized |
| Repo | |
| Framework | |
Proactive Resource Management for LTE in Unlicensed Spectrum: A Deep Learning Perspective
| Title | Proactive Resource Management for LTE in Unlicensed Spectrum: A Deep Learning Perspective |
| Authors | Ursula Challita, Li Dong, Walid Saad |
| Abstract | LTE in unlicensed spectrum using licensed assisted access LTE (LTE-LAA) is a promising approach to overcome the wireless spectrum scarcity. However, to reap the benefits of LTE-LAA, a fair coexistence mechanism with other incumbent WiFi deployments is required. In this paper, a novel deep learning approach is proposed for modeling the resource allocation problem of LTE-LAA small base stations (SBSs). The proposed approach enables multiple SBSs to proactively perform dynamic channel selection, carrier aggregation, and fractional spectrum access while guaranteeing fairness with existing WiFi networks and other LTE-LAA operators. Adopting a proactive coexistence mechanism enables future delay-tolerant LTE-LAA data demands to be served within a given prediction window ahead of their actual arrival time thus avoiding the underutilization of the unlicensed spectrum during off-peak hours while maximizing the total served LTE-LAA traffic load. To this end, a noncooperative game model is formulated in which SBSs are modeled as Homo Egualis agents that aim at predicting a sequence of future actions and thus achieving long-term equal weighted fairness with WLAN and other LTE-LAA operators over a given time horizon. The proposed deep learning algorithm is then shown to reach a mixed-strategy Nash equilibrium (NE), when it converges. Simulation results using real data traces show that the proposed scheme can yield up to 28% and 11% gains over a conventional reactive approach and a proportional fair coexistence mechanism, respectively. The results also show that the proposed framework prevents WiFi performance degradation for a densely deployed LTE-LAA network. |
| Tasks | |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1702.07031v2 |
| http://arxiv.org/pdf/1702.07031v2.pdf | |
| PWC | https://paperswithcode.com/paper/proactive-resource-management-for-lte-in |
| Repo | |
| Framework | |
Online Convolutional Dictionary Learning
| Title | Online Convolutional Dictionary Learning |
| Authors | Jialin Liu, Cristina Garcia-Cardona, Brendt Wohlberg, Wotao Yin |
| Abstract | While a number of different algorithms have recently been proposed for convolutional dictionary learning, this remains an expensive problem. The single biggest impediment to learning from large training sets is the memory requirements, which grow at least linearly with the size of the training set since all existing methods are batch algorithms. The work reported here addresses this limitation by extending online dictionary learning ideas to the convolutional context. |
| Tasks | Dictionary Learning |
| Published | 2017-06-29 |
| URL | http://arxiv.org/abs/1706.09563v2 |
| http://arxiv.org/pdf/1706.09563v2.pdf | |
| PWC | https://paperswithcode.com/paper/online-convolutional-dictionary-learning |
| Repo | |
| Framework | |
