Paper Group ANR 1758
Estimation of Personalized Heterogeneous Treatment Effects Using Concatenation and Augmentation of Feature Vectors. Towards a Wearable Interface for Food Quality Grading through ERP Analysis. Task-Agnostic Dynamics Priors for Deep Reinforcement Learning. Dependency Parsing for Spoken Dialog Systems. Progressive Learning Algorithm for Efficient Pers …
Estimation of Personalized Heterogeneous Treatment Effects Using Concatenation and Augmentation of Feature Vectors
| Title | Estimation of Personalized Heterogeneous Treatment Effects Using Concatenation and Augmentation of Feature Vectors |
| Authors | Lev V. Utkin, Mikhail V. Kots, Viacheslav S. Chukanov |
| Abstract | A new meta-algorithm for estimating the conditional average treatment effects is proposed in the paper. The main idea underlying the algorithm is to consider a new dataset consisting of feature vectors produced by means of concatenation of examples from control and treatment groups, which are close to each other. Outcomes of new data are defined as the difference between outcomes of the corresponding examples comprising new feature vectors. The second idea is based on the assumption that the number of controls is rather large and the control outcome function is precisely determined. This assumption allows us to augment treatments by generating feature vectors which are closed to available treatments. The outcome regression function constructed on the augmented set of concatenated feature vectors can be viewed as an estimator of the conditional average treatment effects. A simple modification of the Co-learner based on the random subspace method or the feature bagging is also proposed. Various numerical simulation experiments illustrate the proposed algorithm and show its outperformance in comparison with the well-known T-learner and X-learner for several types of the control and treatment outcome functions. |
| Tasks | |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03894v1 |
| https://arxiv.org/pdf/1909.03894v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimation-of-personalized-heterogeneous |
| Repo | |
| Framework | |
Towards a Wearable Interface for Food Quality Grading through ERP Analysis
| Title | Towards a Wearable Interface for Food Quality Grading through ERP Analysis |
| Authors | M. Guermandi, S. Benatti, D. Brunelli, V. Kartsch, L. Benini |
| Abstract | Sensory evaluation is used to assess the consumer acceptance of foods or other consumer products, so as to improve industrial processes and marketing strategies. The procedures currently involved are time-consuming because they require a statistical approach from measurements and feedback reports from a wide set of evaluators under a well-established measurement setup. In this paper, we propose to collect directly the signal of the perceived quality of the food from Event-related potentials (ERPs) that are the outcome of the processing of visual stimuli. This permits to narrow the number of evaluators since errors related to psychological factors are by-passed. We present the design of a wearable system for ERP measurement and we present preliminary results on the use of ERP to give a quantitative measure to the appearance of a food product. The system is developed to be wearable and our experiments demonstrate that is possible to use it to identify and classify the grade of acceptance of the food. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11633v1 |
| https://arxiv.org/pdf/1905.11633v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-wearable-interface-for-food-quality |
| Repo | |
| Framework | |
Task-Agnostic Dynamics Priors for Deep Reinforcement Learning
| Title | Task-Agnostic Dynamics Priors for Deep Reinforcement Learning |
| Authors | Yilun Du, Karthik Narasimhan |
| Abstract | While model-based deep reinforcement learning (RL) holds great promise for sample efficiency and generalization, learning an accurate dynamics model is often challenging and requires substantial interaction with the environment. A wide variety of domains have dynamics that share common foundations like the laws of classical mechanics, which are rarely exploited by existing algorithms. In fact, humans continuously acquire and use such dynamics priors to easily adapt to operating in new environments. In this work, we propose an approach to learn task-agnostic dynamics priors from videos and incorporate them into an RL agent. Our method involves pre-training a frame predictor on task-agnostic physics videos to initialize dynamics models (and fine-tune them) for unseen target environments. Our frame prediction architecture, SpatialNet, is designed specifically to capture localized physical phenomena and interactions. Our approach allows for both faster policy learning and convergence to better policies, outperforming competitive approaches on several different environments. We also demonstrate that incorporating this prior allows for more effective transfer between environments. |
| Tasks | |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.04819v4 |
| https://arxiv.org/pdf/1905.04819v4.pdf | |
| PWC | https://paperswithcode.com/paper/task-agnostic-dynamics-priors-for-deep |
| Repo | |
| Framework | |
Dependency Parsing for Spoken Dialog Systems
| Title | Dependency Parsing for Spoken Dialog Systems |
| Authors | Sam Davidson, Dian Yu, Zhou Yu |
| Abstract | Dependency parsing of conversational input can play an important role in language understanding for dialog systems by identifying the relationships between entities extracted from user utterances. Additionally, effective dependency parsing can elucidate differences in language structure and usage for discourse analysis of human-human versus human-machine dialogs. However, models trained on datasets based on news articles and web data do not perform well on spoken human-machine dialog, and currently available annotation schemes do not adapt well to dialog data. Therefore, we propose the Spoken Conversation Universal Dependencies (SCUD) annotation scheme that extends the Universal Dependencies (UD) (Nivre et al., 2016) guidelines to spoken human-machine dialogs. We also provide ConvBank, a conversation dataset between humans and an open-domain conversational dialog system with SCUD annotation. Finally, to demonstrate the utility of the dataset, we train a dependency parser on the ConvBank dataset. We demonstrate that by pre-training a dependency parser on a set of larger public datasets and fine-tuning on ConvBank data, we achieved the best result, 85.05% unlabeled and 77.82% labeled attachment accuracy. |
| Tasks | Dependency Parsing |
| Published | 2019-09-07 |
| URL | https://arxiv.org/abs/1909.03317v1 |
| https://arxiv.org/pdf/1909.03317v1.pdf | |
| PWC | https://paperswithcode.com/paper/dependency-parsing-for-spoken-dialog-systems |
| Repo | |
| Framework | |
Progressive Learning Algorithm for Efficient Person Re-Identification
| Title | Progressive Learning Algorithm for Efficient Person Re-Identification |
| Authors | Zhen Li, Hanyang Shao, Nian Xue, Liang Niu, LiangLiang Cao |
| Abstract | This paper studies the problem of Person Re-Identification (ReID)for large-scale applications. Recent research efforts have been devoted to building complicated part models, which introduce considerably high computational cost and memory consumption, inhibiting its practicability in large-scale applications. This paper aims to develop a novel learning strategy to find efficient feature embeddings while maintaining the balance of accuracy and model complexity. More specifically, we find by enhancing the classical triplet loss together with cross-entropy loss, our method can explore the hard examples and build a discriminant feature embedding yet compact enough for large-scale applications. Our method is carried out progressively using Bayesian optimization, and we call it the Progressive Learning Algorithm (PLA). Extensive experiments on three large-scale datasets show that our PLA is comparable or better than the-state-of-the-arts. Especially, on the challenging Market-1501 dataset, we achieve Rank-1=94.7%/mAP=89.4% while saving at least 30% parameters than strong part models. |
| Tasks | Person Re-Identification |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07447v1 |
| https://arxiv.org/pdf/1912.07447v1.pdf | |
| PWC | https://paperswithcode.com/paper/progressive-learning-algorithm-for-efficient |
| Repo | |
| Framework | |
Network Embedding: An Overview
| Title | Network Embedding: An Overview |
| Authors | Nino Arsov, Georgina Mirceva |
| Abstract | Networks are one of the most powerful structures for modeling problems in the real world. Downstream machine learning tasks defined on networks have the potential to solve a variety of problems. With link prediction, for instance, one can predict whether two persons will become friends on a social network. Many machine learning algorithms, however, require that each input example is a real vector. Network embedding encompasses various methods for unsupervised, and sometimes supervised, learning of feature representations of nodes and links in a network. Typically, embedding methods are based on the assumption that the similarity between nodes in the network should be reflected in the learned feature representations. In this paper, we review significant contributions to network embedding in the last decade. In particular, we look at four methods: Spectral Clustering, DeepWalk, Large-scale Information Network Embedding (LINE), and node2vec. We describe each method and list its advantages and shortcomings. In addition, we give examples of real-world machine learning problems on networks in which the embedding is critical in order to maximize the predictive performance of the machine learning task. Finally, we take a look at research trends and state-of-the art methods in the research on network embedding. |
| Tasks | Link Prediction, Network Embedding |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11726v1 |
| https://arxiv.org/pdf/1911.11726v1.pdf | |
| PWC | https://paperswithcode.com/paper/network-embedding-an-overview |
| Repo | |
| Framework | |
Iris Recognition for Personal Identification using LAMSTAR neural network
| Title | Iris Recognition for Personal Identification using LAMSTAR neural network |
| Authors | Shideh Homayon, Mahdi Salarian |
| Abstract | Iris recognition is one of the most important biometric recognition method. This is because the iris texture provides many features such as freckles, coronas, stripes, furrows, crypts, etc. Those features are unique for different people and distinguishable. Such unique features in the anatomical structure of the iris make it possible the differentiation among individuals. So during last years huge number of people have been trying to improve its performance. In this article first different common steps for the Iris recognition system is explained. Then a special type of neural network is used for recognition part. Experimental results show high accuracy can be obtained especially when the primary steps are done well. |
| Tasks | Iris Recognition |
| Published | 2019-07-28 |
| URL | https://arxiv.org/abs/1907.12145v1 |
| https://arxiv.org/pdf/1907.12145v1.pdf | |
| PWC | https://paperswithcode.com/paper/iris-recognition-for-personal-identification |
| Repo | |
| Framework | |
PT-ResNet: Perspective Transformation-Based Residual Network for Semantic Road Image Segmentation
| Title | PT-ResNet: Perspective Transformation-Based Residual Network for Semantic Road Image Segmentation |
| Authors | Rui Fan, Yuan Wang, Lei Qiao, Ruiwen Yao, Peng Han, Weidong Zhang, Ioannis Pitas, Ming Liu |
| Abstract | Semantic road region segmentation is a high-level task, which paves the way towards road scene understanding. This paper presents a residual network trained for semantic road segmentation. Firstly, we represent the projections of road disparities in the v-disparity map as a linear model, which can be estimated by optimizing the v-disparity map using dynamic programming. This linear model is then utilized to reduce the redundant information in the left and right road images. The right image is also transformed into the left perspective view, which greatly enhances the road surface similarity between the two images. Finally, the processed stereo images and their disparity maps are concatenated to create a set of 3D images, which are then utilized to train our neural network. The experimental results illustrate that our network achieves a maximum F1-measure of approximately 91.19% when analyzing the images from the KITTI road dataset. |
| Tasks | Scene Understanding, Semantic Segmentation |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13055v1 |
| https://arxiv.org/pdf/1910.13055v1.pdf | |
| PWC | https://paperswithcode.com/paper/pt-resnet-perspective-transformation-based |
| Repo | |
| Framework | |
Deep-SLAM++: Object-level RGBD SLAM based on class-specific deep shape priors
| Title | Deep-SLAM++: Object-level RGBD SLAM based on class-specific deep shape priors |
| Authors | Lan Hu, Wanting Xu, Kun Huang, Laurent Kneip |
| Abstract | In an effort to increase the capabilities of SLAM systems and produce object-level representations, the community increasingly investigates the imposition of higher-level priors into the estimation process. One such example is given by employing object detectors to load and register full CAD models. Our work extends this idea to environments with unknown objects and imposes object priors by employing modern class-specific neural networks to generate complete model geometry proposals. The difficulty of using such predictions in a real SLAM scenario is that the prediction performance depends on the view-point and measurement quality, with even small changes of the input data sometimes leading to a large variability in the network output. We propose a discrete selection strategy that finds the best among multiple proposals from different registered views by re-enforcing the agreement with the online depth measurements. The result is an effective object-level RGBD SLAM system that produces compact, high-fidelity, and dense 3D maps with semantic annotations. It outperforms traditional fusion strategies in terms of map completeness and resilience against degrading measurement quality. |
| Tasks | |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09691v2 |
| https://arxiv.org/pdf/1907.09691v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-slam-object-level-rgbd-slam-based-on |
| Repo | |
| Framework | |
Detection of perfusion ROI as a quality control in perfusion analysis
| Title | Detection of perfusion ROI as a quality control in perfusion analysis |
| Authors | Svitlana Alkhimova |
| Abstract | In perfusion analysis automated approaches for image processing is preferable due to reduce time-consuming tasks for radiologists. Assessment of perfusion results quality is important step in development of algorithms for automated processing. One of them is an assessment of perfusion maps quality based on detection of perfusion ROI. |
| Tasks | |
| Published | 2019-02-04 |
| URL | http://arxiv.org/abs/1902.01855v1 |
| http://arxiv.org/pdf/1902.01855v1.pdf | |
| PWC | https://paperswithcode.com/paper/detection-of-perfusion-roi-as-a-quality |
| Repo | |
| Framework | |
Crowd Density Estimation using Novel Feature Descriptor
| Title | Crowd Density Estimation using Novel Feature Descriptor |
| Authors | Adwan Alownie Alanazi, Muhammad Bilal |
| Abstract | Crowd density estimation is an important task for crowd monitoring. Many efforts have been done to automate the process of estimating crowd density from images and videos. Despite series of efforts, it remains a challenging task. In this paper, we proposes a new texture feature-based approach for the estimation of crowd density based on Completed Local Binary Pattern (CLBP). We first divide the image into blocks and then re-divide the blocks into cells. For each cell, we compute CLBP and then concatenate them to describe the texture of the corresponding block. We then train a multi-class Support Vector Machine (SVM) classifier, which classifies each block of image into one of four categories, i.e. Very Low, Low, Medium, and High. We evaluate our technique on the PETS 2009 dataset, and from the experiments, we show to achieve 95% accuracy for the proposed descriptor. We also compare other state-of-the-art texture descriptors and from the experimental results, we show that our proposed method outperforms other state-of-the-art methods. |
| Tasks | Density Estimation |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.05891v1 |
| https://arxiv.org/pdf/1905.05891v1.pdf | |
| PWC | https://paperswithcode.com/paper/crowd-density-estimation-using-novel-feature |
| Repo | |
| Framework | |
RLScheduler: Learn to Schedule HPC Batch Jobs Using Deep Reinforcement Learning
| Title | RLScheduler: Learn to Schedule HPC Batch Jobs Using Deep Reinforcement Learning |
| Authors | Di Zhang, Dong Dai, Youbiao He, Forrest Sheng Bao |
| Abstract | We present RLScheduler, a deep reinforcement learning based job scheduler for scheduling independent batch jobs in high-performance computing (HPC) environment. From knowing nothing about scheduling at beginning, RLScheduler is able to autonomously learn how to effectively schedule HPC batch jobs, targeting a given optimization goal. This is achieved by deep reinforcement learning with the help of specially designed neural network structures and various optimizations to stabilize and accelerate the learning. Our results show that RLScheduler can outperform existing heuristic scheduling algorithms, including a manually fine-tuned machine learning-based scheduler on the same workload. More importantly, we show that RLScheduler does not blindly over-fit the given workload to achieve such optimization, instead, it learns general rules for scheduling batch jobs which can be further applied to different workloads and systems to achieve similarly optimized performance. We also demonstrate that RLScheduler is capable of adjusting itself along with changing goals and workloads, making it an attractive solution for the future autonomous HPC management. |
| Tasks | |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.08925v1 |
| https://arxiv.org/pdf/1910.08925v1.pdf | |
| PWC | https://paperswithcode.com/paper/rlscheduler-learn-to-schedule-hpc-batch-jobs |
| Repo | |
| Framework | |
Filling Factors of Sunspots in SODISM Images
| Title | Filling Factors of Sunspots in SODISM Images |
| Authors | Amro F. Alasta, Abdrazag Algamudi, Fatma Almesrati, Mustapha Meftah, Rami Qahwaji |
| Abstract | Received: 1st December 2018; Accepted: 18th February 2019; Published: 1st April 2019 Abstract: The calculated filling factors (FFs) for a feature reflect the fraction of the solar disc covered by that feature, and the assignment of reference synthetic spectra. In this paper, the FFs, specified as a function of radial position on the solar disc, are computed for each image in a tabular form. The filling factor (FF) is an important parameter and is defined as the fraction of area in a pixel covered with the magnetic field, whereas the rest of the area in the pixel is field-free. However, this does not provide extensive information about the experiments conducted on tens or hundreds of such images. This is the first time that filling factors for SODISM images have been catalogued in tabular formation. This paper presents a new method that provides the means to detect sunspots on full-disk solar images recorded by the Solar Diameter Imager and Surface Mapper (SODISM) on the PICARD satellite. The method is a totally automated detection process that achieves a sunspot recognition rate of 97.6%. The number of sunspots detected by this method strongly agrees with the NOAA catalogue. The sunspot areas calculated by this method have a 99% correlation with SOHO over the same period, and thus help to calculate the filling factor for wavelength (W.L.) 607nm. |
| Tasks | |
| Published | 2019-04-01 |
| URL | http://arxiv.org/abs/1904.01133v1 |
| http://arxiv.org/pdf/1904.01133v1.pdf | |
| PWC | https://paperswithcode.com/paper/filling-factors-of-sunspots-in-sodism-images |
| Repo | |
| Framework | |
Liver Lesion Segmentation with slice-wise 2D Tiramisu and Tversky loss function
| Title | Liver Lesion Segmentation with slice-wise 2D Tiramisu and Tversky loss function |
| Authors | Karsten Roth, Tomasz Konopczyński, Jürgen Hesser |
| Abstract | At present, lesion segmentation is still performed manually (or semi-automatically) by medical experts. To facilitate this process, we contribute a fully-automatic lesion segmentation pipeline. This work proposes a method as a part of the LiTS (Liver Tumor Segmentation Challenge) competition for ISBI 17 and MICCAI 17 comparing methods for automatics egmentation of liver lesions in CT scans. By utilizing cascaded, densely connected 2D U-Nets and a Tversky-coefficient based loss function, our framework achieves very good shape extractions with high detection sensitivity, with competitive scores at time of publication. In addition, adjusting hyperparameters in our Tversky-loss allows to tune the network towards higher sensitivity or robustness. |
| Tasks | Lesion Segmentation |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03639v1 |
| https://arxiv.org/pdf/1905.03639v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503639 |
| Repo | |
| Framework | |
A Programmatic and Semantic Approach to Explaining and DebuggingNeural Network Based Object Detectors
| Title | A Programmatic and Semantic Approach to Explaining and DebuggingNeural Network Based Object Detectors |
| Authors | Edward Kim, Divya Gopinath, Corina Pasareanu, Sanjit Seshia |
| Abstract | Even as deep neural networks have become very effective for tasks in vision and perception, it remains difficult to explain and debug their behavior. In this paper, we present a programmatic and semantic approach to explaining, understanding, and debugging the correct and incorrect behaviors of a neural network based perception system. Our approach is semantic in that it employs a high-level representation of the distribution of environment scenarios that the detector is intended to work on. It is programmatic in that the representation is a program in a domain-specific probabilistic programming language using which synthetic data can be generated to train and test the neural network. We present a framework that assesses the performance of the neural network to identify correct and incorrect detections, extracts rules from those results that semantically characterizes the correct and incorrect scenarios, and then specializes the probabilistic program with those rules in order to more precisely characterize the scenarios in which the neural network operates correctly or not, without human intervention to identify important features. We demonstrate our results using the SCENIC probabilistic programming language and a neural network-based object detector. Our experiments show that it is possible to automatically generate compact rules that significantly increase the correct detection rate (or conversely the incorrect detection rate) of the network and can thus help with debugging and understanding its behavior. |
| Tasks | Probabilistic Programming |
| Published | 2019-12-01 |
| URL | https://arxiv.org/abs/1912.00289v1 |
| https://arxiv.org/pdf/1912.00289v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-programmatic-and-semantic-approach-to |
| Repo | |
| Framework | |
