Paper Group ANR 577
Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps. Corresponding Supine and Prone Colon Visualization Using Eigenfunction Analysis and Fold Modeling. Geared Rotationally Identical and Invariant Convolutional Neural Network Systems. Data Driven Chiller Plant Energy Optimization with Domain Knowledge. A Theo …
Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps
| Title | Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps |
| Authors | Pingping Zhang, Wei Liu, Dong Wang, Yinjie Lei, Hongyu Wang, Chunhua Shen, Huchuan Lu |
| Abstract | In this paper, we propose a novel effective non-rigid object tracking framework based on the spatial-temporal consistent saliency detection. In contrast to most existing trackers that utilize a bounding box to specify the tracked target, the proposed framework can extract accurate regions of the target as tracking outputs. It achieves a better description of the non-rigid objects and reduces the background pollution for the tracking model. Furthermore, our model has several unique features. First, a tailored fully convolutional neural network (TFCN) is developed to model the local saliency prior for a given image region, which not only provides the pixel-wise outputs but also integrates the semantic information. Second, a novel multi-scale multi-region mechanism is proposed to generate local saliency maps that effectively consider visual perceptions with different spatial layouts and scale variations. Subsequently, local saliency maps are fused via a weighted entropy method, resulting in a final discriminative saliency map. Finally, we present a non-rigid object tracking algorithm based on the predicted saliency maps. By utilizing a spatial-temporal consistent saliency map (STCSM), we conduct target-background classification and use a simple fine-tuning scheme for online updating. Extensive experiments demonstrate that the proposed algorithm achieves competitive performance in both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets. |
| Tasks | Object Tracking, Saliency Detection, Visual Tracking |
| Published | 2018-02-22 |
| URL | http://arxiv.org/abs/1802.07957v2 |
| http://arxiv.org/pdf/1802.07957v2.pdf | |
| PWC | https://paperswithcode.com/paper/non-rigid-object-tracking-via-deep-multi |
| Repo | |
| Framework | |
Corresponding Supine and Prone Colon Visualization Using Eigenfunction Analysis and Fold Modeling
| Title | Corresponding Supine and Prone Colon Visualization Using Eigenfunction Analysis and Fold Modeling |
| Authors | Saad Nadeem, Joseph Marino, Xianfeng Gu, Arie Kaufman |
| Abstract | We present a method for registration and visualization of corresponding supine and prone virtual colonoscopy scans based on eigenfunction analysis and fold modeling. In virtual colonoscopy, CT scans are acquired with the patient in two positions, and their registration is desirable so that physicians can corroborate findings between scans. Our algorithm performs this registration efficiently through the use of Fiedler vector representation (the second eigenfunction of the Laplace-Beltrami operator). This representation is employed to first perform global registration of the two colon positions. The registration is then locally refined using the haustral folds, which are automatically segmented using the 3D level sets of the Fiedler vector. The use of Fiedler vectors and the segmented folds presents a precise way of visualizing corresponding regions across datasets and visual modalities. We present multiple methods of visualizing the results, including 2D flattened rendering and the corresponding 3D endoluminal views. The precise fold modeling is used to automatically find a suitable cut for the 2D flattening, which provides a less distorted visualization. Our approach is robust, and we demonstrate its efficiency and efficacy by showing matched views on both the 2D flattened colons and in the 3D endoluminal view. We analytically evaluate the results by measuring the distance between features on the registered colons, and we also assess our fold segmentation against 20 manually labeled datasets. We have compared our results analytically to previous methods, and have found our method to achieve superior results. We also prove the hot spots conjecture for modeling cylindrical topology using Fiedler vector representation, which allows our approach to be used for general cylindrical geometry modeling and feature extraction. |
| Tasks | |
| Published | 2018-10-20 |
| URL | http://arxiv.org/abs/1810.08850v1 |
| http://arxiv.org/pdf/1810.08850v1.pdf | |
| PWC | https://paperswithcode.com/paper/corresponding-supine-and-prone-colon |
| Repo | |
| Framework | |
Geared Rotationally Identical and Invariant Convolutional Neural Network Systems
| Title | Geared Rotationally Identical and Invariant Convolutional Neural Network Systems |
| Authors | ShihChung B. Lo, Ph. D., Matthew T. Freedman, M. D., Seong K. Mun, Ph. D., Heang-Ping Chan, Ph. D |
| Abstract | Theorems and techniques to form different types of transformationally invariant processing and to produce the same output quantitatively based on either transformationally invariant operators or symmetric operations have recently been introduced by the authors. In this study, we further propose to compose a geared rotationally identical CNN system (GRI-CNN) with a small step angle by connecting networks of participated processes at the first flatten layer. Using an ordinary CNN structure as a base, requirements for constructing a GRI-CNN include the use of either symmetric input vector or kernels with an angle increment that can form a complete cycle as a “gearwheel”. Four basic GRI-CNN structures were studied. Each of them can produce quantitatively identical output results when a rotation angle of the input vector is evenly divisible by the step angle of the gear. Our study showed when an input vector rotated with an angle does not match to a step angle, the GRI-CNN can also produce a highly consistent result. With a design of using an ultra-fine gear-tooth step angle (e.g., 1 degree or 0.1 degree), all four GRI-CNN systems can be constructed virtually isotropically. |
| Tasks | |
| Published | 2018-08-03 |
| URL | http://arxiv.org/abs/1808.01280v3 |
| http://arxiv.org/pdf/1808.01280v3.pdf | |
| PWC | https://paperswithcode.com/paper/geared-rotationally-identical-and-invariant |
| Repo | |
| Framework | |
Data Driven Chiller Plant Energy Optimization with Domain Knowledge
| Title | Data Driven Chiller Plant Energy Optimization with Domain Knowledge |
| Authors | Hoang Dung Vu, Kok Soon Chai, Bryan Keating, Nurislam Tursynbek, Boyan Xu, Kaige Yang, Xiaoyan Yang, Zhenjie Zhang |
| Abstract | Refrigeration and chiller optimization is an important and well studied topic in mechanical engineering, mostly taking advantage of physical models, designed on top of over-simplified assumptions, over the equipments. Conventional optimization techniques using physical models make decisions of online parameter tuning, based on very limited information of hardware specifications and external conditions, e.g., outdoor weather. In recent years, new generation of sensors is becoming essential part of new chiller plants, for the first time allowing the system administrators to continuously monitor the running status of all equipments in a timely and accurate way. The explosive growth of data flowing to databases, driven by the increasing analytical power by machine learning and data mining, unveils new possibilities of data-driven approaches for real-time chiller plant optimization. This paper presents our research and industrial experience on the adoption of data models and optimizations on chiller plant and discusses the lessons learnt from our practice on real world plants. Instead of employing complex machine learning models, we emphasize the incorporation of appropriate domain knowledge into data analysis tools, which turns out to be the key performance improver over state-of-the-art deep learning techniques by a significant margin. Our empirical evaluation on a real world chiller plant achieves savings by more than 7% on daily power consumption. |
| Tasks | |
| Published | 2018-12-03 |
| URL | http://arxiv.org/abs/1812.00679v1 |
| http://arxiv.org/pdf/1812.00679v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-driven-chiller-plant-energy-optimization |
| Repo | |
| Framework | |
A Theory of Diagnostic Interpretation in Supervised Classification
| Title | A Theory of Diagnostic Interpretation in Supervised Classification |
| Authors | Anirban Mukhopadhyay |
| Abstract | Interpretable deep learning is a fundamental building block towards safer AI, especially when the deployment possibilities of deep learning-based computer-aided medical diagnostic systems are so eminent. However, without a computational formulation of black-box interpretation, general interpretability research rely heavily on subjective bias. Clear decision structure of the medical diagnostics lets us approximate the decision process of a radiologist as a model - removed from subjective bias. We define the process of interpretation as a finite communication between a known model and a black-box model to optimally map the black box’s decision process in the known model. Consequently, we define interpretability as maximal information gain over the initial uncertainty about the black-box’s decision within finite communication. We relax this definition based on the observation that diagnostic interpretation is typically achieved by a process of minimal querying. We derive an algorithm to calculate diagnostic interpretability. The usual question of accuracy-interpretability tradeoff, i.e. whether a black-box model’s prediction accuracy is dependent on its ability to be interpreted by a known source model, does not arise in this theory. With multiple example simulation experiments of various complexity levels, we demonstrate the working of such a theoretical model in synthetic supervised classification scenarios. |
| Tasks | |
| Published | 2018-06-26 |
| URL | http://arxiv.org/abs/1806.10080v1 |
| http://arxiv.org/pdf/1806.10080v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-theory-of-diagnostic-interpretation-in |
| Repo | |
| Framework | |
Automatic Detection of Vague Words and Sentences in Privacy Policies
| Title | Automatic Detection of Vague Words and Sentences in Privacy Policies |
| Authors | Logan Lebanoff, Fei Liu |
| Abstract | Website privacy policies represent the single most important source of information for users to gauge how their personal data are collected, used and shared by companies. However, privacy policies are often vague and people struggle to understand the content. Their opaqueness poses a significant challenge to both users and policy regulators. In this paper, we seek to identify vague content in privacy policies. We construct the first corpus of human-annotated vague words and sentences and present empirical studies on automatic vagueness detection. In particular, we investigate context-aware and context-agnostic models for predicting vague words, and explore auxiliary-classifier generative adversarial networks for characterizing sentence vagueness. Our experimental results demonstrate the effectiveness of proposed approaches. Finally, we provide suggestions for resolving vagueness and improving the usability of privacy policies. |
| Tasks | |
| Published | 2018-08-19 |
| URL | http://arxiv.org/abs/1808.06219v2 |
| http://arxiv.org/pdf/1808.06219v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-detection-of-vague-words-and |
| Repo | |
| Framework | |
CellLineNet: End-to-End Learning and Transfer Learning For Multiclass Epithelial Breast cell Line Classification via a Convolutional Neural Network
| Title | CellLineNet: End-to-End Learning and Transfer Learning For Multiclass Epithelial Breast cell Line Classification via a Convolutional Neural Network |
| Authors | Darlington Ahiale Akogo, Vincent Appiah, Xavier-Lewis Palmer |
| Abstract | Computer Vision for Analyzing and Classifying cells and tissues often require rigorous lab procedures and so automated Computer Vision solutions have been sought. Most work in such field usually requires Feature Extractions before the analysis of such features via Machine Learning and Machine Vision algorithms. We developed a Convolutional Neural Network that classifies 5 types of epithelial breast cell lines comprised of two human cancer lines, 2 normal immortalized lines, and 1 immortalized mouse line (MDA-MB-468, MCF7, 10A, 12A and HC11) without requiring feature extraction. The Multiclass Cell Line Classification Convolutional Neural Network extends our earlier work on a Binary Breast Cancer Cell Line Classification model. CellLineNet is 31-layer Convolutional Neural Network trained, validated and tested on a 3,252 image dataset of 5 types of Epithelial Breast cell Lines (MDA-MB-468, MCF7, 10A, 12A and HC11) in an end-to-end fashion. End-to-End Learning enables CellLineNet to identify and learn on its own, visual features and regularities most important to Breast Cancer Cell Line Classification from the dataset of images. Using Transfer Learning, the 28-layer MobileNet Convolutional Neural Network architecture with pre-trained ImageNet weights is extended and fine tuned to the Multiclass Epithelial Breast cell Line Classification problem. CellLineNet simply requires an imaged Cell Line as input and it outputs the type of breast epithelial cell line (MDA-MB-468, MCF7, 10A, 12A or HC11) as predicted probabilities for the 5 classes. CellLineNet scored a 96.67% Accuracy. |
| Tasks | Transfer Learning |
| Published | 2018-08-18 |
| URL | http://arxiv.org/abs/1808.06041v1 |
| http://arxiv.org/pdf/1808.06041v1.pdf | |
| PWC | https://paperswithcode.com/paper/celllinenet-end-to-end-learning-and-transfer |
| Repo | |
| Framework | |
A real-time reactive framework for the surgical case sequencing problem
| Title | A real-time reactive framework for the surgical case sequencing problem |
| Authors | Belinda Spratt, Erhan Kozan |
| Abstract | In this paper, we address the multiple operating room (OR) surgical case sequencing problem (SCSP). The objective is to maximise total OR utilisation during standard opening hours. This work uses a case study of a large Australian public hospital with long surgical waiting lists and high levels of non-elective demand. Due to the complexity of the SCSP and the size of the instances considered herein, heuristic techniques are required to solve the problem. We present constructive heuristics based on both a modified block scheduling policy and an open scheduling policy. A number of real-time reactive strategies are presented that can be used to maintain schedule feasibility in the case of disruptions. Results of computational experiments show that this approach maintains schedule feasibility in real-time, whilst increasing operating theatre (OT) utilisation and throughput, and reducing the waiting time of non-elective patients. The framework presented here is applicable to the real-life scheduling of OT departments, and we provide recommendations regarding implementation of the approach. |
| Tasks | |
| Published | 2018-08-30 |
| URL | https://arxiv.org/abs/1808.10133v3 |
| https://arxiv.org/pdf/1808.10133v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-real-time-reactive-framework-for-the |
| Repo | |
| Framework | |
Learning Sparse Neural Networks via Sensitivity-Driven Regularization
| Title | Learning Sparse Neural Networks via Sensitivity-Driven Regularization |
| Authors | Enzo Tartaglione, Skjalg Lepsøy, Attilio Fiandrotti, Gianluca Francini |
| Abstract | The ever-increasing number of parameters in deep neural networks poses challenges for memory-limited applications. Regularize-and-prune methods aim at meeting these challenges by sparsifying the network weights. In this context we quantify the output sensitivity to the parameters (i.e. their relevance to the network output) and introduce a regularization term that gradually lowers the absolute value of parameters with low sensitivity. Thus, a very large fraction of the parameters approach zero and are eventually set to zero by simple thresholding. Our method surpasses most of the recent techniques both in terms of sparsity and error rates. In some cases, the method reaches twice the sparsity obtained by other techniques at equal error rates. |
| Tasks | |
| Published | 2018-10-28 |
| URL | http://arxiv.org/abs/1810.11764v1 |
| http://arxiv.org/pdf/1810.11764v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-sparse-neural-networks-via |
| Repo | |
| Framework | |
Integration of Absolute Orientation Measurements in the KinectFusion Reconstruction pipeline
| Title | Integration of Absolute Orientation Measurements in the KinectFusion Reconstruction pipeline |
| Authors | Silvio Giancola, Jens Schneider, Peter Wonka, Bernard S. Ghanem |
| Abstract | In this paper, we show how absolute orientation measurements provided by low-cost but high-fidelity IMU sensors can be integrated into the KinectFusion pipeline. We show that integration improves both runtime, robustness and quality of the 3D reconstruction. In particular, we use this orientation data to seed and regularize the ICP registration technique. We also present a technique to filter the pairs of 3D matched points based on the distribution of their distances. This filter is implemented efficiently on the GPU. Estimating the distribution of the distances helps control the number of iterations necessary for the convergence of the ICP algorithm. Finally, we show experimental results that highlight improvements in robustness, a speed-up of almost 12%, and a gain in tracking quality of 53% for the ATE metric on the Freiburg benchmark. |
| Tasks | 3D Reconstruction |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.03980v2 |
| http://arxiv.org/pdf/1802.03980v2.pdf | |
| PWC | https://paperswithcode.com/paper/integration-of-absolute-orientation |
| Repo | |
| Framework | |
Demand-Weighted Completeness Prediction for a Knowledge Base
| Title | Demand-Weighted Completeness Prediction for a Knowledge Base |
| Authors | Andrew Hopkinson, Amit Gurdasani, Dave Palfrey, Arpit Mittal |
| Abstract | In this paper we introduce the notion of Demand-Weighted Completeness, allowing estimation of the completeness of a knowledge base with respect to how it is used. Defining an entity by its classes, we employ usage data to predict the distribution over relations for that entity. For example, instances of person in a knowledge base may require a birth date, name and nationality to be considered complete. These predicted relation distributions enable detection of important gaps in the knowledge base, and define the required facts for unseen entities. Such characterisation of the knowledge base can also quantify how usage and completeness change over time. We demonstrate a method to measure Demand-Weighted Completeness, and show that a simple neural network model performs well at this prediction task. |
| Tasks | |
| Published | 2018-04-30 |
| URL | http://arxiv.org/abs/1804.11109v1 |
| http://arxiv.org/pdf/1804.11109v1.pdf | |
| PWC | https://paperswithcode.com/paper/demand-weighted-completeness-prediction-for-a |
| Repo | |
| Framework | |
A Kernel Theory of Modern Data Augmentation
| Title | A Kernel Theory of Modern Data Augmentation |
| Authors | Tri Dao, Albert Gu, Alexander J. Ratner, Virginia Smith, Christopher De Sa, Christopher Ré |
| Abstract | Data augmentation, a technique in which a training set is expanded with class-preserving transformations, is ubiquitous in modern machine learning pipelines. In this paper, we seek to establish a theoretical framework for understanding data augmentation. We approach this from two directions: First, we provide a general model of augmentation as a Markov process, and show that kernels appear naturally with respect to this model, even when we do not employ kernel classification. Next, we analyze more directly the effect of augmentation on kernel classifiers, showing that data augmentation can be approximated by first-order feature averaging and second-order variance regularization components. These frameworks both serve to illustrate the ways in which data augmentation affects the downstream learning model, and the resulting analyses provide novel connections between prior work in invariant kernels, tangent propagation, and robust optimization. Finally, we provide several proof-of-concept applications showing that our theory can be useful for accelerating machine learning workflows, such as reducing the amount of computation needed to train using augmented data, and predicting the utility of a transformation prior to training. |
| Tasks | Data Augmentation |
| Published | 2018-03-16 |
| URL | http://arxiv.org/abs/1803.06084v2 |
| http://arxiv.org/pdf/1803.06084v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-kernel-theory-of-modern-data-augmentation |
| Repo | |
| Framework | |
Prosodic entrainment in dialog acts
| Title | Prosodic entrainment in dialog acts |
| Authors | Uwe D. Reichel, Katalin Mády, Jennifer Cole |
| Abstract | We examined prosodic entrainment in spoken dialogs separately for several dialog acts in cooperative and competitive games. Entrainment was measured for intonation features derived from a superpositional intonation stylization as well as for rhythm features. The found differences can be related to the cooperative or competitive nature of the game, as well as to dialog act properties as its intrinsic authority, supportiveness and distributional characteristics. In cooperative games dialog acts with a high authority given by knowledge and with a high frequency showed the most entrainment. The results are discussed amongst others with respect to the degree of active entrainment control in cooperative behavior. |
| Tasks | |
| Published | 2018-10-30 |
| URL | http://arxiv.org/abs/1810.12646v1 |
| http://arxiv.org/pdf/1810.12646v1.pdf | |
| PWC | https://paperswithcode.com/paper/prosodic-entrainment-in-dialog-acts |
| Repo | |
| Framework | |
Looking at the Driver/Rider in Autonomous Vehicles to Predict Take-Over Readiness
| Title | Looking at the Driver/Rider in Autonomous Vehicles to Predict Take-Over Readiness |
| Authors | Nachiket Deo, Mohan M. Trivedi |
| Abstract | Continuous estimation the driver’s take-over readiness is critical for safe and timely transfer of control during the failure modes of autonomous vehicles. In this paper, we propose a data-driven approach for estimating the driver’s take-over readiness based purely on observable cues from in-vehicle vision sensors. We present an extensive naturalistic drive dataset of drivers in a conditionally autonomous vehicle running on Californian freeways. We collect subjective ratings for the driver’s take-over readiness from multiple human observers viewing the sensor feed. Analysis of the ratings in terms of intra-class correlation coefficients (ICCs) shows a high degree of consistency in the ratings across raters. We define a metric for the driver’s take-over readiness termed the ‘Observable Readiness Index (ORI)’ based on the ratings. Finally, we propose an LSTM model for continuous estimation of the driver’s ORI based on a holistic representation of the driver’s state, capturing gaze, hand, pose and foot activity. Our model estimates the ORI with a mean absolute error of 0.449 on a 5 point scale. |
| Tasks | Autonomous Vehicles |
| Published | 2018-11-14 |
| URL | http://arxiv.org/abs/1811.06047v1 |
| http://arxiv.org/pdf/1811.06047v1.pdf | |
| PWC | https://paperswithcode.com/paper/looking-at-the-driverrider-in-autonomous |
| Repo | |
| Framework | |
Cooperative Group Optimization with Ants (CGO-AS): Leverage Optimization with Mixed Individual and Social Learning
| Title | Cooperative Group Optimization with Ants (CGO-AS): Leverage Optimization with Mixed Individual and Social Learning |
| Authors | Xiao-Feng Xie, Zun-Jing Wang |
| Abstract | We present CGO-AS, a generalized Ant System (AS) implemented in the framework of Cooperative Group Optimization (CGO), to show the leveraged optimization with a mixed individual and social learning. Ant colony is a simple yet efficient natural system for understanding the effects of primary intelligence on optimization. However, existing AS algorithms are mostly focusing on their capability of using social heuristic cues while ignoring their individual learning. CGO can integrate the advantages of a cooperative group and a low-level algorithm portfolio design, and the agents of CGO can explore both individual and social search. In CGO-AS, each ant (agent) is added with an individual memory, and is implemented with a novel search strategy to use individual and social cues in a controlled proportion. The presented CGO-AS is therefore especially useful in exposing the power of the mixed individual and social learning for improving optimization. The optimization performance is tested with instances of the Traveling Salesman Problem (TSP). The results prove that a cooperative ant group using both individual and social learning obtains a better performance than the systems solely using either individual or social learning. The best performance is achieved under the condition when agents use individual memory as their primary information source, and simultaneously use social memory as their searching guidance. In comparison with existing AS systems, CGO-AS retains a faster learning speed toward those higher-quality solutions, especially in the later learning cycles. The leverage in optimization by CGO-AS is highly possible due to its inherent feature of adaptively maintaining the population diversity in the individual memory of agents, and of accelerating the learning process with accumulated knowledge in the social memory. |
| Tasks | |
| Published | 2018-08-01 |
| URL | http://arxiv.org/abs/1808.00524v1 |
| http://arxiv.org/pdf/1808.00524v1.pdf | |
| PWC | https://paperswithcode.com/paper/cooperative-group-optimization-with-ants-cgo |
| Repo | |
| Framework | |
