Number Of Annotated Examples Research Articles

Active Gaze Labeling: Visualization for Trust Building.

Areas of interest (AOIs) are well-established means of providing semantic information for visualizing, analyzing, and classifying gaze data. However, the usual manual annotation of AOIs is time-consuming and further impaired by ambiguities in label assignments. To address these issues, we present an interactive labeling approach that combines visualization, machine learning, and user-centered explainable annotation. Our system provides uncertainty-aware visualization to build trust in classification with an increasing number of annotated examples. It combines specifically designed EyeFlower glyphs, dimensionality reduction, and selection and exploration techniques in an integrated workflow. The approach is versatile and hardware-agnostic, supporting video stimuli from stationary and unconstrained mobile eye tracking alike. We conducted an expert review to assess labeling strategies and trust building.

Human Posture Detection Using Image Augmentation and Hyperparameter-Optimized Transfer Learning Algorithms

With the advancement in pose estimation techniques, human posture detection recently received considerable attention in many applications, including ergonomics and healthcare. When using neural network models, overfitting and poor performance are prevalent issues. Recently, convolutional neural networks (CNNs) were successfully used for human posture recognition from human images due to their superior multiscale high-level visual representations over hand-engineering low-level characteristics. However, calculating millions of parameters in a deep CNN requires a significant number of annotated examples, which prohibits many deep CNNs such as AlexNet and VGG16 from being used on issues with minimal training data. We propose a new three-phase model for decision support that integrates CNN transfer learning, image data augmentation, and hyperparameter optimization (HPO) to address this problem. The model is used as part of a new decision support framework for the optimization of hyperparameters for AlexNet, VGG16, CNN, and multilayer perceptron (MLP) models for accomplishing optimal classification results. The AlexNet and VGG16 transfer learning algorithms with HPO are used for human posture detection, while CNN and Multilayer Perceptron (MLP) were used as standard classifiers for contrast. The HPO methods are essential for machine learning and deep learning algorithms because they directly influence the behaviors of training algorithms and have a major impact on the performance of machine learning and deep learning models. We used an image data augmentation technique to increase the number of images to be used for model training to reduce model overfitting and improve classification performance using the AlexNet, VGG16, CNN, and MLP models. The optimal combination of hyperparameters was found for the four models using a random-based search strategy. The MPII human posture datasets were used to test the proposed approach. The proposed models achieved an accuracy of 91.2% using AlexNet, 90.2% using VGG16, 87.5% using CNN, and 89.9% using MLP. The study is the first HPO study executed on the MPII human pose dataset.

Synthetic document generator for annotation-free layout recognition

Analyzing the layout of a document to identify headers, sections, tables, figures etc. is critical to understanding its content. Deep learning based approaches for detecting the layout structure of document images have been promising. However, these methods require a large number of annotated examples during training, which are both expensive and time consuming to obtain. We describe here a synthetic document generator that automatically produces realistic documents with labels for spatial positions, extents and categories of the layout elements. The proposed generative process treats every physical component of a document as a random variable and models their intrinsic dependencies using a Bayesian Network graph. Our hierarchical formulation using stochastic templates allow parameter sharing between documents for retaining broad themes and yet the distributional characteristics produces visually unique samples, thereby capturing complex and diverse layouts. We empirically illustrate that a deep layout detection model trained purely on the synthetic documents can match the performance of a model that uses real documents.

Natural language processing to facilitate breast cancer research and management.

The medical literature has been growing exponentially, and its size has become a barrier for physicians to locate and extract clinically useful information. As a promising solution, natural language processing (NLP), especially machine learning (ML)-based NLP is a technology that potentially provides a promising solution. ML-based NLP is based on training a computational algorithm with a large number of annotated examples to allow the computer to "learn" and "predict" the meaning of human language. Although NLP has been widely applied in industry and business, most physicians still are not aware of the huge potential of this technology in medicine, and the implementation of NLP in breast cancer research and management is fairly limited. With a real-world successful project of identifying penetrance papers for breast and other cancer susceptibility genes, this review illustrates how to train and evaluate an NLP-based medical abstract classifier, incorporate it into a semiautomatic meta-analysis procedure, and validate the effectiveness of this procedure. Other implementations of NLP technology in breast cancer research, such as parsing pathology reports and mining electronic healthcare records, are also discussed. We hope this review will help breast cancer physicians and researchers to recognize, understand, and apply this technology to meet their own clinical or research needs.

A multi-scale data fusion framework for bone age assessment with convolutional neural networks

Bone age assessment (BAA) has various clinical applications such as diagnosis of endocrine disorders and prediction of final adult height for adolescents. Recent studies indicate that deep learning techniques have great potential in developing automated BAA methods with significant advantages over the conventional methods based on handcrafted features. In this paper, we propose a multi-scale data fusion framework for bone age assessment with X-ray images based on non-subsampled contourlet transform (NSCT) and convolutional neural networks (CNNs). Unlike the existing CNN-based BAA methods that adopt the original spatial domain image as network input directly, we pre-extract a rich set of features for the input image by performing NSCT to obtain its multi-scale and multi-direction representations. This feature pre-extraction strategy could be beneficial to network training as the number of annotated examples in the problem of BAA is typically quite limited. The obtained NSCT coefficient maps at each scale are fed into a convolutional network individually and the information from different scales are then merged to achieve the final prediction. Specifically, two CNN models with different data fusion strategies are presented for BAA: a regression model with feature-level fusion and a classification model with decision-level fusion. Experiments on the public BAA dataset Digital Hand Atlas demonstrate that the proposed method can obtain promising results and outperform many state-of-the-art BAA methods. In particular, the proposed approaches exhibit obvious advantages over the corresponding spatial domain approaches (generally with an improvement of more than 0.1 years on the mean absolute error), showing great potential in the future study of this field.

Acquiring Word-Meaning Mappings for Natural Language Interfaces

This paper focuses on a system, WOLFIE (WOrd Learning From Interpreted Examples), that acquires a semantic lexicon from a corpus of sentences paired with semantic representations. The lexicon learned consists of phrases paired with meaning representations. WOLFIE is part of an integrated system that learns to transform sentences into representations such as logical database queries. Experimental results are presented demonstrating WOLFIE's ability to learn useful lexicons for a database interface in four different natural languages. The usefulness of the lexicons learned by WOLFIE are compared to those acquired by a similar system, with results favorable to WOLFIE. A second set of experiments demonstrates WOLFIE's ability to scale to larger and more difficult, albeit artificially generated, corpora. In natural language acquisition, it is difficult to gather the annotated data needed for supervised learning; however, unannotated data is fairly plentiful. Active learning methods attempt to select for annotation and training only the most informative examples, and therefore are potentially very useful in natural language applications. However, most results to date for active learning have only considered standard classification tasks. To reduce annotation effort while maintaining accuracy, we apply active learning to semantic lexicons. We show that active learning can significantly reduce the number of annotated examples required to achieve a given level of performance.