Active learning stands for methods which increase classification quality by means of user feedback. An important subcategory is active learning for one-class classifiers, i.e., for imbalanced class distributions. While various methods in this category exist, selecting one for a given application scenario is difficult. This is because existing methods rely on different assumptions, have different objectives, and often are tailored to a specific use case. All this calls for a comprehensive comparison, the topic of this article. This article starts with a categorization of the various methods. We then propose ways to evaluate active learning results. Next, we run extensive experiments to compare existing methods, for a broad variety of scenarios. One result is that the practicality and the performance of an active learning method strongly depend on its category and on the assumptions behind it. Another observation is that there only is a small subset of our experiments where existing approaches outperform random baselines. Finally, we show that a well-laid-out categorization and a rigorous specification of assumptions can facilitate the selection of a good method for one-class classification.
Applying deep learning methods to mammography assessment has remained a challenging topic. Dense noise with sparse expressions, mega-pixel raw data resolution, lack of diverse examples have all been factors affecting performance. The lack of pixel-level ground truths have especially limited segmentation methods in pushing beyond approximately bounding regions. We propose a classification approach grounded in high performance tissue assessment as an alternative to all-in-one localization and assessment models that is also capable of pinpointing the causal pixels. First, the objective of the mammography assessment task is formalized in the context of local tissue classifiers. Then, the accuracy of a convolutional neural net is evaluated on classifying patches of tissue with suspicious findings at varying scales, where highest obtained AUC is above $0.9$. The local evaluations of one such expert tissue classifier is used to augment the results of a heatmap regression model and additionally recover the exact causal regions at high resolution as a saliency image suitable for clinical settings.
Automatically learned quality assessment for images has recently become a hot topic due to its usefulness in a wide variety of applications such as evaluating image capture pipelines, storage techniques and sharing media. Despite the subjective nature of this problem, most existing methods only predict the mean opinion score provided by datasets such as AVA [1] and TID2013 [2]. Our approach differs from others in that we predict the distribution of human opinion scores using a convolutional neural network. Our architecture also has the advantage of being significantly simpler than other methods with comparable performance. Our proposed approach relies on the success (and retraining) of proven, state-of-the-art deep object recognition networks. Our resulting network can be used to not only score images reliably and with high correlation to human perception, but also to assist with adaptation and optimization of photo editing/enhancement algorithms in a photographic pipeline. All this is done without need for a "golden" reference image, consequently allowing for single-image, semantic- and perceptually-aware, no-reference quality assessment.
Estimating the uncertainty in image registration is an area of current research that is aimed at providing information that will enable surgeons to assess the operative risk based on registered image data and the estimated registration uncertainty. If they receive inaccurately calculated registration uncertainty and misplace confidence in the alignment solutions, severe consequences may result. For probabilistic image registration (PIR), most research quantifies the registration uncertainty using summary statistics of the transformation distributions. In this paper, we study a rarely examined topic: whether those summary statistics of the transformation distribution truly represent the registration uncertainty. Using concrete examples, we show that there are two types of uncertainties: the transformation uncertainty, Ut, and label uncertainty Ul. Ut indicates the doubt concerning transformation parameters and can be estimated by conventional uncertainty measures, while Ul is strongly linked to the goal of registration. Further, we show that using Ut to quantify Ul is inappropriate and can be misleading. In addition, we present some potentially critical findings regarding PIR.
This paper describes two systems that were used by the authors for addressing Arabic Sentiment Analysis as part of SemEval-2017, task 4. The authors participated in three Arabic related subtasks which are: Subtask A (Message Polarity Classification), Sub-task B (Topic-Based Message Polarity classification) and Subtask D (Tweet quantification) using the team name of NileTMRG. For subtask A, we made use of our previously developed sentiment analyzer which we augmented with a scored lexicon. For subtasks B and D, we used an ensemble of three different classifiers. The first classifier was a convolutional neural network for which we trained (word2vec) word embeddings. The second classifier consisted of a MultiLayer Perceptron, while the third classifier was a Logistic regression model that takes the same input as the second classifier. Voting between the three classifiers was used to determine the final outcome. The output from task B, was quantified to produce the results for task D. In all three Arabic related tasks in which NileTMRG participated, the team ranked at number one.
Digital retouching of face images is becoming more widespread due to the introduction of software packages that automate the task. Several researchers have introduced algorithms to detect whether a face image is original or retouched. However, previous work on this topic has not considered whether or how accuracy of retouching detection varies with the demography of face images. In this paper, we introduce a new Multi-Demographic Retouched Faces (MDRF) dataset, which contains images belonging to two genders, male and female, and three ethnicities, Indian, Chinese, and Caucasian. Further, retouched images are created using two different retouching software packages. The second major contribution of this research is a novel semi-supervised autoencoder incorporating "subclass" information to improve classification. The proposed approach outperforms existing state-of-the-art detection algorithms for the task of generalized retouching detection. Experiments conducted with multiple combinations of ethnicities show that accuracy of retouching detection can vary greatly based on the demographics of the training and testing images.
Symbolic regression is an important but challenging research topic in data mining. It can detect the underlying mathematical models. Genetic programming (GP) is one of the most popular methods for symbolic regression. However, its convergence speed might be too slow for large scale problems with a large number of variables. This drawback has become a bottleneck in practical applications. In this paper, a new non-evolutionary real-time algorithm for symbolic regression, Elite Bases Regression (EBR), is proposed. EBR generates a set of candidate basis functions coded with parse-matrix in specific mapping rules. Meanwhile, a certain number of elite bases are preserved and updated iteratively according to the correlation coefficients with respect to the target model. The regression model is then spanned by the elite bases. A comparative study between EBR and a recent proposed machine learning method for symbolic regression, Fast Function eXtraction (FFX), are conducted. Numerical results indicate that EBR can solve symbolic regression problems more effectively.
Conversational speech recognition has served as a flagship speech recognition task since the release of the Switchboard corpus in the 1990s. In this paper, we measure the human error rate on the widely used NIST 2000 test set, and find that our latest automated system has reached human parity. The error rate of professional transcribers is 5.9% for the Switchboard portion of the data, in which newly acquainted pairs of people discuss an assigned topic, and 11.3% for the CallHome portion where friends and family members have open-ended conversations. In both cases, our automated system establishes a new state of the art, and edges past the human benchmark, achieving error rates of 5.8% and 11.0%, respectively. The key to our system's performance is the use of various convolutional and LSTM acoustic model architectures, combined with a novel spatial smoothing method and lattice-free MMI acoustic training, multiple recurrent neural network language modeling approaches, and a systematic use of system combination.
Image instance retrieval is the problem of retrieving images from a database which contain the same object. Convolutional Neural Network (CNN) based descriptors are becoming the dominant approach for generating {\it global image descriptors} for the instance retrieval problem. One major drawback of CNN-based {\it global descriptors} is that uncompressed deep neural network models require hundreds of megabytes of storage making them inconvenient to deploy in mobile applications or in custom hardware. In this work, we study the problem of neural network model compression focusing on the image instance retrieval task. We study quantization, coding, pruning and weight sharing techniques for reducing model size for the instance retrieval problem. We provide extensive experimental results on the trade-off between retrieval performance and model size for different types of networks on several data sets providing the most comprehensive study on this topic. We compress models to the order of a few MBs: two orders of magnitude smaller than the uncompressed models while achieving negligible loss in retrieval performance.
This article describes a data driven method for deriving the relationship between personality and media preferences. A qunatifiable representation of such a relationship can be leveraged for use in recommendation systems and ameliorate the "cold start" problem. Here, the data is comprised of an original collection of 1,316 Okcupid dating profiles. Of these profiles, 800 are labeled with one of 16 possible Myers-Briggs Type Indicators (MBTI). A personality specific topic model describing a person's favorite books, movies, shows, music, and food was generated using latent Dirichlet allocation (LDA). There were several significant findings, for example, intuitive thinking types preferred sci-fi/fantasy entertainment, extraversion correlated positively with upbeat dance music, and jazz, folk, and international cuisine correlated positively with those characterized by openness to experience. Many other correlations confirmed previous findings describing the relationship among personality, writing style, and personal preferences. (For complete word/personality type assocations see the Appendix).
Add to Chrome
Add to Firefox