Zero-Shot Deep Domain Adaptation With Common Representation Learning.

Domain Adaptation aims at adapting the knowledge learned from a domain (source-domain) to another (target-domain). Existing approaches typically require a portion of task-relevant target-domain data a priori. We propose an approach, zero-shot deep domain adaptation (ZDDA), which uses paired dual-domain task-irrelevant data to eliminate the need for task-relevant target-domain training data. ZDDA learns to generate common representations for source and target domains data. Then, either domain representation is used later to train a system that works on both domains or having the ability to eliminate the need to either domain in sensor fusion settings. Two variants of ZDDA have been developed: ZDDA for classification task (ZDDA-C) and ZDDA for metric learning task (ZDDA-ML). Another limitation in Existing approaches is that most of them are designed for the closed-set classification task, i.e., the sets of classes in both the source and target domains are "known." However, ZDDA-C is also applicable to the open-set classification task where not all classes are "known" during training. Moreover, the effectiveness of ZDDA-ML shows ZDDA's applicability is not limited to classification tasks. ZDDA-C and ZDDA-ML are tested on classification and metric-learning tasks, respectively. Under most experimental conditions, ZDDA outperforms the baseline without using task-relevant target-domain-training data.

Inlier Clustering based on the Residuals of Random Hypotheses.

We present an approach for motion clustering based on a novel observation that a signature for putative pixel correspondences can be generated by collecting their residuals with respect to model hypotheses drawn randomly from the data. Inliers of the same motion cluster should have strongly correlated residuals, which are low when a hypothesis is consistent with the data in the cluster and high otherwise. After evaluating a number of hypotheses, members of the same cluster can be identified based on these correlations. Due to this property, we named our approach Inlier Clustering based on the Residuals of Random Hypotheses (ICR). An important advantage of ICR is that it does not require an inlier-outlier threshold or parameter tuning. In addition, we propose a supervised recursive formulation of ICR (r-ICR) that, unlike many motion clustering methods, does not require the number of clusters to be known a priori, as long as annotated data are available for training. We validate ICR and r-ICR on several publicly available datasets for robust geometric model fitting.

Lifestyle Intervention for Cardiovascular Disease Risk Factors in Jeddah, Saudi Arabia.

Background Cardiovascular disease (CVD) remains the major cause of global mortality. Applying a comprehensive interventional program may reduce the incidence of cardiovascular disease and its complications. Objective This study compared the effects of a three-month intervention involving lifestyle modification and physical activity with standard care in women ≥30 years having a moderate to high risk of CVD, with respect to improving physical activity and cardiovascular disease risk factors at the National Guard Residential City in Jeddah, Saudi Arabia, in 2015. Methods The effects of this community-based lifestyle program were assessed through a randomized controlled trial from January 1st to September 6th, 2015. Women in the intervention group (n = 31) received health education, exercise training, and diet counselling as individuals and in groups according to the participant's risk. Women in the control group (n = 28) received one health education session at the screening site. The primary outcome was the proportion of women with moderate Framingham risk scores (FRS) reducing their risk by 10% and the proportion of women with high FRS reducing their risk by 25%. The secondary outcome was the proportion of women reducing their risk by ≥1 risk category. Results The mean participant age was 42 ± 8 years. At three-month's follow-up, reductions were greater in the intervention group and the difference between groups was statistically significant (p < 0.05). Lifestyle intervention program significantly reduced systolic blood pressure (-9.2 mmHg), blood glucose (-45 mg/dL) and Framingham risk score (-13.6). Linear regression analysis revealed a significant improvement in the Framingham risk score (p < 0.01). Conclusion In a population of women with moderate-to-high risk of CVD, a personalized lifestyle modification program showed positive association in improving the 10-year cardiovascular Framingham risk score after three months.