Numerous large vision models for natural images, such as SAM, Florence-2, and GPT-4, have achieved state-of-the-art (SOTA) performance, largely due to vast amounts of image and text data available online. Smaller models like EfficientSAM and CLIP have also shown the potential of achieving significant results with comparatively less data. However, real-world scientific problems, particularly in remote sensing, present unique challenges due to the complexity of the data and scarcity of annotations. These problems often require data from multiple sources, such as hyperspectral sensors on airplanes and multispectral sensors on satellites, which are expensive and time-consuming to acquire.This dissertation addresses the key question: how can large vision models be built and trained effectively under data constraints? The proposed solution involves integrating domain-specific knowledge into large vision models, specifically vision transformers, to optimize their performance and training efficiency. By incorporating core signal processing techniques, domain-specific knowledge is encoded as prior information, guiding the feature extraction process and refining randomly initialized queries via a query refiner module. This approach accelerates convergence with limited training data. Three key applications are explored: (1) methane detection in remote sensing from aerial imagery, (2) animal detection and classification in large grasslands for ecological studies, and (3) estimation of physiological signals such as ECG and ISTI for stress assessment in biomedical contexts. This research establishes an optimal methodology for embedding domain-specific knowledge into deep learning models, thereby enhancing performance in data-limited environments. It provides valuable insights for improving the applicability of vision transformer-based models across various domains, contributing to advancements in computer vision research and its practical real-world applications.

Research into indoor environmental quality (IEQ) and its effects on health, comfort, and performance of occupants is becoming an increasing priority as interest in high performance buildings and organizational productivity advances. Facility managers are interested in IEQ's close relationship to energy use in facilities and employers want to enhance employee comfort and productivity, reduce absenteeism and health costs, and reduce or even eliminate litigation by providing excellent indoor environments to employees. The increasing interest in this field as architects, engineers, facility managers, building investors, health officials, jurists, and the public seek simple and general guidelines on creating safe, healthy, and comfortable indoor environment, has put additional pressure on the research community. In the last twenty years, IEQ researchers have advanced our understanding of the influence of IEQ on health and productivity, but many uncertainties remain. Consequently, there is a critical need to expand research in this field, particularly research that is highly multidisciplinary. In addition, there is a strong need to better communicate knowledge currently documented in research publications to building professionals in order to encourage implementation of designs and practices that enhance health and productivity. Against this background, the Indoor Health and Productivity (IHP) project aims to develop a fuller understanding of the relationships between physical attributes of the workplace (e.g. thermal, lighting, ventilation, and air quality) in non-residential and non-industrial buildings and the health and productivity of occupants. A particular emphasis of the IHP project is to identify and communicate key research findings, with their practical and policy implications, to policymakers, design practitioners, facility managers, construction and energy services companies, and building investors.The IHP project has a steering committee of sponsors and senior scientists. Advisory committees are also established for specific efforts. NIST provides an administrative role for some federally supported efforts, i.e., sponsors provide money to NIST which then funds the work. The preferred mode of operation of the IHP Project is to pool modest amounts of support from multiple sponsors to achieve objectives, with projects selected by the IHP Steering Committee. Additional information on the IHP Project is available at the project web site www.IHPCentral.org.