Related papers: Foundation Models Meet Visualizations: Challenges …

Accurate segmentation of organs and tumors in CT and MRI scans is essential for diagnosis, treatment planning, and disease monitoring. While deep learning has advanced automated segmentation, most models remain task-specific, lacking…

In recent years, there has been a proliferation of spatiotemporal foundation models in different scientific disciplines. While promising, these models are often domain-specific and are only assessed within the particular applications for…

Vision Transformers (ViT) have marked a paradigm shift in computer vision, outperforming state-of-the-art models across diverse tasks. However, their practical deployment is hampered by high computational and memory demands. This study…

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…

Foundation models have garnered increasing attention for representation learning in remote sensing. Many such foundation models adopt approaches that have demonstrated success in computer vision with minimal domain-specific modification.…

Due to the increase in computational resources and accessibility of data, an increase in large, deep learning models trained on copious amounts of multi-modal data using self-supervised or semi-supervised learning have emerged. These…

Foundation models have rapidly advanced AI, raising the question of whether their decisions will ultimately surpass human strategies in real-world domains. The exponential, and possibly super-exponential, pace of AI development makes such…

The proliferation of Large Language Models (LLMs) has s fueled a shift in robot learning from automation towards general embodied Artificial Intelligence (AI). Adopting foundation models together with traditional learning methods to robot…

Foundation models excel at single-turn reasoning but struggle with multi-turn exploration in dynamic environments, a requirement for many real-world challenges. We evaluated these models on their ability to learn from experience, adapt, and…

Foundation Models (FMs) serve as a general class for the development of artificial intelligence systems, offering broad potential for generalization across a spectrum of downstream tasks. Despite extensive research into self-supervised…

Visualization and virtual environments (VEs) have been two interconnected parallel strands in visual computing for decades. Some VEs have been purposely developed for visualization applications, while many visualization applications are…

Spatial understanding is a critical capability for vision foundation models. While recent advances in large vision models or vision-language models (VLMs) have expanded recognition capabilities, most benchmarks emphasize localization…

Geospatial foundation models (GeoFMs) promise broad generalisation capacity for Earth observation (EO) tasks, particularly under data-limited conditions. However, their large size poses a barrier to deployment on resource-constrained space…

Large vision models (LVMs) have emerged as a foundational paradigm in visual intelligence, achieving state-of-the-art performance across diverse visual tasks. Recent advances in LVMs have facilitated their integration into Internet of…

Foundation Models (FMs), such as OpenAI's GPT, are fundamentally transforming the practice of software engineering by enabling the development of \emph{FMware} -- applications and infrastructures built around these models. FMware systems…

Vision Transformers (ViTs) are essential as foundation backbones in establishing the visual comprehension capabilities of Multimodal Large Language Models (MLLMs). Although most ViTs achieve impressive performance through image-text…

While recent vision-and-language models (VLMs) like CLIP are a powerful tool for analyzing text and images in a shared semantic space, they do not explicitly model the hierarchical nature of the set of texts which may describe an image.…

Leveraging the vision foundation models has emerged as a mainstream paradigm that improves the performance of image feature matching. However, previous works have ignored the misalignment when introducing the foundation models into feature…

Though vision transformers (ViTs) have achieved state-of-the-art performance in a variety of settings, they exhibit surprising failures when performing tasks involving visual relations. This begs the question: how do ViTs attempt to perform…

The dissertation presents four key contributions toward fairness and robustness in vision learning. First, to address the problem of large-scale data requirements, the dissertation presents a novel Fairness Domain Adaptation approach…