Related papers: Low-Resource Vision Challenges for Foundation Mode…
The primary aim of this manuscript is to underscore a significant limitation in current deep learning models, particularly vision models. Unlike human vision, which efficiently selects only the essential visual areas for further processing,…
Depth estimation is a fundamental task in 3D computer vision, crucial for applications such as 3D reconstruction, free-viewpoint rendering, robotics, autonomous driving, and AR/VR technologies. Traditional methods relying on hardware…
Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature representation that is useful for various applications. However, in case we have multiple views of…
Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable…
Multisource image analysis that leverages complementary spectral, spatial, and structural information benefits fine-grained object recognition that aims to classify an object into one of many similar subcategories. However, for multisource…
Foundation models have recently expanded into robotics after excelling in computer vision and natural language processing. The models are accessible in two ways: open-source or paid, closed-source options. Users with access to both face a…
The rapid advancement of remote sensing foundation models, particularly vision and multimodal models, has significantly enhanced the capabilities of intelligent geospatial data interpretation. These models combine various data modalities,…
Despite the rapid advancement in the field of image recognition, the processing of high-resolution imagery remains a computational challenge. However, this processing is pivotal for extracting detailed object insights in areas ranging from…
Vision foundation models have attracted significant attention for their ability to leverage large-scale unlabeled visual data. This advantage is particularly important in remote sensing, where data acquisition is costly and annotation often…
Generating images conditioned on multiple visual references is critical for real-world applications such as multi-subject composition, narrative illustration, and novel view synthesis, yet current models suffer from severe performance…
Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the real-world…
Foundation models can be disruptive for future AI development by scaling up deep learning in terms of model size and training data's breadth and size. These models achieve state-of-the-art performance (often through further adaptation) on a…
The rapid advancement of foundation modelslarge-scale neural networks trained on diverse, extensive datasetshas revolutionized artificial intelligence, enabling unprecedented advancements across domains such as natural language processing,…
Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…
Foundation models encompass an extensive knowledge base and offer remarkable transferability. However, this knowledge becomes outdated or insufficient over time. The challenge lies in continuously updating foundation models to accommodate…
Recent advancements in language and vision assistants have showcased impressive capabilities but suffer from a lack of transparency, limiting broader research and reproducibility. While open-source models handle general image tasks…
Real-world perception systems in many cases build on hardware with limited resources to adhere to cost and power limitations of their carrying system. Deploying deep neural networks on resource-constrained hardware became possible with…
In data-rich domains such as vision, language, and speech, deep learning prevails to deliver high-performance task-specific models and can even learn general task-agnostic representations for efficient finetuning to downstream tasks.…
Visual grounding, which aims to build a correspondence between visual objects and their language entities, plays a key role in cross-modal scene understanding. One promising and scalable strategy for learning visual grounding is to utilize…
While transformer-based finetuning techniques have proven effective in tasks that involve low-resource, low-data environments, a lack of properly established baselines and benchmark datasets make it hard to compare different approaches that…