Claudio Schiavella

Papers

Total Citations

H-Index

About

Claudio Schiavella is a researcher whose work sits at the intersection of computer vision and efficient deep learning architectures. His primary focus is on optimizing transformer-based models for visual perception tasks, with a particular emphasis on monocular depth estimation—a critical challenge for autonomous systems and 3D scene understanding. In his most-cited study, "Optimize Vision Transformer Architecture via Efficient Attention Modules: A Study on the Monocular Depth Estimation Task" (2024), Schiavella investigates how streamlined attention mechanisms can reduce the computational overhead of Vision Transformers while preserving, or even enhancing, their accuracy in predicting depth from a single image. This work addresses a key bottleneck in deploying state-of-the-art models on resource-constrained devices. Though early in its trajectory, the paper has already garnered 4 citations, signaling growing interest in his pragmatic approach to model efficiency. Schiavella’s contributions are particularly valuable for bridging the gap between theoretical advances in attention mechanisms and real-world engineering constraints, making his research a promising resource for students and practitioners seeking to build lighter, faster, and more deployable vision systems.