Beyond mAP: Better Evaluation of Bbox
In my experiences with computer vision models, evaluating the performance of instance segmentation or object detection models has predominantly relied on a m...
posts
Knowledge Distillation: A Comparative Exploration and the Role of Soft Targets
Knowledge Distillation is a process that refines large, complex models into smaller, efficient ones without losing much of the original performance. The conc...
ViT vs CNN: A Technical Deep Dive for High-Resolution Vision Tasks
This isn’t just theory—it’s battle-tested. Over years of deploying vision systems for farming applications, I’ve learned one truth: architecture choice makes...
Relative Theory
Understanding Relativity: My note into the Depths of Space and Time
Conformal Prediction
The Concept of Conformal Prediction
Data Science in Elixir
Transitioning from Python to Elixir in Data Science Data processing is often dominated by Python and libraries like pandas and spark. However, Elixir is emer...