How to Build a Team: A Resource Optimization Perspective
When building a team, two fundamental approaches emerge: Recruiting individuals whose skills precisely match predefined tasks Aligning all team members ...
posts
Distributed Data Parallel: Scaling AI Model Training
What truly makes for a better AI model? It’s a multifaceted journey, beginning with good data and winding through the intricacies of data processing, model a...
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...
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