Effective Train/Test Stratification for Object Detection
TL;DR: Here’s a talk based on this post: There’s an unavoidable, inherent difficulty in fine-tuning deep neural networks for specific tasks, which primarily stems from the lack of training data. It would seem ridiculous to a layperson that a pretrained vision model (containing millions of parameters, trained on millions of images) could learn to solve highly specific problems. Therefore, when fine-tuned models do perform well, they seem all the more miraculous.