Adding New Categories in Object Detection Using Few-Shot Copy-Paste
This addresses the problem of data-efficient instance detection for rare categories in computer vision, though it appears incremental as it builds on existing few-shot and copy-paste techniques.
The study tackled the challenge of adding new object categories to detection models with minimal data by investigating occlusion-based data augmentation, achieving 95% accuracy on an unseen test set using only 15 new images added to a large-scale dataset.
Developing data-efficient instance detection models that can handle rare object categories remains a key challenge in computer vision. However, existing research often overlooks data collection strategies and evaluation metrics tailored to real-world scenarios involving neural networks. In this study, we systematically investigate data collection and augmentation techniques focused on object occlusion, aiming to mimic occlusion relationships observed in practical applications. Surprisingly, we find that even a simple occlusion mechanism is sufficient to achieve strong performance when introducing new object categories. Notably, by adding just 15 images of a new category to a large-scale training dataset containing over half a million images across hundreds of categories, the model achieves 95\% accuracy on an unseen test set with thousands of instances of the new category.