Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
This addresses the data scarcity issue for instance detection in new environments, reducing the need for expensive annotation, though it is incremental as it builds on existing synthesis approaches.
The paper tackles the problem of lacking large annotated datasets for instance detection by proposing a simple synthesis method that cuts objects and pastes them on random backgrounds, achieving competitive performance on real data and improving relative performance by over 21% when combined with real images.
A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new environment with new instances requires expensive data collection and annotation. In this paper, we propose a simple approach to generate large annotated instance datasets with minimal effort. Our key insight is that ensuring only patch-level realism provides enough training signal for current object detector models. We automatically `cut' object instances and `paste' them on random backgrounds. A naive way to do this results in pixel artifacts which result in poor performance for trained models. We show how to make detectors ignore these artifacts during training and generate data that gives competitive performance on real data. Our method outperforms existing synthesis approaches and when combined with real images improves relative performance by more than 21% on benchmark datasets. In a cross-domain setting, our synthetic data combined with just 10% real data outperforms models trained on all real data.