Explore the Power of Synthetic Data on Few-shot Object Detection. (arXiv:2303.13221v2 [cs.CV] UPDATED)

Few-shot object detection (FSOD) aims to expand an object detector for novel
categories given only a few instances for training. The few training samples
restrict the performance of FSOD model. Recent text-to-image generation models
have shown promising results in generating high-quality images. How applicable
these synthetic images are for FSOD tasks remains under-explored. This work
extensively studies how synthetic images generated from state-of-the-art
text-to-image generators benefit FSOD tasks. We focus on two perspectives: (1)
How to use synthetic data for …

arxiv data detection image image generation image generation models images instances novel performance power quality synthetic synthetic data text text-to-image training