Learning to Count without Annotations

arXiv:2307.08727v2 Announce Type: replace
Abstract: While recent supervised methods for reference-based object counting continue to improve the performance on benchmark datasets, they have to rely on small datasets due to the cost associated with manually annotating dozens of objects in images. We propose UnCounTR, a model that can learn this task without requiring any manual annotations. To this end, we construct "Self-Collages", images with various pasted objects as training samples, that provide a rich learning signal covering arbitrary object types …

abstract annotations arxiv benchmark cost count cs.cv datasets images learn object objects performance reference small type