TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Object Counting	FSC147	LOCA	MAE(val)	10.24	# 1
Object Counting	FSC147	LOCA	RMSE(val)	32.56	# 1
Object Counting	FSC147	LOCA	MAE(test)	10.79	# 1
Object Counting	FSC147	LOCA	RMSE(test)	56.97	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/a-low-shot-object-counting-network-with/object-counting-on-fsc147)](https://paperswithcode.com/sota/object-counting-on-fsc147?p=a-low-shot-object-counting-network-with)`

A Low-Shot Object Counting Network With Iterative Prototype Adaptation

ICCV 2023 · Nikola Djukic, Alan Lukezic, Vitjan Zavrtanik, Matej Kristan ·

We consider low-shot counting of arbitrary semantic categories in the image using only few annotated exemplars (few-shot) or no exemplars (no-shot). The standard few-shot pipeline follows extraction of appearance queries from exemplars and matching them with image features to infer the object counts. Existing methods extract queries by feature pooling which neglects the shape information (e.g., size and aspect) and leads to a reduced object localization accuracy and count estimates. We propose a Low-shot Object Counting network with iterative prototype Adaptation (LOCA). Our main contribution is the new object prototype extraction module, which iteratively fuses the exemplar shape and appearance information with image features. The module is easily adapted to zero-shot scenarios, enabling LOCA to cover the entire spectrum of low-shot counting problems. LOCA outperforms all recent state-of-the-art methods on FSC147 benchmark by 20-30% in RMSE on one-shot and few-shot and achieves state-of-the-art on zero-shot scenarios, while demonstrating better generalization capabilities.