ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Counting

TL;DR

This paper introduces a new dataset and a novel counting method that can simultaneously count multiple object types without needing examples during training or inference, improving multi-class counting accuracy.

Contribution

The paper presents the first multi-class, class-agnostic counting dataset (MCAC) and a new method (ABC123) that counts objects without exemplars, advancing multi-class counting capabilities.

Findings

ABC123 outperforms existing methods on MCAC

ABC123 generalizes well to FSC-147 dataset

The dataset MCAC enables better multi-class counting evaluation

Abstract

Class-agnostic counting methods enumerate objects of an arbitrary class, providing tremendous utility in many fields. Prior works have limited usefulness as they require either a set of examples of the type to be counted or that the query image contains only a single type of object. A significant factor in these shortcomings is the lack of a dataset to properly address counting in settings with more than one kind of object present. To address these issues, we propose the first Multi-class, Class-Agnostic Counting dataset (MCAC) and A Blind Counter (ABC123), a method that can count multiple types of objects simultaneously without using examples of type during training or inference. ABC123 introduces a new paradigm where instead of requiring exemplars to guide the enumeration, examples are found after the counting stage to help a user understand the generated outputs. We show that ABC123 outperforms contemporary methods on MCAC without needing human in-the-loop annotations. We also show that this performance transfers to FSC-147, the standard class-agnostic counting dataset. MCAC is available at MCAC.active.vision and ABC123 is available at ABC123.active.vision.