ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Counting
It addresses a limitation in class-agnostic counting for multi-object scenarios, offering utility in fields like surveillance or biology, but is incremental as it builds on existing counting paradigms.
The paper tackles the problem of counting multiple types of objects simultaneously without requiring exemplars, by proposing a new dataset (MCAC) and method (ABC123) that outperforms contemporary methods on this dataset and transfers well to a standard benchmark.
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.