Exemplar Free Class Agnostic Counting
This addresses the need for automated object counting in new categories without manual adaptation, though it appears incremental as it builds on prior work in class agnostic counting.
The paper tackles the problem of Class Agnostic Counting, aiming to count objects in novel categories without labeled training data, and achieves superior performance on the FSC-147 dataset compared to existing methods.
We tackle the task of Class Agnostic Counting, which aims to count objects in a novel object category at test time without any access to labeled training data for that category. All previous class agnostic counting methods cannot work in a fully automated setting, and require computationally expensive test time adaptation. To address these challenges, we propose a visual counter which operates in a fully automated setting and does not require any test time adaptation. Our proposed approach first identifies exemplars from repeating objects in an image, and then counts the repeating objects. We propose a novel region proposal network for identifying the exemplars. After identifying the exemplars, we obtain the corresponding count by using a density estimation based Visual Counter. We evaluate our proposed approach on FSC-147 dataset, and show that it achieves superior performance compared to the existing approaches.