Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Exemplar Free Class Agnostic Counting

About

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.

Viresh Ranjan, Minh Hoai• 2022

Related benchmarks

TaskDatasetResultRank
Object CountingFSC-147 (test)
MAE26.66
297
Object CountingFSC-147 (val)
MAE29.24
211
Object CountingFSC-147 1.0 (val)
MAE29.24
50
Object CountingFSC-147 1.0 (test)
MAE26.66
50
Object Counting and DetectionFSCD147 19 (val)
MAE29.24
7
Object Counting and DetectionFSCD147 19 (test)
MAE26.66
7
Showing 6 of 6 rows

Other info

Follow for update