Interactive Class-Agnostic Object Counting

Yifeng Huang, Viresh Ranjan, Minh Hoai; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 22312-22322


We propose a novel framework for interactive class-agnostic object counting, where a human user can interactively provide feedback to improve the accuracy of a counter. Our framework consists of two main components: a user-friendly visualizer to gather feedback and an efficient mechanism to incorporate it. In each iteration, we produce a density map to show the current prediction result, and we segment it into non-overlapping regions with an easily verifiable number of objects. The user can provide feedback by selecting a region with obvious counting errors and specifying the range for the estimated number of objects within it. To improve the counting result, we develop a novel adaptation loss to force the visual counter to output the predicted count within the user-specified range. For effective and efficient adaptation, we propose a refinement module that can be used with any density-based visual counter, and only the parameters in the refinement module will be updated during adaptation. Our experiments on two challenging class-agnostic object counting benchmarks, FSCD-LVIS and FSC-147, show that our method can reduce the mean absolute error of multiple state-of-the-art visual counters by roughly 30% to 40% with minimal user input. Our project can be found at

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Huang_2023_ICCV, author = {Huang, Yifeng and Ranjan, Viresh and Hoai, Minh}, title = {Interactive Class-Agnostic Object Counting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22312-22322} }