Calibrating Uncertainty for Semi-Supervised Crowd Counting

Chen LI, Xiaoling Hu, Shahira Abousamra, Chao Chen; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 16731-16741


Semi-supervised crowd counting is an important yet challenging task. A popular approach is to iteratively generate pseudo-labels for unlabeled data and add them to the training set. The key is to use uncertainty to select reliable pseudo-labels. In this paper, we propose a novel method to calibrate model uncertainty for crowd counting. Our method takes a supervised uncertainty estimation strategy to train the model through a surrogate function. This ensures the uncertainty is well controlled throughout the training. We propose a matching-based patch-wise surrogate function to better approximate uncertainty for crowd counting tasks. The proposed method pays a sufficient amount of attention to details, while maintaining a proper granularity. Altogether our method is able to generate reliable uncertainty estimation, high quality pseudolabels, and achieve state-of-the-art performance in semisupervised crowd counting.

Related Material

[pdf] [supp] [arXiv]
@InProceedings{LI_2023_ICCV, author = {LI, Chen and Hu, Xiaoling and Abousamra, Shahira and Chen, Chao}, title = {Calibrating Uncertainty for Semi-Supervised Crowd Counting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16731-16741} }