MMDEW: Multipurpose Multiclass Density Estimation in the Wild
This work addresses the problem of accurate object counting in crowded environments for applications like crowd monitoring and biodiversity conservation, representing a strong specific gain in the domain.
The paper tackles multiclass object counting in dense scenes by proposing a framework with a transformer backbone and a multi-class counting head, achieving reductions in MAE of 33%, 43%, and 64% on benchmarks compared to prior methods.
Density map estimation can be used to estimate object counts in dense and occluded scenes where discrete counting-by-detection methods fail. We propose a multicategory counting framework that leverages a Twins pyramid vision-transformer backbone and a specialised multi-class counting head built on a state-of-the-art multiscale decoding approach. A two-task design adds a segmentation-based Category Focus Module, suppressing inter-category cross-talk at training time. Training and evaluation on the VisDrone and iSAID benchmarks demonstrates superior performance versus prior multicategory crowd-counting approaches (33%, 43% and 64% reduction to MAE), and the comparison with YOLOv11 underscores the necessity of crowd counting methods in dense scenes. The method's regional loss opens up multi-class crowd counting to new domains, demonstrated through the application to a biodiversity monitoring dataset, highlighting its capacity to inform conservation efforts and enable scalable ecological insights.