Crowd Counting with Sparse Annotation
This work addresses the annotation bottleneck in crowd counting for computer vision applications, offering a more efficient labeling method with incremental improvements.
The paper tackles the problem of reducing human labeling effort in crowd counting by introducing Sparse Annotation (SA) and a Progressive Point Matching network (PPM), which outperforms previous semi-supervised methods and achieves competitive performance with state-of-the-art fully-supervised approaches.
This paper presents a new annotation method called Sparse Annotation (SA) for crowd counting, which reduces human labeling efforts by sparsely labeling individuals in an image. We argue that sparse labeling can reduce the redundancy of full annotation and capture more diverse information from distant individuals that is not fully captured by Partial Annotation methods. Besides, we propose a point-based Progressive Point Matching network (PPM) to better explore the crowd from the whole image with sparse annotation, which includes a Proposal Matching Network (PMN) and a Performance Restoration Network (PRN). The PMN generates pseudo-point samples using a basic point classifier, while the PRN refines the point classifier with the pseudo points to maximize performance. Our experimental results show that PPM outperforms previous semi-supervised crowd counting methods with the same amount of annotation by a large margin and achieves competitive performance with state-of-the-art fully-supervised methods.