Abstract
The mainstream crowd counting methods usually utilize the convolution neural network (CNN) to regress a density map, requiring point-level annotations. However, annotating each person with a point is an expensive and laborious process. During the testing phase, the point-level annotations are not considered to evaluate the counting accuracy, which means the point-level annotations are redundant. Hence, it is desirable to develop weakly-supervised counting methods that just rely on count level annotations, a more economical way of labeling. Current weakly-supervised counting methods adopt the CNN to regress a total count of the crowd by an image-to-count paradigm. However, having limited receptive fields for context modeling is an intrinsic limitation of these weakly-supervised CNN-based methods. These methods thus can not achieve satisfactory performance, limited applications in the real-word. The Transformer is a popular sequence-to-sequence prediction model in NLP, which contains a global receptive field. In this paper, we propose TransCrowd, which reformulates the weakly-supervised crowd counting problem from the perspective of sequence-to-count based on Transformer. We observe that the proposed TransCrowd can effectively extract the semantic crowd information by using the self-attention mechanism of Transformer. To the best of our knowledge, this is the first work to adopt a pure Transformer for crowd counting research. Experiments on five benchmark datasets demonstrate that the proposed TransCrowd achieves superior performance compared with all the weakly-supervised CNN-based counting methods and gains highly competitive counting performance compared with some popular fully-supervised counting methods. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2104.09116
