Learning to Count in the Crowd from Limited Labeled Data
This addresses the costly annotation process in crowd counting for computer vision applications, but it is incremental as it builds on existing semi-supervised paradigms.
The paper tackles the problem of reducing annotation effort in crowd counting by proposing a semi-supervised method that uses limited labeled data and a large pool of unlabeled data, achieving effectiveness across multiple datasets like ShanghaiTech and UCF-QNRF.
Recent crowd counting approaches have achieved excellent performance. However, they are essentially based on fully supervised paradigm and require large number of annotated samples. Obtaining annotations is an expensive and labour-intensive process. In this work, we focus on reducing the annotation efforts by learning to count in the crowd from limited number of labeled samples while leveraging a large pool of unlabeled data. Specifically, we propose a Gaussian Process-based iterative learning mechanism that involves estimation of pseudo-ground truth for the unlabeled data, which is then used as supervision for training the network. The proposed method is shown to be effective under the reduced data (semi-supervised) settings for several datasets like ShanghaiTech, UCF-QNRF, WorldExpo, UCSD, etc. Furthermore, we demonstrate that the proposed method can be leveraged to enable the network in learning to count from synthetic dataset while being able to generalize better to real-world datasets (synthetic-to-real transfer).