Scale-Aware Crowd Count Network with Annotation Error Correction
Traditional crowd counting networks suffer from information loss when feature maps are downsized through pooling layers, leading to inaccuracies in counting crowds at a distance. Existing methods often assume correct annotations during training, disregarding the impact of noisy annotations, especially in crowded scenes. Furthermore, the use of a fixed Gaussian kernel fails to account for the varying pixel distribution with respect to the camera distance. To overcome these challenges, we propose a Scale-Aware Crowd Counting Network (SACC-Net) that introduces a ``scale-aware'' architecture with error-correcting capabilities of noisy annotations. For the first time, we {\bf simultaneously} model labeling errors (mean) and scale variations (variance) by spatially-varying Gaussian distributions to produce fine-grained heat maps for crowd counting. Furthermore, the proposed adaptive Gaussian kernel variance enables the model to learn dynamically with a low-rank approximation, leading to improved convergence efficiency with comparable accuracy. The performance of SACC-Net is extensively evaluated on four public datasets: UCF-QNRF, UCF CC 50, NWPU, and ShanghaiTech A-B. Experimental results demonstrate that SACC-Net outperforms all state-of-the-art methods, validating its effectiveness in achieving superior crowd counting accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Crowd CountingSimilar Papers 제목 키워드 기반
Scale-Aware Crowd Counting Using a Joint Likelihood Density Map and Synthetic Fusion Pyramid Network
We develop a Synthetic Fusion Pyramid Network (SPF-Net) with a scale-aware loss function design for accurate crowd counting. Existing crowd-counting methods assume that the training annotation points were accurate and th…
Crowd CountingMulti-Scale Attention Network for Crowd Counting
In crowd counting datasets, people appear at different scales, depending on their distance from the camera. To address this issue, we propose a novel multi-branch scale-aware attention network that exploits the hierarchi…
Crowd CountingCrowd Density Estimation using Imperfect Labels
Density estimation is one of the most widely used methods for crowd counting in which a deep learning model learns from head-annotated crowd images to estimate crowd density in unseen images. Typically, the learning perf…
Crowd CountingDensity EstimationMissing LabelsA Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds
In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are labeled with points) to estimate both the cen…
Crowd CountingObjectobject-detectionObject DetectionJHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method
Due to its variety of applications in the real-world, the task of single image-based crowd counting has received a lot of interest in the recent years. Recently, several approaches have been proposed to address various p…
Crowd Counting