Towards a Universal Model for Cross-Dataset Crowd Counting
This paper proposes to handle the practical problem of learning a universal model for crowd counting across scenes and datasets. We dissect that the crux of this problem is the catastrophic sensitivity of crowd counters to scale shift, which is very common in the real world and caused by factors such as different scene layouts and image resolutions. Therefore it is difficult to train a universal model that can be applied to various scenes. To address this problem, we propose scale alignment as a prime module for establishing a novel crowd counting framework. We derive a closed-form solution to get the optimal image rescaling factors for alignment by minimizing the distances between their scale distributions. A novel neural network together with a loss function based on an efficient sliced Wasserstein distance is also proposed for scale distribution estimation. Benefiting from the proposed method, we have learned a universal model that generally works well on several datasets where can even outperform state-of-the-art models that are particularly fine-tuned for each dataset significantly. Experiments also demonstrate the much better generalizability of our model to unseen scenes.
Code (0)
등록된 구현이 없습니다.
Tasks
Crowd CountingImage RescalingSimilar Papers 제목 키워드 기반
Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance
In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity. This feature is universal both within an image and across dif…
Crowd CountingDensity EstimationCross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
Crowd counting is a fundamental yet challenging task, which desires rich information to generate pixel-wise crowd density maps. However, most previous methods only used the limited information of RGB images and cannot we…
Crowd CountingRepresentation LearningPoint-Query Quadtree for Crowd Counting, Localization, and More
We show that crowd counting can be viewed as a decomposable point querying process. This formulation enables arbitrary points as input and jointly reasons whether the points are crowd and where they locate. The querying …
Crowd CountingCross-Scene Crowd Counting via Deep Convolutional Neural Networks
Cross-scene crowd counting is a challenging task where no laborious data annotation is required for counting people in new target surveillance crowd scenes unseen in the training set. The performance of most existing cro…
Crowd CountingWisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting
Datasets for training crowd counting deep networks are typically heavy-tailed in count distribution and exhibit discontinuities across the count range. As a result, the de facto statistical measures (MSE, MAE) exhibit la…
Crowd Counting