Bound Tightening Network for Robust Crowd Counting
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910624135512064 |
|---|---|
| author | Wu, Qiming |
| author_facet | Wu, Qiming |
| contents | Crowd Counting is a fundamental topic, aiming to estimate the number of individuals in the crowded images or videos fed from surveillance cameras. Recent works focus on improving counting accuracy, while ignoring the certified robustness of counting models. In this paper, we propose a novel Bound Tightening Network (BTN) for Robust Crowd Counting. It consists of three parts: base model, smooth regularization module and certify bound module. The core idea is to propagate the interval bound through the base model (certify bound module) and utilize the layer weights (smooth regularization module) to guide the network learning. Experiments on different benchmark datasets for counting demonstrate the effectiveness and efficiency of BTN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19146 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bound Tightening Network for Robust Crowd Counting Wu, Qiming Computer Vision and Pattern Recognition Artificial Intelligence Crowd Counting is a fundamental topic, aiming to estimate the number of individuals in the crowded images or videos fed from surveillance cameras. Recent works focus on improving counting accuracy, while ignoring the certified robustness of counting models. In this paper, we propose a novel Bound Tightening Network (BTN) for Robust Crowd Counting. It consists of three parts: base model, smooth regularization module and certify bound module. The core idea is to propagate the interval bound through the base model (certify bound module) and utilize the layer weights (smooth regularization module) to guide the network learning. Experiments on different benchmark datasets for counting demonstrate the effectiveness and efficiency of BTN. |
| title | Bound Tightening Network for Robust Crowd Counting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2409.19146 |