Crowd counting is a difficult task because of the diversity of scenes. Most of the existing crowd counting methods adopt complex structures with massive backbones to enhance the generalization ability. Unfortunately, the performance of existing methods on large-scale data sets is not satisfactory. In order to handle various scenarios with less complex network, we explored how to efficiently use the multi-expert model for crowd counting tasks. We mainly focus on how to train more efficient expert networks and how to choose the most suitable expert. Specifically, we propose a task-driven similarity metric based on sample’s mutual enhancement, referred as co-fine-tune similarity, which can find a more efficient subset of data for training the expert network. Similar samples are considered as a cluster which is used to obtain parameters of an expert. Besides, to make better use of the proposed method, we design a simple network called FPN with Deconvolution Counting Network, which is a more suitable base model for the multi-expert counting network. Experimental results show that multiple experts FDC (MFDC) achieves the best performance on four public data sets, including the large scale NWPU-Crowd data set. Furthermore, the MFDC trained on an extensive dense crowd data set can generalize well on the other data sets without extra training or fine-tuning.
Exploiting sample correlation for crowd counting with multi-expert network / Liu, Xinyan; Li, Guorong; Han, Zhenjun; Zhang, Weigang; Yang, Yifan; Huang, Qingming; Sebe, Nicu. - (2021), pp. 3195-3204. (Intervento presentato al convegno 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 tenutosi a Virtual event nel 11th-17th October 2021) [10.1109/ICCV48922.2021.00320].
Exploiting sample correlation for crowd counting with multi-expert network
Sebe, Nicu
2021-01-01
Abstract
Crowd counting is a difficult task because of the diversity of scenes. Most of the existing crowd counting methods adopt complex structures with massive backbones to enhance the generalization ability. Unfortunately, the performance of existing methods on large-scale data sets is not satisfactory. In order to handle various scenarios with less complex network, we explored how to efficiently use the multi-expert model for crowd counting tasks. We mainly focus on how to train more efficient expert networks and how to choose the most suitable expert. Specifically, we propose a task-driven similarity metric based on sample’s mutual enhancement, referred as co-fine-tune similarity, which can find a more efficient subset of data for training the expert network. Similar samples are considered as a cluster which is used to obtain parameters of an expert. Besides, to make better use of the proposed method, we design a simple network called FPN with Deconvolution Counting Network, which is a more suitable base model for the multi-expert counting network. Experimental results show that multiple experts FDC (MFDC) achieves the best performance on four public data sets, including the large scale NWPU-Crowd data set. Furthermore, the MFDC trained on an extensive dense crowd data set can generalize well on the other data sets without extra training or fine-tuning.File | Dimensione | Formato | |
---|---|---|---|
Liu_Exploiting_Sample_Correlation_for_Crowd_Counting_With_Multi-Expert_Network_ICCV_2021_paper.pdf
accesso aperto
Tipologia:
Post-print referato (Refereed author’s manuscript)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.8 MB
Formato
Adobe PDF
|
1.8 MB | Adobe PDF | Visualizza/Apri |
Exploiting_sample_correlation_for_crowd_counting_with_multi-expert_network.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
2.45 MB
Formato
Adobe PDF
|
2.45 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione