Tracking People in Dense Crowds Using Supervoxels

Takayama, Shota; Suzuki, Teppei; Aoki, Yoshimitsu; Isobe, Sho; Masuda, Makoto

doi:10.1109/sitis.2016.90

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hierarchical clustering approaches are sometimes used to solve image segmentation. For example, some previous methods [14,19,22,52,65,66,51,50,53,45] group pixels into small segments by using superpixel segmentation [1,49,24] for pre-processing; the obtained segments are then merged or classified to obtain the desired cluster. Such a hierarchical approach often reduces computational costs and improves segmentation accuracy compared to directly clustering or classifying pixels.…”

Section: Hierarchical Clusteringmentioning

confidence: 99%

HCFormer: Unified Image Segmentation with Hierarchical Clustering

Suzuki¹

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a hierarchical clustering-based image segmentation scheme for deep neural networks, called HCFormer. We interpret image segmentation, including semantic, instance, and panoptic segmentation, as a pixel clustering problem, and accomplish it by bottom-up, hierarchical clustering with deep neural networks. Our hierarchical clustering removes the pixel decoder from conventional segmentation models and simplifies the segmentation pipeline, resulting in improved segmentation accuracies and interpretability. HCFormer can address semantic, instance, and panoptic segmentation with the same architecture because the pixel clustering is a common approach for various image segmentation. In experiments, HCFormer achieves comparable or superior segmentation accuracies compared to baseline methods on semantic segmentation (55.5 mIoU on ADE20K), instance segmentation (47.1 AP on COCO), and panoptic segmentation (55.7 PQ on COCO). 1

show abstract