Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911961702203392 |
|---|---|
| author | Cai, Zhi Gao, Yingjie Zheng, Yaoyan Zhou, Nan Huang, Di |
| author_facet | Cai, Zhi Gao, Yingjie Zheng, Yaoyan Zhou, Nan Huang, Di |
| contents | In computer vision, object detection is an important task that finds its application in many scenarios. However, obtaining extensive labels can be challenging, especially in crowded scenes. Recently, the Segment Anything Model (SAM) has been proposed as a powerful zero-shot segmenter, offering a novel approach to instance segmentation tasks. However, the accuracy and efficiency of SAM and its variants are often compromised when handling objects in crowded and occluded scenes. In this paper, we introduce Crowd-SAM, a SAM-based framework designed to enhance SAM's performance in crowded and occluded scenes with the cost of few learnable parameters and minimal labeled images. We introduce an efficient prompt sampler (EPS) and a part-whole discrimination network (PWD-Net), enhancing mask selection and accuracy in crowded scenes. Despite its simplicity, Crowd-SAM rivals state-of-the-art (SOTA) fully-supervised object detection methods on several benchmarks including CrowdHuman and CityPersons. Our code is available at https://github.com/FelixCaae/CrowdSAM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11464 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes Cai, Zhi Gao, Yingjie Zheng, Yaoyan Zhou, Nan Huang, Di Computer Vision and Pattern Recognition In computer vision, object detection is an important task that finds its application in many scenarios. However, obtaining extensive labels can be challenging, especially in crowded scenes. Recently, the Segment Anything Model (SAM) has been proposed as a powerful zero-shot segmenter, offering a novel approach to instance segmentation tasks. However, the accuracy and efficiency of SAM and its variants are often compromised when handling objects in crowded and occluded scenes. In this paper, we introduce Crowd-SAM, a SAM-based framework designed to enhance SAM's performance in crowded and occluded scenes with the cost of few learnable parameters and minimal labeled images. We introduce an efficient prompt sampler (EPS) and a part-whole discrimination network (PWD-Net), enhancing mask selection and accuracy in crowded scenes. Despite its simplicity, Crowd-SAM rivals state-of-the-art (SOTA) fully-supervised object detection methods on several benchmarks including CrowdHuman and CityPersons. Our code is available at https://github.com/FelixCaae/CrowdSAM. |
| title | Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.11464 |