Regressor-Segmenter Mutual Prompt Learning for Crowd Counting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909059993567232 |
|---|---|
| author | Guo, Mingyue Yuan, Li Yan, Zhaoyi Chen, Binghui Wang, Yaowei Ye, Qixiang |
| author_facet | Guo, Mingyue Yuan, Li Yan, Zhaoyi Chen, Binghui Wang, Yaowei Ye, Qixiang |
| contents | Crowd counting has achieved significant progress by training regressors to predict instance positions. In heavily crowded scenarios, however, regressors are challenged by uncontrollable annotation variance, which causes density map bias and context information inaccuracy. In this study, we propose mutual prompt learning (mPrompt), which leverages a regressor and a segmenter as guidance for each other, solving bias and inaccuracy caused by annotation variance while distinguishing foreground from background. In specific, mPrompt leverages point annotations to tune the segmenter and predict pseudo head masks in a way of point prompt learning. It then uses the predicted segmentation masks, which serve as spatial constraint, to rectify biased point annotations as context prompt learning. mPrompt defines a way of mutual information maximization from prompt learning, mitigating the impact of annotation variance while improving model accuracy. Experiments show that mPrompt significantly reduces the Mean Average Error (MAE), demonstrating the potential to be general framework for down-stream vision tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_01711 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Regressor-Segmenter Mutual Prompt Learning for Crowd Counting Guo, Mingyue Yuan, Li Yan, Zhaoyi Chen, Binghui Wang, Yaowei Ye, Qixiang Computer Vision and Pattern Recognition Crowd counting has achieved significant progress by training regressors to predict instance positions. In heavily crowded scenarios, however, regressors are challenged by uncontrollable annotation variance, which causes density map bias and context information inaccuracy. In this study, we propose mutual prompt learning (mPrompt), which leverages a regressor and a segmenter as guidance for each other, solving bias and inaccuracy caused by annotation variance while distinguishing foreground from background. In specific, mPrompt leverages point annotations to tune the segmenter and predict pseudo head masks in a way of point prompt learning. It then uses the predicted segmentation masks, which serve as spatial constraint, to rectify biased point annotations as context prompt learning. mPrompt defines a way of mutual information maximization from prompt learning, mitigating the impact of annotation variance while improving model accuracy. Experiments show that mPrompt significantly reduces the Mean Average Error (MAE), demonstrating the potential to be general framework for down-stream vision tasks. |
| title | Regressor-Segmenter Mutual Prompt Learning for Crowd Counting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.01711 |