Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911782929432576 |
|---|---|
| author | Lin, Hui Ma, Zhiheng Ji, Rongrong Wang, Yaowei Su, Zhou Hong, Xiaopeng Meng, Deyu |
| author_facet | Lin, Hui Ma, Zhiheng Ji, Rongrong Wang, Yaowei Su, Zhou Hong, Xiaopeng Meng, Deyu |
| contents | This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled. We formulate the pixel-wise density value to regress as a probability distribution, instead of a single deterministic value. On this basis, we propose a semi-supervised crowd-counting model. Firstly, we design a pixel-wise distribution matching loss to measure the differences in the pixel-wise density distributions between the prediction and the ground truth; Secondly, we enhance the transformer decoder by using density tokens to specialize the forwards of decoders w.r.t. different density intervals; Thirdly, we design the interleaving consistency self-supervised learning mechanism to learn from unlabeled data efficiently. Extensive experiments on four datasets are performed to show that our method clearly outperforms the competitors by a large margin under various labeled ratio settings. Code will be released at https://github.com/LoraLinH/Semi-supervised-Counting-via-Pixel-by-pixel-Density-Distribution-Modelling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15297 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling Lin, Hui Ma, Zhiheng Ji, Rongrong Wang, Yaowei Su, Zhou Hong, Xiaopeng Meng, Deyu Computer Vision and Pattern Recognition Machine Learning This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled. We formulate the pixel-wise density value to regress as a probability distribution, instead of a single deterministic value. On this basis, we propose a semi-supervised crowd-counting model. Firstly, we design a pixel-wise distribution matching loss to measure the differences in the pixel-wise density distributions between the prediction and the ground truth; Secondly, we enhance the transformer decoder by using density tokens to specialize the forwards of decoders w.r.t. different density intervals; Thirdly, we design the interleaving consistency self-supervised learning mechanism to learn from unlabeled data efficiently. Extensive experiments on four datasets are performed to show that our method clearly outperforms the competitors by a large margin under various labeled ratio settings. Code will be released at https://github.com/LoraLinH/Semi-supervised-Counting-via-Pixel-by-pixel-Density-Distribution-Modelling. |
| title | Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2402.15297 |