Locating Noise is Halfway Denoising for Semi-Supervised Segmentation
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2024, 00, pp. 16566-16576
- Issue Date:
- 2024-01-15
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| 1702643.pdf | Published version | 9.98 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
We investigate semi supervised semantic segmentation with self training where a teacher model generates pseudo masks to exploit the benefits of a large amount of unlabeled images We notice that the noisy label from the generated pseudo masks is the major obstacle to achieving good performance Previous works all treat the noise in pixel level and ignore the contextual information of the noise This work shows that locating the patch wise noisy region is a better way to deal with noise To be specific our method named Uncertainty aware Patch CutMix UPC first estimates the uncertainty of per pixel prediction for pseudo masks of unlabeled images Then UPC splits the uncertainty map into patches and calculates patch wise uncertainty UPC selects top k most uncertain patches to generate the uncertain regions Finally uncertain regions are replaced with reliable ones from labeled images We conduct extensive experiments using standard semi supervised settings on Pascal VOC and Cityscapes Experiment results show that UPC can significantly boost the performance of the state of the art methods In addition we further demonstrate that our UPC is robust to out of distribution unlabeled images e g MSCOCO
Please use this identifier to cite or link to this item: