Coming soon!
The Official PyTorch code for “A Weakly Supervised Semantic Segmentation Method based on Local Superpixel Transformation”.
Use the following command to prepare your environment.
pip install -r requirements.txt- PASCAL VOC 2012
- Images
- Saliency maps using Poolnet
Please set the dataset path in
dataset_root.py.
- Pretrained models
- We utilize DeepLab-V2 for the segmentation network.
- Please see deeplab-pytorch for the implementation in PyTorch.
If you use our codes and models in your research, please cite:
@misc {PPR:PPR635314,
Title = {A Weakly Supervised Semantic Segmentation Method based on Local Superpixel Transformation},
Author = {Ma, Zhiming and Chen, Dali and Mo, Yilin and Chen, Yue and Zhang, Yuming},
DOI = {10.21203/rs.3.rs-2714436/v1},
Abstract = {Weakly supervised semantic segmentation (WSSS) can obtain pseudo-semantic masks through a weaker level of supervised labels, reducing the need for costly pixel-level annotations. However, the general class activation map (CAM)-based pseudo-mask acquisition method suffers from sparse coverage, leading to false positive and false negative regions that reduce accuracy. We propose a WSSS method based on local superpixel transformation that combines superpixel theory and image local information. Our method uses a superpixel local consistency weighted cross-entropy loss to correct erroneous regions and a post-processing method based on the adjacent superpixel affinity matrix (ASAM) to expand false negatives, suppress false positives, and optimize semantic boundaries. Our method achieves 73.4% mIoU on the PASCAL VOC 2012 validation set and 73.9% on the test set, and the ASAM post-processing method is validated on several state-of-the-art methods. If our paper is accepted, our code will be published.},
Publisher = {Research Square},
Year = {2023},
URL = {https://doi.org/10.21203/rs.3.rs-2714436/v1},
}A gradio run effect demo.
2023.8.28 🎉🎉Our paper was accepted and the full code will be made public soon!