Lei Zhu, Hangzhou He, Lujia Jin, Yanye Lu, Xinliang Zhang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Scribble-based weakly-supervised semantic segmentation using sparse scribble supervision is gaining traction as it reduces annotation costs when compared to fully annotated alternatives. Existing methods primarily generate pseudolabels by diffusing labeled pixels to unlabeled ones with local cues for supervision. However, this diffusion process fails to exploit global semantics and class-specific cues, which are important for semantic segmentation. In this study, we propose a class-driven scribble promotion network, which utilizes both scribble annotations and pseudo-labels informed by image-level classes and global semantics for supervision. Directly adopting pseudo-labels might misguide the segmentation model, thus we design a localization rectification module to correct foreground representations in the feature space. To further combine the advantages of both supervisions, we also introduce a distance entropy loss for uncertainty reduction, which adapts per-pixel confidence weights according to the reliable region determined by the scribble and pseudo-label's boundary. Experiments on the ScribbleSup dataset with different qualities of scribble annotations outperform all the previous methods, demonstrating the superiority and robustness of our method. The code is available at https://github.com/ Zxl19990529/Class-driven-Scribble-Promotion-Network.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.17555")
get_code_for_paper("2402.17555")
have("2402.17555")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.17555.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.17555)
Connect an agent — have() is free.