Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation

Jinpeng Chen, Runmin Cong, Yuxuan Luo, H. Ip, Sam Kwong
2/12/2026

No official code found. Best implementation: jinpeng0528/STAR (20 stars, last commit 2025-03-19).

DOISemantic Scholar

Code Implementations(1)

jinpeng0528/STARCommunity67%

Code release for "Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation" (NeurIPS 2023)

202Shell, PythonOct 2, 20231 years ago

Cite this paper

@article{chen2026saving,
  title  = {Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation},
  author = {Jinpeng Chen and Runmin Cong and Yuxuan Luo and H. Ip and Sam Kwong},
  year   = {2026},
  doi    = {10.52202/075280-1561},
  url    = {https://doi.org/10.52202/075280-1561},
  journal = {NEURIPS 2023 2023}
}

Discussion