IGNORE: Information Gap-Based False Negative Loss Rejection for Single Positive Multi-Label Learning

GyeongRyeol Song, Noo-Ri Kim, Jin-Seop Lee, Jee-Hyong Lee
2/14/2026

No official code found. Best implementation: gyeong-ryeol-song/SPML-IGNORE (5 stars, last commit 2025-01-30).

DOISemantic Scholar

Code Implementations(1)

gyeong-ryeol-song/SPML-IGNORECommunity63%

Official PyTorch implementation of ECCV 2024 paper (IGNORE: Information Gap-based False Negative Loss Rejection for Single Positive Multi-Label Learning)

50PythonJan 21, 20251 years ago

Cite this paper

@article{song2026ignore,
  title  = {IGNORE: Information Gap-Based False Negative Loss Rejection for Single Positive Multi-Label Learning},
  author = {GyeongRyeol Song and Noo-Ri Kim and Jin-Seop Lee and Jee-Hyong Lee},
  year   = {2026},
  doi    = {10.1007/978-3-031-72754-2_27},
  url    = {https://doi.org/10.1007/978-3-031-72754-2_27},
  journal = {ECCV 2024 2024}
}

Discussion