# Understanding Label Bias in Single Positive Multi-Label Learning

arXiv: https://arxiv.org/abs/2305.15584 · HTML: https://mlsanity.com/paper/2305.15584/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 11 of 11)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://mlsanity.com/paper/1604.04573/) (2016)
- [Multi-Label Learning from Single Positive Labels](https://mlsanity.com/paper/2106.09708/) (2021)
- [CNN: Single-label to Multi-label](https://mlsanity.com/paper/1406.5726/) (2014)
- [Large Loss Matters in Weakly Supervised Multi-Label Classification](https://mlsanity.com/paper/2206.03740/) (2022)
- [Simple and Robust Loss Design for Multi-Label Learning with Missing Labels](https://mlsanity.com/paper/2112.07368/) (2021)
- [Acknowledging the Unknown for Multi-label Learning with Single Positive Labels](https://mlsanity.com/paper/2203.16219/) (2022)
- [One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement](https://mlsanity.com/paper/2206.00517/) (2022)
- [Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations](https://mlsanity.com/paper/2203.06127/) (2022)
- [G2NetPL: Generic Game-Theoretic Network for Partial-Label Image Classification](https://mlsanity.com/paper/2210.11469/) (2022)
- [PLMCL: Partial-Label Momentum Curriculum Learning for Multi-Label Image Classification](https://mlsanity.com/paper/2208.09999/) (2022)

## Built on by (most cited first, 3 of 3)

- [Spatial Implicit Neural Representations for Global-Scale Species Mapping](https://mlsanity.com/paper/2306.02564/) (2023)
- [Merlin L48 Spectrogram Dataset](https://mlsanity.com/paper/2511.00252/) (2025)
- [A Survey on Incomplete Multi-label Learning: Recent Advances and Future Trends](https://mlsanity.com/paper/2406.06119/) (2024)

## Abstract (arXiv)

Annotating data for multi-label classification is prohibitively expensive because every category of interest must be confirmed to be present or absent. Recent work on single positive multi-label (SPML) learning shows that it is possible to train effective multi-label classifiers using only one positive label per image. However, the standard benchmarks for SPML are derived from traditional multi-label classification datasets by retaining one positive label for each training example (chosen uniformly at random) and discarding all other labels. In realistic settings it is not likely that positive labels are chosen uniformly at random. This work introduces protocols for studying label bias in SPML and provides new empirical results.