# Pseudo Labels for Single Positive Multi-Label Learning

Source: [Pseudo Labels for Single Positive Multi-Label Learning](<https://www.sota2.com/research/paper/68fa6f8f1e209131cea46419>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:22:26.639Z

Authors: Julio Arroyo

Published: 2023-06-01T17:21:42.000Z

## Abstract

The cost of data annotation is a substantial impediment for multi-label image classification: in every image, every category must be labeled as present or absent. Single positive multi-label (SPML) learning is a cost-effective solution, where models are trained on a single positive label per image. Thus, SPML is a more challenging domain, since it requires dealing with missing labels. In this work, we propose a method to turn single positive data into fully-labeled data: Pseudo Multi-Labels. Basically, a teacher network is trained on single positive labels. Then, we treat the teacher model's predictions on the training data as ground-truth labels to train a student network on fully-labeled images. With this simple approach, we show that the performance achieved by the student model approaches that of a model trained on the actual fully-labeled images.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.01034>)

[PDF](<https://arxiv.org/pdf/2306.01034.pdf>)