# Multi-Label Learning from Single Positive Labels

arXiv: https://arxiv.org/abs/2106.09708 · HTML: https://mlsanity.com/paper/2106.09708/

## Key facts

- Cited by 81 papers in the map (data through 7 Oct 2026).
- Builds on 31 of its 68 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Learning from positive and unlabeled data: a survey](https://mlsanity.com/paper/1811.04820/) (2018)
- [Does label smoothing mitigate label noise?](https://mlsanity.com/paper/2003.02819/) (2020)
- [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://mlsanity.com/paper/1604.04573/) (2016)
- [Learning Visual Features from Large Weakly Supervised Data](https://mlsanity.com/paper/1511.02251/) (2015)
- [Deep Learning is Robust to Massive Label Noise](https://mlsanity.com/paper/1705.10694/) (2017)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Learning From Noisy Large-Scale Datasets With Minimal Supervision](https://mlsanity.com/paper/1701.01619/) (2017)
- [Presence-Only Geographical Priors for Fine-Grained Image Classification](https://mlsanity.com/paper/1906.05272/) (2019)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [Learning from Complementary Labels](https://mlsanity.com/paper/1705.07541/) (2017)
- [CNN: Single-label to Multi-label](https://mlsanity.com/paper/1406.5726/) (2014)
- [Deep Convolutional Ranking for Multilabel Image Annotation](https://mlsanity.com/paper/1312.4894/) (2013)
- [Effective Use of Word Order for Text Categorization with Convolutional Neural Networks](https://mlsanity.com/paper/1412.1058/) (2014)
- [Large-scale Multi-label Text Classification - Revisiting Neural Networks](https://mlsanity.com/paper/1312.5419/) (2013)
- [PU Learning for Matrix Completion](https://mlsanity.com/paper/1411.6081/) (2014)
- [Set-valued classification -- overview via a unified framework](https://mlsanity.com/paper/2102.12318/) (2021)
- [Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition](https://mlsanity.com/paper/1910.11012/) (2019)
- [Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning](https://mlsanity.com/paper/1901.01703/) (2019)
- [Elucidating image-to-set prediction: An analysis of models, losses and datasets](https://mlsanity.com/paper/1904.05709/) (2019)

## Built on by (most cited first, 30 of 81)

- [Spatial Implicit Neural Representations for Global-Scale Species Mapping](https://mlsanity.com/paper/2306.02564/) (2023)
- [KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2205.06784/) (2022)
- [CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification](https://mlsanity.com/paper/2307.16634/) (2023)
- [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)
- [Integrative Few-Shot Learning for Classification and Segmentation](https://mlsanity.com/paper/2203.15712/) (2022)
- [Acknowledging the Unknown for Multi-label Learning with Single Positive Labels](https://mlsanity.com/paper/2203.16219/) (2022)
- [Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels](https://mlsanity.com/paper/2303.13223/) (2023)
- [One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement](https://mlsanity.com/paper/2206.00517/) (2022)
- [Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation](https://mlsanity.com/paper/2111.13517/) (2021)
- [Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations](https://mlsanity.com/paper/2203.06127/) (2022)
- [The iNaturalist Sounds Dataset](https://mlsanity.com/paper/2506.00343/) (2025)
- [Design of Negative Sampling Strategies for Distantly Supervised Skill Extraction](https://mlsanity.com/paper/2209.05987/) (2022)
- [Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning](https://mlsanity.com/paper/2305.02795/) (2023)
- [Learning Semantic Segmentation from Multiple Datasets with Label Shifts](https://mlsanity.com/paper/2202.14030/) (2022)
- [IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training](https://mlsanity.com/paper/2207.05333/) (2022)
- [Object Recognition as Next Token Prediction](https://mlsanity.com/paper/2312.02142/) (2023)
- [Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noise](https://mlsanity.com/paper/2312.07087/) (2023)
- [Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning](https://mlsanity.com/paper/2310.15985/) (2023)
- [On the selection and effectiveness of pseudo-absences for species distribution modeling with deep learning](https://mlsanity.com/paper/2401.02989/) (2024)
- [Text-Region Matching for Multi-Label Image Recognition with Missing Labels](https://mlsanity.com/paper/2407.18520/) (2024)
- [When Less is Enough: Positive and Unlabeled Learning Model for Vulnerability Detection](https://mlsanity.com/paper/2308.10523/) (2023)
- [GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2309.00923/) (2023)
- [Language Modelling via Learning to Rank](https://mlsanity.com/paper/2110.06961/) (2021)
- [Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference](https://mlsanity.com/paper/2205.04227/) (2022)
- [G2NetPL: Generic Game-Theoretic Network for Partial-Label Image Classification](https://mlsanity.com/paper/2210.11469/) (2022)
- [Font Generation with Missing Impression Labels](https://mlsanity.com/paper/2203.10348/) (2022)
- [Improving Multi-label Recognition using Class Co-Occurrence Probabilities](https://mlsanity.com/paper/2404.16193/) (2024)
- [Boosting Single Positive Multi-label Classification with Generalized Robust Loss](https://mlsanity.com/paper/2405.03501/) (2024)
- [PLMCL: Partial-Label Momentum Curriculum Learning for Multi-Label Image Classification](https://mlsanity.com/paper/2208.09999/) (2022)

## Abstract (arXiv)

Predicting all applicable labels for a given image is known as multi-label classification. Compared to the standard multi-class case (where each image has only one label), it is considerably more challenging to annotate training data for multi-label classification. When the number of potential labels is large, human annotators find it difficult to mention all applicable labels for each training image. Furthermore, in some settings detection is intrinsically difficult e.g. finding small object instances in high resolution images. As a result, multi-label training data is often plagued by false negatives. We consider the hardest version of this problem, where annotators provide only one relevant label for each image. As a result, training sets will have only one positive label per image and no confirmed negatives. We explore this special case of learning from missing labels across four different multi-label image classification datasets for both linear classifiers and end-to-end fine-tuned deep networks. We extend existing multi-label losses to this setting and propose novel variants that constrain the number of expected positive labels during training. Surprisingly, we show that in some cases it is possible to approach the performance of fully labeled classifiers despite training with significantly fewer confirmed labels.