# Towards Imbalanced Large Scale Multi-label Classification with Partially Annotated Labels

arXiv: https://arxiv.org/abs/2308.00166 · HTML: https://mlsanity.com/paper/2308.00166/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 38 references that are in the map.
- First posted on arXiv 31 Jul 2023.

## Builds on (most cited first, 18 of 18)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (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)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets](https://mlsanity.com/paper/2007.09654/) (2020)
- [Imbalance Problems in Object Detection: A Review](https://mlsanity.com/paper/1909.00169/) (2019)
- [Presence-Only Geographical Priors for Fine-Grained Image Classification](https://mlsanity.com/paper/1906.05272/) (2019)
- [Multi-Label Learning from Single Positive Labels](https://mlsanity.com/paper/2106.09708/) (2021)
- [Large-scale Multi-label Learning with Missing Labels](https://mlsanity.com/paper/1307.5101/) (2013)
- [Large-scale Multi-label Text Classification - Revisiting Neural Networks](https://mlsanity.com/paper/1312.5419/) (2013)
- [Simple and Robust Loss Design for Multi-Label Learning with Missing Labels](https://mlsanity.com/paper/2112.07368/) (2021)
- [Computational discovery of new 2D materials using deep learning generative models](https://mlsanity.com/paper/2012.09314/) (2020)
- [An Effective Approach for Multi-label Classification with Missing Labels](https://mlsanity.com/paper/2210.13651/) (2022)

## Built on by (most cited first, 1 of 1)

- [Revising the Problem of Partial Labels from the Perspective of CNNs' Robustness](https://mlsanity.com/paper/2407.17630/) (2024)

## Abstract (arXiv)

Multi-label classification is a widely encountered problem in daily life, where an instance can be associated with multiple classes. In theory, this is a supervised learning method that requires a large amount of labeling. However, annotating data is time-consuming and may be infeasible for huge labeling spaces. In addition, label imbalance can limit the performance of multi-label classifiers, especially when some labels are missing. Therefore, it is meaningful to study how to train neural networks using partial labels. In this work, we address the issue of label imbalance and investigate how to train classifiers using partial labels in large labeling spaces. First, we introduce the pseudo-labeling technique, which allows commonly adopted networks to be applied in partially labeled settings without the need for additional complex structures. Then, we propose a novel loss function that leverages statistical information from existing datasets to effectively alleviate the label imbalance problem. In addition, we design a dynamic training scheme to reduce the dimension of the labeling space and further mitigate the imbalance. Finally, we conduct extensive experiments on some publicly available multi-label datasets such as COCO, NUS-WIDE, CUB, and Open Images to demonstrate the effectiveness of the proposed approach. The results show that our approach outperforms several state-of-the-art methods, and surprisingly, in some partial labeling settings, our approach even exceeds the methods trained with full labels.