# Fine-Grained AutoAugmentation for Multi-Label Classification

arXiv: https://arxiv.org/abs/2107.05384 · HTML: https://mlsanity.com/paper/2107.05384/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 12 Jul 2021.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://mlsanity.com/paper/1712.01887/) (2017)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [Adversarial AutoAugment](https://mlsanity.com/paper/1912.11188/) (2019)
- [Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification](https://mlsanity.com/paper/1702.05891/) (2017)
- [Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification](https://mlsanity.com/paper/1912.07872/) (2019)
- [Multi-Label Classification with Label Graph Superimposing](https://mlsanity.com/paper/1911.09243/) (2019)
- [Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization](https://mlsanity.com/paper/1910.04562/) (2019)
- [Improved Mixed-Example Data Augmentation](https://mlsanity.com/paper/1805.11272/) (2018)
- [Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning](https://mlsanity.com/paper/1802.09129/) (2018)
- [Attribute Recognition by Joint Recurrent Learning of Context and Correlation](https://mlsanity.com/paper/1709.08553/) (2017)
- [Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model](https://mlsanity.com/paper/1707.06089/) (2017)
- [Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization](https://mlsanity.com/paper/1611.05603/) (2016)
- [Probability Weighted Compact Feature for Domain Adaptive Retrieval](https://mlsanity.com/paper/2003.03293/) (2020)

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

- [LA3: Efficient Label-Aware AutoAugment](https://mlsanity.com/paper/2304.10310/) (2023)

## Abstract (arXiv)

Data augmentation is a commonly used approach to improving the generalization of deep learning models. Recent works show that learned data augmentation policies can achieve better generalization than hand-crafted ones. However, most of these works use unified augmentation policies for all samples in a dataset, which is observed not necessarily beneficial for all labels in multi-label classification tasks, i.e., some policies may have negative impacts on some labels while benefitting the others. To tackle this problem, we propose a novel Label-Based AutoAugmentation (LB-Aug) method for multi-label scenarios, where augmentation policies are generated with respect to labels by an augmentation-policy network. The policies are learned via reinforcement learning using policy gradient methods, providing a mapping from instance labels to their optimal augmentation policies. Numerical experiments show that our LB-Aug outperforms previous state-of-the-art augmentation methods by large margins in multiple benchmarks on image and video classification.