# Feature Space Augmentation for Long-Tailed Data

arXiv: https://arxiv.org/abs/2008.03673 · HTML: https://mlsanity.com/paper/2008.03673/

## Key facts

- Cited by 136 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2020.

## Built on by (most cited first, 30 of 136)

- [DeiT III: Revenge of the ViT](https://mlsanity.com/paper/2204.07118/) (2022)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification](https://mlsanity.com/paper/2103.14267/) (2021)
- [Retrieval Augmented Classification for Long-Tail Visual Recognition](https://mlsanity.com/paper/2202.11233/) (2022)
- [The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification](https://mlsanity.com/paper/2112.00412/) (2021)
- [Balanced MSE for Imbalanced Visual Regression](https://mlsanity.com/paper/2203.16427/) (2022)
- [Distributional Robustness Loss for Long-tail Learning](https://mlsanity.com/paper/2104.03066/) (2021)
- [FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2102.12867/) (2021)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [Self Supervision to Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2109.04075/) (2021)
- [VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2111.13579/) (2021)
- [Trustworthy Long-Tailed Classification](https://mlsanity.com/paper/2111.09030/) (2021)
- [Class-Balancing Diffusion Models](https://mlsanity.com/paper/2305.00562/) (2023)
- [Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions](https://mlsanity.com/paper/2305.08661/) (2023)
- [Probabilistic Contrastive Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2403.06726/) (2024)
- [Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective](https://mlsanity.com/paper/2111.03874/) (2021)
- [Long-Tailed Class Incremental Learning](https://mlsanity.com/paper/2210.00266/) (2022)
- [How Re-sampling Helps for Long-Tail Learning?](https://mlsanity.com/paper/2310.18236/) (2023)
- [Learning Imbalanced Data with Vision Transformers](https://mlsanity.com/paper/2212.02015/) (2022)
- [CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition](https://mlsanity.com/paper/2302.05499/) (2023)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [Class-Balanced Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2104.05279/) (2021)
- [Balancing Logit Variation for Long-tailed Semantic Segmentation](https://mlsanity.com/paper/2306.02061/) (2023)
- [Constructing Balance from Imbalance for Long-tailed Image Recognition](https://mlsanity.com/paper/2208.02567/) (2022)
- [Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification](https://mlsanity.com/paper/2112.07928/) (2021)
- [Balanced Knowledge Distillation for Long-tailed Learning](https://mlsanity.com/paper/2104.10510/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Delving into Semantic Scale Imbalance](https://mlsanity.com/paper/2212.14613/) (2022)
- [Long-Tailed Partial Label Learning via Dynamic Rebalancing](https://mlsanity.com/paper/2302.05080/) (2023)

## Abstract (arXiv)

Real-world data often follow a long-tailed distribution as the frequency of each class is typically different. For example, a dataset can have a large number of under-represented classes and a few classes with more than sufficient data. However, a model to represent the dataset is usually expected to have reasonably homogeneous performances across classes. Introducing class-balanced loss and advanced methods on data re-sampling and augmentation are among the best practices to alleviate the data imbalance problem. However, the other part of the problem about the under-represented classes will have to rely on additional knowledge to recover the missing information. In this work, we present a novel approach to address the long-tailed problem by augmenting the under-represented classes in the feature space with the features learned from the classes with ample samples. In particular, we decompose the features of each class into a class-generic component and a class-specific component using class activation maps. Novel samples of under-represented classes are then generated on the fly during training stages by fusing the class-specific features from the under-represented classes with the class-generic features from confusing classes. Our results on different datasets such as iNaturalist, ImageNet-LT, Places-LT and a long-tailed version of CIFAR have shown the state of the art performances.