# Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

arXiv: https://arxiv.org/abs/2112.07928 · HTML: https://mlsanity.com/paper/2112.07928/

## Key facts

- Cited by 24 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 15 Dec 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [What is the Effect of Importance Weighting in Deep Learning?](https://mlsanity.com/paper/1812.03372/) (2018)
- [Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning](https://mlsanity.com/paper/1806.06193/) (2018)
- [Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective](https://mlsanity.com/paper/2003.10780/) (2020)
- [Feature Space Augmentation for Long-Tailed Data](https://mlsanity.com/paper/2008.03673/) (2020)
- [Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification](https://mlsanity.com/paper/2103.14267/) (2021)
- [Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective](https://mlsanity.com/paper/2002.10826/) (2020)
- [GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks](https://mlsanity.com/paper/1810.10863/) (2018)
- [Implicit Semantic Data Augmentation for Deep Networks](https://mlsanity.com/paper/1909.12220/) (2019)
- [MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2103.12579/) (2021)
- [Learning to Compose Domain-Specific Transformations for Data Augmentation](https://mlsanity.com/paper/1709.01643/) (2017)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [Does Head Label Help for Long-Tailed Multi-Label Text Classification](https://mlsanity.com/paper/2101.09704/) (2021)

## Built on by (most cited first, 24 of 24)

- [Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions](https://mlsanity.com/paper/2305.08661/) (2023)
- [LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content](https://mlsanity.com/paper/2403.05854/) (2024)
- [Use Your Head: Improving Long-Tail Video Recognition](https://mlsanity.com/paper/2304.01143/) (2023)
- [ConR: Contrastive Regularizer for Deep Imbalanced Regression](https://mlsanity.com/paper/2309.06651/) (2023)
- [NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2306.16709/) (2023)
- [SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems](https://mlsanity.com/paper/2308.00994/) (2023)
- [Multi-Granularity Regularized Re-Balancing for Class Incremental Learning](https://mlsanity.com/paper/2206.15189/) (2022)
- [SCoRe: Submodular Combinatorial Representation Learning](https://mlsanity.com/paper/2310.00165/) (2023)
- [Boosting Model Resilience via Implicit Adversarial Data Augmentation](https://mlsanity.com/paper/2404.16307/) (2024)
- [DBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2207.02173/) (2022)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Enhancing In-Context Learning via Implicit Demonstration Augmentation](https://mlsanity.com/paper/2407.00100/) (2024)
- [Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail](https://mlsanity.com/paper/2408.06742/) (2024)
- [Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition](https://mlsanity.com/paper/2407.12312/) (2024)
- [Long-Tailed Learning as Multi-Objective Optimization](https://mlsanity.com/paper/2310.20490/) (2023)
- [All-around Neural Collapse for Imbalanced Classification](https://mlsanity.com/paper/2408.07253/) (2024)
- [Handling Label Uncertainty for Camera Incremental Person Re-Identification](https://mlsanity.com/paper/2210.08710/) (2022)
- [Implicit Counterfactual Data Augmentation for Robust Learning](https://mlsanity.com/paper/2304.13431/) (2023)
- [Covariance-based Space Regularization for Few-shot Class Incremental Learning](https://mlsanity.com/paper/2411.01172/) (2024)
- [VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection](https://mlsanity.com/paper/2602.05415/) (2026)
- [Conformal-in-the-Loop for Learning with Imbalanced Noisy Data](https://mlsanity.com/paper/2411.02281/) (2024)
- [Mitigating Spurious Correlations with Causal Logit Perturbation](https://mlsanity.com/paper/2505.15246/) (2025)
- [Optimizing Class Distributions for Bias-Aware Multi-Class Learning](https://mlsanity.com/paper/2509.11588/) (2025)
- [Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2602.06512/) (2026)

## Abstract (arXiv)

Real-world data often follows a long-tailed distribution, which makes the performance of existing classification algorithms degrade heavily. A key issue is that samples in tail categories fail to depict their intra-class diversity. Humans can imagine a sample in new poses, scenes, and view angles with their prior knowledge even if it is the first time to see this category. Inspired by this, we propose a novel reasoning-based implicit semantic data augmentation method to borrow transformation directions from other classes. Since the covariance matrix of each category represents the feature transformation directions, we can sample new directions from similar categories to generate definitely different instances. Specifically, the long-tailed distributed data is first adopted to train a backbone and a classifier. Then, a covariance matrix for each category is estimated, and a knowledge graph is constructed to store the relations of any two categories. Finally, tail samples are adaptively enhanced via propagating information from all the similar categories in the knowledge graph. Experimental results on CIFAR-100-LT, ImageNet-LT, and iNaturalist 2018 have demonstrated the effectiveness of our proposed method compared with the state-of-the-art methods.