# Decision Boundary-aware Generation for Long-tailed Learning

arXiv: https://arxiv.org/abs/2605.01468 · HTML: https://mlsanity.com/paper/2605.01468/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 2 May 2026.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [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)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Deep Learning Scaling is Predictable, Empirically](https://mlsanity.com/paper/1712.00409/) (2017)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [M2m: Imbalanced Classification via Major-to-minor Translation](https://mlsanity.com/paper/2004.00431/) (2020)
- [Retrieval Augmented Classification for Long-Tail Visual Recognition](https://mlsanity.com/paper/2202.11233/) (2022)
- [Class-Balancing Diffusion Models](https://mlsanity.com/paper/2305.00562/) (2023)
- [How Re-sampling Helps for Long-Tail Learning?](https://mlsanity.com/paper/2310.18236/) (2023)
- [Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval](https://mlsanity.com/paper/2308.07648/) (2023)
- [CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition](https://mlsanity.com/paper/2302.05499/) (2023)
- [Long-Tailed Anomaly Detection with Learnable Class Names](https://mlsanity.com/paper/2403.20236/) (2024)
- [Latent-based Diffusion Model for Long-tailed Recognition](https://mlsanity.com/paper/2404.04517/) (2024)
- [Long-tailed Recognition with Model Rebalancing](https://mlsanity.com/paper/2510.08177/) (2025)
- [LCReg: Long-Tailed Image Classification with Latent Categories based Recognition](https://mlsanity.com/paper/2309.07186/) (2023)
- [Learning from Neighbors: Category Extrapolation for Long-Tail Learning](https://mlsanity.com/paper/2410.15980/) (2024)

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

- [A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition](https://mlsanity.com/paper/2607.09832/) (2026)

## Abstract (arXiv)

Long-tailed data bias decision boundaries toward head classes and degrade tail class accuracy. Diffusion-based generative augmentation address this problem by generating additional data, while head-to-tail transfer further mitigate the generator bias inherit from long-tailed dataset. However, we show that while head-to-tail transfer helps balance the decision space of the classifier, it also induces latent non-local feature mixing that entangles inter-class features, causing decision boundary overlap and tail class distribution shift. To address this, we first identify the problem of boundary ambiguity and then propose Decision Boundary-aware Generation (DBG) framework, which promotes near-boundary representation learning by generating informative near-boundary samples. Overall, DBG rebalances the long-tailed dataset while yielding more separable decision space for long-tailed learning. Across standard long-tailed benchmarks, DBG consistently improves tail class and overall accuracy with less inter-class overlap. The code of DBG is available at https://github.com/keepdigitalabc-svg/DBG.