Decision Boundary-aware Generation for Long-tailed Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSimilar Papers 제목 키워드 기반
Solving The Long-Tailed Problem via Intra- and Inter-Category Balance
Benchmark datasets for visual recognition assume that data is uniformly distributed, while real-world datasets obey long-tailed distribution. Current approaches handle the long-tailed problem to transform the long-tailed…
Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment
Real-world data distributions are often highly skewed. This has spurred a growing body of research on long-tailed recognition, aimed at addressing the imbalance in training classification models. Among the methods studie…
Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. …
DiversitySaVe-TAG: Semantic-aware Vicinal Risk Minimization for Long-Tailed Text-Attributed Graphs
Real-world graph data often follows long-tailed distributions, making it difficult for Graph Neural Networks (GNNs) to generalize well across both head and tail classes. Recent advances in Vicinal Risk Minimization (VRM)…
ClassificationData AugmentationLanguage ModelingLanguage Modelling+3RICASSO: Reinforced Imbalance Learning with Class-Aware Self-Supervised Outliers Exposure
In real-world scenarios, deep learning models often face challenges from both imbalanced (long-tailed) and out-of-distribution (OOD) data. However, existing joint methods rely on real OOD data, which leads to unnecessary…