针对长尾识别中样本难易差异，提出动态调整边距的新损失函数。
Difficulty-aware Balancing Margin Loss for Long-tailed Recognition
- 按类别和实例难度分别设置边距，缓解数据不均衡影响。
- 在多个长尾数据集上显著提升识别准确率，尤其改善少数类性能。
- 适合需要提升小样本类别识别能力的研究与应用。
当使用严重不均衡的数据训练深度神经网络时，模型往往难以准确识别样本数量极少的类别。以往长尾识别研究主要基于已知样本分布，在类别层面处理分类难度差异，但忽略了每个类别内部实例间的难易变化。本文提出一种难度感知的平衡边距（DBM）损失，同时考虑类别不平衡和实例难度差异。DBM损失包含两部分：类别级边距以缓解频次偏差带来的学习偏倚；实例级边距则根据每个困难正样本的个体难度动态分配。该方法通过为更难样本设置更大边距，增强类别可区分性。所提方法可无缝集成现有方法，并在多个长尾识别基准上持续提升性能。
原文摘要 · Abstract (English)
When trained with severely imbalanced data, deep neural networks often struggle to accurately recognize classes with only a few samples. Previous studies in long-tailed recognition have attempted to rebalance biased learning using known sample distributions, primarily addressing different classification difficulties at the class level. However, these approaches often overlook the instance difficulty variation within each class. In this paper, we propose a difficulty-aware balancing margin (DBM) loss, which considers both class imbalance and instance difficulty. DBM loss comprises two components: a class-wise margin to mitigate learning bias caused by imbalanced class frequencies, and an instance-wise margin assigned to hard positive samples based on their individual difficulty. DBM loss improves class discriminativity by assigning larger margins to more difficult samples. Our method seamlessly combines with existing approaches and consistently improves performance across various long-tailed recognition benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。