做长尾识别或类别不平衡任务的开发者，终于可以告别调参噩梦了——SAMN 直接省去超参数搜索，即插即用还能涨点，建议试试。
长尾识别是深度学习中的难题，两阶段解耦范式中的自适应范数缩放技术虽有效，但依赖超参数调优，性能波动大。本文提出 Self-Adaptive Monotonic Normalization (SAMN)，通过 Pool Adjacent Violators Algorithm 直接对每类权重范数施加单调性约束，无需参数正则化，彻底消除超参数敏感性。SAMN 是一种通用策略，可无缝集成到其他方法中提升性能。在多个基准数据集上，SAMN 显著提升长尾识别准确率，常达到最优结果。
Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition
Long-tailed recognition poses a significant challenge for deep learning. The two-stage decoupling paradigm, which separates representation learning from classifier retraining, offers a promising solution. During the classifier retraining stage, adaptive norm rescaling is a popular technique. It adjusts the per-class weight norms via parameter regularization, which inevitably introduces hyperparameters. However, many studies report that long-tailed recognition is sensitive to these hyperparameters, as their setup significantly impacts performance. In this paper, we first provide a class-conditional distribution perspective to support norm rescaling methods. Furthermore, we propose a simple but effective approach called Self-Adaptive Monotonic Normalization (SAMN). SAMN avoids the need for parameter regularization. It directly enforces monotonicity on per-class weight norms using the Pool Adjacent Violators Algorithm, making the method hyperparameter-friendly. SAMN is a universal strategy that integrates seamlessly with other methods for enhanced performance. Experiments on benchmark datasets demonstrate that our method significantly boosts long-tailed recognition performance, often achieving state-of-the-art results.