揭示数据增强的两面性：一种基于非对称蒸馏的开放集识别双赢解决方案
Revealing the Two Sides of Data Augmentation: An Asymmetric Distillation-based Win-Win Solution for Open-Set Recognition
AI总结：
本文针对数据增强在提升封闭集识别的同时损害开放集识别的问题，提出非对称蒸馏框架，并结合互信息损失与选择性重标记，在多个数据集上取得优于SOTA的开放集识别性能。
摘要：
本文揭示了数据增强的两面性：封闭集识别性能的提升与开放集识别性能的显著下降相关。通过实证研究，我们发现基于多样本的增强会导致特征判别力降低，从而削弱开放集判别标准。尽管知识蒸馏可能通过模仿损害特征，但具有模糊语义的混合特征会阻碍蒸馏过程。为此，我们提出了一种非对称蒸馏框架，通过向教师模型输入额外的原始数据来扩大教师的优势。此外，我们利用联合互信息损失和选择性重标记策略来缓解困难混合样本的影响。我们的方法成功缓解了开放集性能的下降，在Tiny-ImageNet数据集上比SOTA方法AUROC高出2%~3%，在大规模数据集ImageNet-21K上的实验证明了我们方法的泛化能力。
英文摘要：
In this paper, we reveal the two sides of data augmentation: enhancements in closed-set recognition correlate with a significant decrease in open-set recognition. Through empirical investigation, we find that multi-sample-based augmentations would contribute to reducing feature discrimination, thereby diminishing the open-set criteria. Although knowledge distillation could impair the feature via imitation, the mixed feature with ambiguous semantics hinders the distillation. To this end, we propose an asymmetric distillation framework by feeding teacher model extra raw data to enlarge the benefit of teacher. Moreover, a joint mutual information loss and a selective relabel strategy are utilized to alleviate the influence of hard mixed samples. Our method successfully mitigates the decline in open-set and outperforms SOTAs by 2%~3% AUROC on the Tiny-ImageNet dataset and experiments on large-scale dataset ImageNet-21K demonstrate the generalization of our method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
