AME：用于鲁棒视觉语言蒸馏的对齐流形熵
AME: Aligned Manifold Entropy for Robust Vision-Language Distillation
AI总结：
针对视觉语言蒸馏中数据不足导致泛化差的问题，提出对齐流形熵（AME）方法，通过在共享流形上最小化熵实现跨模态特征压缩，无需修改骨干网络即可作为即插即用模块提升鲁棒性与泛化能力。
摘要：
知识蒸馏是一种历史悠久的知识迁移技术，并且随着大型视觉语言模型（VLMs）的近期出现而重新受到关注。然而，视觉语言知识蒸馏通常需要充足的训练数据，才能在与高预测不确定性相关的模糊或边界邻近表示的样本上实现鲁棒的泛化。关键在于，在现实场景中，收集此类大规模、特定任务的数据进行训练通常是不切实际的。为了应对由不确定性与跨模态特征表示纠缠所引发的这一重大挑战，我们提出了用于鲁棒视觉语言蒸馏的对齐流形熵（AME），旨在现实条件下实现鲁棒的泛化。AME在重新配置的共享流形上应用熵最小化，其中多模态数据（即图像和文本）通过一对投影函数进行桥接，有助于跨模态特征表示的结构压缩。这使得在低数据状态下能够进行鲁棒的知识蒸馏，同时无需对骨干网络进行架构修改。因此，它可以作为一个即插即用模块，兼容广泛的视觉语言蒸馏框架。值得注意的是，我们的理论分析表明，将知识蒸馏与共享流形上的熵最小化相结合，会产生更紧致的一般化误差界。跨不同蒸馏架构和训练设置的大量实验表明，AME持续促进鲁棒的知识蒸馏，从而在广泛的下游任务中实现卓越的泛化性能。
英文摘要：
Knowledge distillation is a long-established technique for knowledge transfer, and has regained attention in the context of the recent emergence of large vision-language models (VLMs). However, vision-language knowledge distillation often requires sufficient training data to achieve robust generalization on amples with ambiguous or boundary-adjacent representations, which are associated with high predictive uncertainty. Critically, collecting such large-scale, task-specific data for training is often impractical in real-world scenarios. To address this major challenge arising from the entanglement of uncertainty and cross-modal feature representation, we propose Aligned Manifold Entropy for Robust Vision-Language Distillation (AME), aiming to achieve robust generalization under real-world conditions. AME applies entropy minimization over a reconfigured shared manifold, where multi-modal data (i.e., image and text) are bridged through a pair of projection functions, conducive to structural compression for cross-modal feature representations. This enables robust knowledge distillation under low-data regimes, while requiring no architectural modifications to the backbone. As a result, it can serve as a plug-and-play module compatible with a wide range of vision-language distillation frameworks. Notably, our theoretical analysis reveals that integrating knowledge distillation with entropy minimization over the shared manifold leads to a tighter generalization error bound. Extensive experiments across diverse distillation architectures and training settings demonstrate that AME consistently facilitates robust knowledge distillation, resulting in superior generalization performance across a wide spectrum of downstream tasks.
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。
