面向高效不可迁移学习的自适应贝叶斯早退网络
Adaptive Bayesian Early-Exit Networks for Efficient Non-Transferable Learning
对视觉模型部署者而言，这是一种用动态早退分类器实现「源域可用、目标域失效」的访问控制手段：只需训练各出口分类器而不重训骨干网络，即可在推理时按出口位置区分源域与目标域数据，为模型版权保护与受限发布提供可复用范式。
原文依据 it enhances training efficiency by optimizing only the parameters of dynamic exit classifiers, bypassing the need to retrain the backbone
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论不可迁移学习（NTL）旨在通过在目标域数据上限制模型的泛化能力、同时保持其在源域上的效用，来实施使用限制。现有方法面临三大挑战：（1）由于需要重新训练骨干网络而导致训练效率低；（2）推理效率低；（3）僵硬地依赖一个横跨源域与目标域的共享、非自适应骨干网络。这种共享设置旨在最大化源域性能并最小化目标域性能，但由于源域与目标域之间存在重叠的类别，往往会引入优化冲突。本文提出一种新颖且高效的 NTL 方法，采用动态早退网络，命名为 ENL-DEE，它借助贝叶斯理论与动态神经网络来应对上述局限。我们定制的损失函数引导源域数据在网络较晚阶段退出，以最大化模型效用；而目标域数据则以非语义特征在较早阶段退出，从而确保有限的可迁移性。ENL-DEE 具有三项关键优势：（1）它仅优化动态出口分类器的参数，无需重新训练骨干网络，从而提升训练效率；（2）由于数据在网络中的不同出口分类器处退出，推理效率得到提升；（3）它通过为源域与目标域使用不同的参数集合来解决优化冲突，在源域上取得更高性能、在目标域上取得更低性能，从而强化 NTL。跨多种数据集与模型架构的大量实验验证了本方法的可扩展性、高效性与有效性。
英文原文摘要 1719 字符
Non-transferable learning (NTL) aims to enforce usage restrictions by limiting a model's generalization on target-domain data while maintaining its utility on the source domain. Current approaches face three major challenges: (1) low training efficiency due to retraining of the backbone network, (2) low inference efficiency, and (3) a rigid reliance on a shared, non-adaptive backbone network spanning both source and target domains. This shared setup, which aims to maximize source-domain performance and minimize target-domain performance, often introduces optimization conflicts due to overlapping class categories across source and target domains. In this paper, we propose a novel and efficient NTL approach using a dynamic Early-Exit Network, named ENL-DEE, which leverages Bayesian theory and dynamic neural networks to address these limitations. Our custom loss function guides source-domain data to exit at later stages of the network, maximizing model utility, while target-domain data exits earlier with non-semantic features, ensuring limited transferability. ENL-DEE offers three key advantages: (1) it enhances training efficiency by optimizing only the parameters of dynamic exit classifiers, bypassing the need to retrain the backbone; (2) it improves inference efficiency as data exits at various exit classifiers in the network; and (3) it resolves optimization conflicts by using distinct parameter sets for source and target domains, achieving higher performance on the source domain and lower performance on the target domain, thereby strengthening NTL. Extensive experiments across diverse datasets and model architectures validate the scalability, efficiency, and effectiveness of our approach.