EERO:面向有限预算高效分类的带弃权选项的早退方法
EERO: Early Exit with Reject Option for Efficient Classification with limited budget
AI总结:
本文提出EERO方法,将早退问题转化为带弃权选项的多分类器选择问题,通过指数权重聚合校准退出概率以保证固定预算,并在Cifar和ImageNet上验证了其在预算管理和准确率提升方面的有效性。
摘要:
先进机器学习模型日益增长的复杂性要求采用创新方法来有效管理计算资源。其中一种方法是早退策略,它通过提供一种机制来缩短较简单数据实例的处理路径,从而实现自适应计算。在本文中,我们提出了EERO,这是一种新方法,将早退问题转化为使用多个带弃权(不执行)选项的分类器的问题,以便更好地为每个实例选择退出头。我们使用指数权重聚合来校准在不同头部的退出概率,以保证固定的预算。我们考虑了贝叶斯风险、预算约束以及头部特定的预算消耗等因素。在使用ResNet-18模型和ConvNext架构在Cifar和ImageNet数据集上进行的实验结果表明,我们的方法不仅能有效管理预算分配,还能在过度思考场景中提高准确率。
英文摘要:
The increasing complexity of advanced machine learning models requires innovative approaches to manage computational resources effectively. One such method is the Early Exit strategy, which allows for adaptive computation by providing a mechanism to shorten the processing path for simpler data instances. In this paper, we propose EERO, a new methodology to translate the problem of early exiting to a problem of using multiple classifiers with reject option in order to better select the exiting head for each instance. We calibrate the probabilities of exiting at the different heads using aggregation with exponential weights to guarantee a fixed budget .We consider factors such as Bayesian risk, budget constraints, and head-specific budget consumption. Experimental results, conducted using a ResNet-18 model and a ConvNext architecture on Cifar and ImageNet datasets, demonstrate that our method not only effectively manages budget allocation but also enhances accuracy in overthinking scenarios.
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。