arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.14130cs.CV
收藏

利用角分布改进知识蒸馏

Leveraging Angular Distributions for Improved Knowledge Distillation

Arizona State University(亚利桑那州立大学)

Eun Som Jeon, Hongjun Choi, Ankita Shukla, Pavan Turaga

摘要:

知识蒸馏作为一种广泛的方法,已经导致轻量级和内存高效模型的发展,使用具有大容量的预训练模型(教师网络)来训练较小的模型(学生网络)。最近,已经研究了利用中间层的激活图作为知识源的知识蒸馏的附加变型。通常,在计算机视觉应用中,可以看到由更高容量模型学习的特征激活包含更丰富的知识,突出完整的对象,同时较少关注背景。基于这一观察,我们利用教师的双重能力来准确区分积极(与目标对象相关)和消极(不相关)区域。提出了一种新的蒸馏损失函数,称为基于角裕度的蒸馏损失。AMD损失通过将正负特征投影到超球体上来使用正负特征之间的角距离,这是由许多特征提取器中看到的近角分布所激发的。然后,我们创建一个更注意的功能,是有角度地分布在超球面上,通过引入一个角余量的积极的功能。从教师网络转移这些知识使学生模型能够为教师利用积极和消极特征的更高辨别力,从而提取出更好的学生模型。在四个公共数据集上对所提出的方法进行了评估。此外,我们表明,所提出的方法具有优势,与其他学习技术,如使用细粒度的功能,增强,和其他蒸馏方法的兼容性。

英文摘要:

Knowledge distillation as a broad class of methods has led to the development of lightweight and memory efficient models, using a pre-trained model with a large capacity (teacher network) to train a smaller model (student network). Recently, additional variations for knowledge distillation, utilizing activation maps of intermediate layers as the source of knowledge, have been studied. Generally, in computer vision applications, it is seen that the feature activation learned by a higher capacity model contains richer knowledge, highlighting complete objects while focusing less on the background. Based on this observation, we leverage the dual ability of the teacher to accurately distinguish between positive (relevant to the target object) and negative (irrelevant) areas. We propose a new loss function for distillation, called angular margin-based distillation (AMD) loss. AMD loss uses the angular distance between positive and negative features by projecting them onto a hypersphere, motivated by the near angular distributions seen in many feature extractors. Then, we create a more attentive feature that is angularly distributed on the hypersphere by introducing an angular margin to the positive feature. Transferring such knowledge from the teacher network enables the student model to harness the higher discrimination of positive and negative features for the teacher, thus distilling superior student models. The proposed method is evaluated for various student-teacher network pairs on four public datasets. Furthermore, we show that the proposed method has advantages in compatibility with other learning techniques, such as using fine-grained features, augmentation, and other distillation methods.

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。

↑