NormKD: Normalized Logits for Knowledge Distillation
This work addresses a bottleneck in knowledge distillation for machine learning practitioners, offering an incremental improvement over existing logit-based methods.
The paper tackles the problem of inefficient knowledge transfer in logit-based knowledge distillation due to using a fixed temperature for all samples, proposing NormKD which customizes temperature per sample based on logit distribution. The result shows that NormKD significantly outperforms vanilla KD on CIFAR-100 and ImageNet with minimal extra cost and can match or exceed feature-based methods.
Logit based knowledge distillation gets less attention in recent years since feature based methods perform better in most cases. Nevertheless, we find it still has untapped potential when we re-investigate the temperature, which is a crucial hyper-parameter to soften the logit outputs. For most of the previous works, it was set as a fixed value for the entire distillation procedure. However, as the logits from different samples are distributed quite variously, it is not feasible to soften all of them to an equal degree by just a single temperature, which may make the previous work transfer the knowledge of each sample inadequately. In this paper, we restudy the hyper-parameter temperature and figure out its incapability to distill the knowledge from each sample sufficiently when it is a single value. To address this issue, we propose Normalized Knowledge Distillation (NormKD), with the purpose of customizing the temperature for each sample according to the characteristic of the sample's logit distribution. Compared to the vanilla KD, NormKD barely has extra computation or storage cost but performs significantly better on CIRAR-100 and ImageNet for image classification. Furthermore, NormKD can be easily applied to the other logit based methods and achieve better performance which can be closer to or even better than the feature based method.