An adaptive block-activation ViT and a mutual-information multi-teacher distillation variant achieve state-of-the-art speed/accuracy trade-offs on six UAV tracking benchmarks.
How to Train the Teacher Model for Effective Knowledge Distillation
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Recently, it was shown that the role of the teacher in knowledge distillation (KD) is to provide the student with an estimate of the true Bayes conditional probability density (BCPD). Notably, the new findings propose that the student's error rate can be upper-bounded by the mean squared error (MSE) between the teacher's output and BCPD. Consequently, to enhance KD efficacy, the teacher should be trained such that its output is close to BCPD in MSE sense. This paper elucidates that training the teacher model with MSE loss equates to minimizing the MSE between its output and BCPD, aligning with its core responsibility of providing the student with a BCPD estimate closely resembling it in MSE terms. In this respect, through a comprehensive set of experiments, we demonstrate that substituting the conventional teacher trained with cross-entropy loss with one trained using MSE loss in state-of-the-art KD methods consistently boosts the student's accuracy, resulting in improvements of up to 2.6\%.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking
An adaptive block-activation ViT and a mutual-information multi-teacher distillation variant achieve state-of-the-art speed/accuracy trade-offs on six UAV tracking benchmarks.