Exploring Dark Knowledge under Various Teacher Capacities and Addressing Capacity Mismatch

arXiv:2405.13078v1 Announce Type: new
Abstract: Knowledge Distillation (KD) could transfer the “dark knowledge” of a well-performed yet large neural network to a weaker but lightweight one. From the view of output logits and softened probabilities, this paper goes deeper into the dark knowledge provided by teachers with different capacities. Two fundamental observations are: (1) a larger teacher tends to produce probability vectors that are less distinct between non-ground-truth classes; (2) teachers with different capacities are basically consistent in their cognition of relative class affinity. Abundant experimental studies verify these observations and in-depth empirical explanations are provided. The difference in dark knowledge leads to the peculiar phenomenon named “capacity mismatch” that a more accurate teacher does not necessarily perform as well as a smaller teacher when teaching the same student network. Enlarging the distinctness between non-ground-truth class probabilities for larger teachers could address the capacity mismatch problem. This paper explores multiple simple yet effective ways to achieve this goal and verify their success by comparing them with popular KD methods that solve the capacity mismatch.



Source link
lol