Local Correlation Consistency for Knowledge Distillation

59 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Patch-based Knowledge Distillation for Lifelong Person Re-Identification (2022, methodology): “Li et al. [33] and Kim et al. [26] extend logit distillation and relation distillation to patch-level, but their methods generate patch features from a regular grid without any selection, bringing the dilemma of high computational cost or loss of fine-grained information.”
Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space (2020, unknown): “Besides, some approaches also implement distillation on the intermediate features via various manners, such as hints [22], distribution of features [10] and local correlations [14].”