# BD-KD: Balancing the Divergences for Online Knowledge Distillation

Source: [BD-KD: Balancing the Divergences for Online Knowledge Distillation](<https://www.sota2.com/research/paper/68fa763e1e209131cea6c124>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:50:30.323Z

Authors: Ibtihel Amara, Nazanin Sepahvand, Brett H. Meyer, Warren J. Gross, James J. Clark

Published: 2022-12-25T22:27:32.000Z

## Abstract

We address the challenge of producing trustworthy and accurate compact models for edge devices. While Knowledge Distillation (KD) has improved model compression in terms of achieving high accuracy performance, calibration of these compact models has been overlooked. We introduce BD-KD (Balanced Divergence Knowledge Distillation), a framework for logit-based online KD. BD-KD enhances both accuracy and model calibration simultaneously, eliminating the need for post-hoc recalibration techniques, which add computational overhead to the overall training pipeline and degrade performance. Our method encourages student-centered training by adjusting the conventional online distillation loss on both the student and teacher losses, employing sample-wise weighting of forward and reverse Kullback-Leibler divergence. This strategy balances student network confidence and boosts performance. Experiments across CIFAR10, CIFAR100, TinyImageNet, and ImageNet datasets, and various architectures demonstrate improved calibration and accuracy compared to recent online KD methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2212.12965>)

[PDF](<https://arxiv.org/pdf/2212.12965.pdf>)