On Explaining Knowledge Distillation: Measuring and Visualising the Knowledge Transfer Process
This work addresses the problem of interpretability in knowledge distillation for researchers and practitioners, though it is incremental as it builds on existing explanation methods.
The paper tackled the challenge of explaining the opaque knowledge transfer process in knowledge distillation by proposing UniCAM, a gradient-based visual explanation method, and two novel metrics (FSS and RS) to quantify distilled knowledge relevance, demonstrating their effectiveness on datasets like CIFAR10, ASIRRA, and Plant Disease.
Knowledge distillation (KD) remains challenging due to the opaque nature of the knowledge transfer process from a Teacher to a Student, making it difficult to address certain issues related to KD. To address this, we proposed UniCAM, a novel gradient-based visual explanation method, which effectively interprets the knowledge learned during KD. Our experimental results demonstrate that with the guidance of the Teacher's knowledge, the Student model becomes more efficient, learning more relevant features while discarding those that are not relevant. We refer to the features learned with the Teacher's guidance as distilled features and the features irrelevant to the task and ignored by the Student as residual features. Distilled features focus on key aspects of the input, such as textures and parts of objects. In contrast, residual features demonstrate more diffused attention, often targeting irrelevant areas, including the backgrounds of the target objects. In addition, we proposed two novel metrics: the feature similarity score (FSS) and the relevance score (RS), which quantify the relevance of the distilled knowledge. Experiments on the CIFAR10, ASIRRA, and Plant Disease datasets demonstrate that UniCAM and the two metrics offer valuable insights to explain the KD process.