Improving Knowledge Distillation via Head and Tail Categories

Knowledge distillation (KD) is a technique that transfers "dark knowledge" from a deep teacher network (teacher) to a shallow student network (student). Despite significant advances in KD, existing work has not adequately mined two crucial types of knowledge: 1) the knowledge of head categories, which represents the relationship between the target category and its similar categories. Our findings reveal that this highly similar (complex) knowledge is essential for improving student's performance; and 2) the effectively utilized knowledge of tail categories. Existing studies often treat the non-target categories collectively without sufficiently considering the effectiveness of knowledge from tail categories. To tackle these challenges, we reformulate classical KD (ReKD) into two components: Top- K Inter-class Similar Distillation (TISD) and Non-Top- K Inter-class Discriminability (NTID). Firstly, TISD captures and imparts the knowledge of head categories to the student. Our experimental results have verified that TISD is particularly effective in transferring the knowledge of head categories, even in fine-grained dataset classification. Secondly, we theoretically show that the weighting coefficient of NTID increases with the probability of Top- K , leading to stronger suppression of knowledge transfer for tail categories. This observation explains why difficult samples are more informative than simple ones. To better utilize both types of knowledge, we optimize both TISD and NTID using different weighting coefficients, thereby enhancing the student's ability to learn this valuable knowledge from both head and tail categories. Furthermore, our extensive experimental results demonstrate that ReKD achieves state-of-the-art performance on various image classification datasets, including CIFAR-100, Tiny-ImageNet, and ImageNet-1K, as well as object detection and instance segmentation using the MS-COCO dataset.