Knowledge distillation improves student model performance. However, using a larger teacher model does not necessarily result in better distillation gains due to significant architecture and output gaps with smaller student networks. To address this issue, we reconsider teacher outputs and find that categories with strong teacher confidence benefit distillation more, while those with weaker certainty contribute less. Thus, we propose Logits Uncertainty Distillation (LUD) to bridge this gap. We introduce category uncertainty weighting to consider the uncertainty in the teacher model’s predictions. A confidence threshold, based on the teacher’s predictions, helps construct a mask that discounts uncertain classes during distillation. Furthermore, we incorporate two Spearman correlation loss functions to align the logits of the teacher and student models. These loss functions measure the discrepancy between the models’ outputs at the category and sample levels. We also introduce adaptive dynamic temperature factors to optimize the distillation process. By combining these techniques, we enhance knowledge distillation results and facilitate effective knowledge transfer between teacher and student models, even when architectural differences exist. Extensive experiments on multiple datasets demonstrate the effectiveness of our method.

Object detection based on Knowledge Distillation can enhance the capabilities and performance of 5G and 6G networks in various domains, such as autonomous vehicles, smart surveillance, and augmented reality. The integration of object detection with Knowledge Distillation techniques is expected to play a pivotal role in realizing the full potential of these networks. This study presents Shared Knowledge Distillation (Shared-KD) as a solution to overcome optimization challenges caused by disparities in cross-layer features between teacher–student networks. The significant gaps in intermediate-level features between teachers and students present a considerable obstacle to the efficacy of distillation. To tackle this issue, we draw inspiration from collaborative learning in real-world education, where teachers work together to prepare lessons and students engage in peer learning. Building upon this concept, our innovative contributions in model construction are highlighted as follows: (1) A teacher knowledge augmentation module: this module is proposed to combine lower-level teacher features, facilitating the knowledge transfer from the teacher to the student. (2) A student mutual learning module is introduced to enable students to learn from each other, mimicking the peer learning concept in collaborative learning. (3) The Teacher Share Module combines lower-level teacher features: the specific functionality of the teacher knowledge augmentation module is described, which involves combining lower-level teacher features. (4) The multi-step transfer process can be easily optimized due to the minimal gap between the features: the proposed approach breaks down the knowledge transfer process into multiple steps, which can be easily optimized due to the minimal gap between the features involved in each step. Shared-KD uses simple feature losses without additional weights in transformation, resulting in an efficient distillation process that can be easily combined with other methods for further improvement. The effectiveness of our approach is validated through experiments on popular tasks such as object detection and instance segmentation.

Knowledge distillation has proven to be an effective technique for enhancing object detection performance. However, the presence of different detector types often results in a significant performance gap between teacher and student models. In this paper, we propose an Instance Mask Alignment (IMA) knowledge distillation framework for object detection. Our framework leverages knowledge transformation operations to reduce the teacher-student gap, leading to notable performance improvements. We introduce instance mask distillation, which incorporates mask information to enhance the student model’s ability to identify and focus on relevant regions or objects. Additionally, we introduce a cascade alignment module with instance standardization, utilizing an adaptive scale deflation module along the instance dimension. Through the integration of these cascade knowledge alignment modules, our proposed framework achieves substantial performance gains across various detector types. Extensive experiments conducted on the MS-COCO, PASCAL VOC and Cityscapes benchmarks demonstrate the effectiveness of our novel method, particularly its adaptability to heterogeneous detectors.